CN109121021A - A kind of generation method of Video Roundup, device, electronic equipment and storage medium - Google Patents
A kind of generation method of Video Roundup, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109121021A CN109121021A CN201811137931.0A CN201811137931A CN109121021A CN 109121021 A CN109121021 A CN 109121021A CN 201811137931 A CN201811137931 A CN 201811137931A CN 109121021 A CN109121021 A CN 109121021A
- Authority
- CN
- China
- Prior art keywords
- video
- roundup
- target fragment
- excellent degree
- video clip
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XDDAORKBJWWYJS-UHFFFAOYSA-N glyphosate Chemical compound OC(=O)CNCP(O)(O)=O XDDAORKBJWWYJS-UHFFFAOYSA-N 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003860 storage Methods 0.000 title claims abstract description 28
- 239000012634 fragment Substances 0.000 claims abstract description 60
- 238000005520 cutting process Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims description 17
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000005291 magnetic effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 208000001491 myopia Diseases 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013467 fragmentation Methods 0.000 description 2
- 238000006062 fragmentation reaction Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010034719 Personality change Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000386 athletic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012887 quadratic function Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The embodiment of the invention discloses a kind of generation method of Video Roundup, device, electronic equipment and storage mediums, this method comprises: by according to preset slice rule by video slicing at video clip, wherein, the slice rule is determined according to video genre and content；It predicts the excellent degree of the video clip, and target fragment is determined according to the excellent degree of the video clip；Video Roundup is generated according to the target fragment, slice rule can be determined automatically according to video genre and content, further cutting video clip makes the collection of choice specimens according to the excellent degree of video clip, solves the problems, such as low prior art production Video Roundup timeliness, high labor cost and low output.
Description
Technical field
The present invention relates to video technique field more particularly to a kind of generation method of Video Roundup, device, electronic equipment and
Storage medium.
Background technique
As the end equipment that reaches its maturity and move of 4G technology and development of Mobile Internet technology is largely popularized, user is more
It is growing day by day easily to obtain information, information, the demand of amusement.Rhythm of life accelerates and the status of playtime fragmentation,
So that short-sighted frequency --- using new media as communication channel, transmitting carrier of the duration within 5 minutes is largely broken by occupying user
The mode of piece time is become common practise.And the short of wonderful, bloom moment or personalized customization segment is intercepted from long video
Video production mode just meets user and gives pleasure in the time of fragmentation to popular movie and television play works, athletics sports class, variety
The ornamental demand of the happy isometric video resource of class also complies with user's expectation at present and is quickly obtained entertainment resource or can obtain individual character
Change the consumption habit of entertainment resource.
Currently, the video highlight collection of choice specimens of major video platform is to be regarded by the video clipping teacher of a large amount of professions in magnanimity mostly
In frequency library, wonderful is defined by artificial means, is positioned, editing, spliced processing result.When its result has
Effect property low, high labor cost, the characteristic of Video Roundup low output, the audiovisual entertainment for being unable to satisfy such huge user group need
It asks, can not also cover so rich and varied short-sighted frequency content requirements in time.Artificial editing can only carry out editing according to plot, interior
Hold single, the collection of choice specimens generation technique robustness of customization is poor, and the Video Roundup style type of production is less, it is difficult to meet user
Demand.
Summary of the invention
The present invention provides generation method, device, electronic equipment and the storage medium of a kind of Video Roundup, solves existing skill
The problem of low Video Roundup timeliness, high labor cost, low output are made in art.
In a first aspect, the embodiment of the invention provides a kind of generation methods of Video Roundup, comprising:
According to preset slice rule cutting video clip from target video, wherein the slice rule is according to view
Frequency type and content determine；
It predicts the excellent degree of the video clip, and target fragment is determined according to the excellent degree of the video clip；
Video Roundup is generated according to the target fragment.
Second aspect, the embodiment of the invention also provides a kind of generating means of Video Roundup, comprising:
Video clip cutting module, for according to preset slice rule cutting video clip from target video, wherein
The slice rule is determined according to video genre and content；
Target fragment determining module, for predicting the excellent degree of the video clip, and according to the video clip
Excellent degree determines target fragment；
Video Roundup generation module, for generating Video Roundup according to the target fragment.
The third aspect, the embodiment of the invention also provides a kind of electronic equipment, the electronic equipment includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes a kind of generation method of Video Roundup as described in any embodiment of that present invention.
Fourth aspect, it is described the embodiment of the invention also provides a kind of storage medium comprising computer executable instructions
Computer executable instructions as computer processor when being executed for executing a kind of view as described in any embodiment of that present invention
The generation method of the frequency collection of choice specimens.
The embodiment of the present invention by according to preset slice rule by video slicing at video clip, wherein the slice
Rule is determined according to video genre and content；Predict the excellent degree of the video clip, and according to the video clip
Excellent degree determines target fragment；Video Roundup is generated according to the target fragment, it can be automatically according to video genre and content
Determine that slice rule, further cutting video clip make the collection of choice specimens according to the excellent degree of video clip, solve the prior art
The problem of making low Video Roundup timeliness, high labor cost and low output.
Detailed description of the invention
Fig. 1 is the flow chart of the generation method of one of the embodiment of the present invention one Video Roundup；
Fig. 2 is the flow chart of the generation method of one of the embodiment of the present invention two Video Roundup；
Fig. 3 is that the crucial moment point of the cutting bout segment in one of embodiment of the present invention two Basketball Match video shows
It is intended to；
Fig. 4 is Robust Deep RankNet in the excellent degree judgment models of one of embodiment of the present invention two training
The structure chart of network；
Fig. 5 is the schematic diagram of loss function in the excellent degree judgment models of one of embodiment of the present invention two training；
Fig. 6 is the structural schematic diagram of the generating means of one of the embodiment of the present invention three Video Roundup；
Fig. 7 is the structural schematic diagram of one of the embodiment of the present invention four electronic equipment.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart of the generation method for Video Roundup that the embodiment of the present invention one provides, and the present embodiment can fit
The case where for Video Roundup production, this method can be executed by the generating means of Video Roundup, which can be using hard
Part and/or software realization, are configured in electronic equipment, and this method specifically comprises the following steps:
S110, according to preset slice rule cutting video clip from target video, wherein the slice rule is root
It is determined according to video genre and content.
Target video can be user and make material video used in Video Roundup.For example, it is desired to which editing goes out from A video
Segment makes Video Roundup, then A video can be for target video.Slice rule can be it is preset for indicate how
The rule of cutting segment is carried out for target video, can specifically be determined according to video genre and content.For example, video genre is
Match video, and video of competing has some rules and rule, for example exchange ball is weighed, in change sides etc. or even game content
Scenes, the users such as some specific scene processes, such as foul penalty shot can be according to particular video frequency type and content production phases
Piece rule deeply concerned, may further cut out video clip according to the slice rule from target video.
The excellent degree of S120, the prediction video clip, and target is determined according to the excellent degree of the video clip
Segment.
Specifically, the excellent degree of prediction video clip can be according to preparatory trained model, classifier or other
Discriminant function etc..Illustratively, an available numerical value corresponding with excellent degree when each video clip is predicted, foundation should
Numerical value may determine that the excellent degree of different video segment, determine target fragment according further to excellent degree.Wherein, target patch
Section can be the video clip to be included in the Video Roundup that user makes and illustratively be syncopated as in target video
In video clip, excellent degree can be higher than to the video clip of given threshold as target fragment.
S130, Video Roundup is generated according to the target fragment.
On the basis of above-mentioned determining target fragment, the target fragment is assembled into a Video Roundup, certainly, in life
When at Video Roundup, it can be arranged according to time sequencing of the target fragment in target video, it can also be according to target patch
The sequence of the excellent degree of section is gathered or other generate the rule of the collection of choice specimens, herein with no restrictions.User can pass through tune
The rule that whole Video Roundup generates, it is ensured that the discontinuous camera lens of the collection of choice specimens is visually softer coherent.
Optionally, before according to the target fragment generation Video Roundup, further includes:
Content and/or temporal characteristics according to the target fragment are added corresponding with target fragment in the target fragment
Characteristic information,
Correspondingly, described generate Video Roundup according to the target fragment, comprising:
Video Roundup is generated according to the target fragment and corresponding characteristic information.
Wherein, the content characteristic of target fragment can be information representative relevant to content in target fragment, exemplary
, in Basketball Match every people's dunk shot, the goal etc. of super remote three-point shot can represent the feature of the target fragment content.Target patch
The feature of section can be target fragment in target video or the process-time point of video match, such as Section four in Basketball Match
Last final hit in 1 minute, the feature for showing hat-trick etc. with time correlation on the 10th minute in football match.Certainly, may be used
To be all to add time and content characteristic in the corresponding characteristic information of target fragment, further according to these characteristic informations into
The generation of row Video Roundup, for example can the collection of choice specimens directly be made according to time tandem.During specific implementation, due to
Video clip includes highly dynamic vision content, and method that C3D is combined with CNN can be used as feature extractor, into one
Step captures the space content and time behavioral characteristics of video clip.
The technical solution of the present embodiment, by according to preset slice rule by video slicing at video clip, wherein institute
Stating slice rule is determined according to video genre and content；Predict the excellent degree of the video clip, and according to the video
The excellent degree of segment determines target fragment；Video Roundup is generated according to the target fragment, it can be automatically according to video genre
Determine that slice rule, further cutting video clip are watched a large amount of materials without special editor, and therefrom selected with content
Meet the segment of collection of choice specimens requirement.The collection of choice specimens is made according to the excellent degree of video clip, solves prior art production Video Roundup
Timeliness is low, high labor cost and the problem of low output.Meanwhile cooperating certain slice regular and judging the model of excellent degree
The Video Roundup of any style type can be made.Furthermore it is possible to rapidly and accurately according to the demand of user, for example compare competition rules
Segment is then intercepted in long video, then wonderful is generated short-sighted frequency by the excellent degree of automatic Prediction, meet a large amount of use in time
The short video-see demand at family.
Embodiment two
Fig. 2 is a kind of flow chart of the generation method of Video Roundup provided by Embodiment 2 of the present invention, in above-described embodiment
On the basis of, optionally, the video genre includes match video, correspondingly, the described method includes:
S210, according to round rule from match video in cutting bout segment.
It therefore, can be with pre-production than grand sports meet there are laws of the game or some rounds rule for video of competing
The good round rule for different matches, can then proceed in these regular cutting video clips, i.e. bout segment.
Optionally, the round rule includes at least one of: halfway line, score, exchange ball are crossed in baseline service
Power and countdown in 24 seconds terminate.Illustratively, if it is ball game, round rule be can be for different ball specific
Laws of the game and the production such as bout rule.
The excellent degree of S220, the prediction bout segment, and target is determined according to the excellent degree of the bout segment
Segment.
In match video in the present embodiment, predict that the excellent degree of bout segment can be by preparatory trained essence
Color Degree Model calculates, and can specifically be ranked up the excellent degree of all calculated bout segments, then therefrom
The higher bout segment of excellent degree is selected as target fragment.
S230, Video Roundup is generated according to the target fragment.
Optionally, according to round rule from match video in cutting bout segment, comprising:
The time range of bout segment is determined by the round rule；
The bout segment is syncopated as from the match video according to the time range.
Specifically, when according to round rule cutting bout segment, it is thus necessary to determine that go out bout segment and compete in target
The location of in video, i.e., 30s is arrived before the bout segment of score can be scoring moment in time range, such as match video
Complete a time range of scoring moment.One bout segment can be just syncopated as according to time range in this way.
By taking Basketball Match as an example, laws of the game include: baseline service, cross halfway line, score, exchange ball power, fall to count within 24 seconds
When terminate, specifically in Different Rule cutting bout segment, determine that the process of time range or method can be different.
(1) baseline service and exchange ball power time point determine
According to the rule of Basketball Match, ball power is handed over when another party executes baseline service after any one team scores and on field
When changing, shot clock will restart timing.Therefore, OCR algorithm (Optical Character can be passed through
Recognition, optical character identification) extract picture in timer parameter can when timer parameter becomes 24 seconds again
This frame is determined as the exchange of ball power or baseline service moment.Correspondingly, the bout segment of corresponding time range, can be from
The exchange of ball power or the bout segment before or after the baseline service moment in preset duration.
(2) score time point determines
When there is scoring event generation, the score in picture, which is shown, to change, and can be extracted in picture by OCR
Score region parameter is judged to having scoring event to have occurred and that when the score of either side changes, and determines score
Moment.Correspondingly, the bout segment of complete scoring event can be obtained by extending preset time forward.Such as
The extraction of fragment section can previously extend 2 seconds according to the score completion moment and obtain.
(3) it is determining to spend halfway line time point
The picture in video can be differentiated by deep learning network, prediction obtains crossing half-court in video pictures
The line moment.It specifically can be and more than half long line moment judged according to trained prediction model in advance, correspondingly, can also should
Before or after moment in a period of time video clip as bout segment.
Illustratively, for the crucial moment point in Basketball Match video as shown in 3 figures, Fig. 3 is in the embodiment of the present invention two
A kind of crucial moment point schematic diagram of cutting bout segment in Basketball Match video, crucial case point can recycle in match
It is existing.
Optionally, the excellent degree of the video clip is determined according to preset excellent degree judgment models, described default
The sample datas of excellent degree judgment models include: the wonderful and non-wonderful for belonging to same video.
During training is embodied, since video clip includes highly dynamic vision content, for how to capture
The space content and time behavioral characteristics of video-frequency band are most important, and C3D network and CNN network phase can be used in the present embodiment
In conjunction with method as feature extractor.Illustratively, feature extraction can be carried out (in Fig. 4 to static class variable using CNN
CNN feature), wherein backbone using Resnet50 as back bone network.C3D replaces passing by used time blank coil lamination
The 2D convolutional layer of system, while the picture centre network architecture of AlexNet can be expanded to visual domain, it carries out in multiple videos point
Generic task, and (the C3D feature in Fig. 4) is extracted to video features.Specifically, can use 3D convolutional Neural net
Network indicates each segment of video, and these video clips include the dynamic space-time visual signature of video height.
Furthermore it is also possible to contextual information is added for video clip, the metamessage and visual signature as video clip
Supplemental information.Specific characteristic information may include class label, the semantic embedding and position feature of video tab etc..It is exemplary
, for position feature, timestamp of the target fragment in target video, sum of ranks relative position etc. can be used.
Illustratively, in the training process of model, a pair of of video clip can be inputted into Robust Deep simultaneously
The network neural network of RankNet, training objective are that the corresponding score of featured videos segment is corresponding higher than non-featured videos segment
Score.If the comparison of excellent degree is to deposit due to more arbitrary two video clips, such as from different videos
In problem, therefore a pair of of the video clip for belonging to same video inputted, one is featured videos segment, another is non-essence
Color video clip.A sequence is constructed on video segment data collection D, so that featured videos sample score rank is greater than non-excellent
Video sample.
Fig. 4 is Robust Deep RankNet in the excellent degree judgment models of one of embodiment of the present invention two training
The structure chart of network, s in Fig. 4+(GIF Segment) and s-(Non-GIF Segment) can respectively represent excellent and non-excellent
Video clip.The network structure of Robust Deep RankNet as shown in Figure 4 can choose 2 full connection hidden layers
(Fully conneted Layer), each layer can connect RELU activation primitive below.512 nodes of first layer, the second layer
128 nodes.The final prediction interval (Scoring Layer) for exporting h (s) (in Fig. 4) is a simple single linear unit,
Predict nonstandardized technique scalar score.Wherein, Ranking loss is the loss that model training carries out excellent degree sequence in the process
Function.In order to be further reduced the variance of model, during model training, the multiple models of training can be initialized.In addition,
During training, in order to accelerate weight to update, Nesterov ' s Accelerated Momentum (NAM) can be used
Carry out gradient updating.
Test phase, model only requires the single video clip of input, and obtains view by one mapping function h of model learning
The corresponding score of frequency segment, the score list of all video clips, Ke Yijin can be got by traversing all video clips
One step makes the sequence of excellent degree.It, can be by obtained in the different training patterns in the case where multiple training patterns
Score about excellent degree is averaging the score as the video clip.
Optionally, the preset excellent degree judgment models are that the loss function training based on Huber loss obtains.
Specifically, following formula can be used and calculate loss function l during training patternp(s+, s-):
lp(s+, s-)=max (0,1-h (s+)+h(s-))p；
In the specific implementation process, loss function L can first be set1(L1Rank loss) and L2(L2Rank loss),
In, L1It can be linear function, L2It can be quadratic function.Due to bigger in positive negative difference, decline closer to 1, loss slower
In the case of, the effect of models fitting is better.Fig. 5 is damaged in the excellent degree judgment models of one of embodiment of the present invention two training
Lose the schematic diagram of function.As shown in figure 5, L1When simulating the loss in normal range (NR) (0,1), decline too fast, it is clear that L1's
Loss function inaccuracy.Although L2It is showed well in the fitting of this point, but works as and the case where abnormal conditions (< 0) occur
Under, obtained loss can directly become to be even more than very much range greatly.Therefore, in the present embodiment, L can be combined1And L2It obtains certainly
The Huber loss function of adaptation:
Where u=1-h (s+)+hs-)；
As can be seen from Figure 5 the fitness of Huber loss is more preferable, and the robustness of the model trained is more preferable.It is exemplary
, in order to consider the different quality degree of user-generated content, the excellent degree of the GIF in social media can be encoded to loss
In function, to meet the Video Roundup of user's efficient editing featured videos content and different-style personalization.
The technical solution of the present embodiment, according to round rule cutting bout segment, utilizes in ball game video
Preparatory trained excellent degree judgment models obtain target fragment, further make Video Roundup.Furthermore it is possible to be regarded from magnanimity
In frequency material, efficient editing goes out to meet the featured videos editing of user demand or the customized demand of user, and solves ball fortune
Personnel's high-speed motion in dynamic, the problems such as how crowded people is, block mutually, multi-cam and camera lens frequently move.
Embodiment three
Fig. 6 is a kind of structural schematic diagram of the generating means for Video Roundup that the embodiment of the present invention three provides, such as Fig. 6 institute
Show, described device includes:
Video clip cutting module 610 is used for according to preset slice rule cutting video clip from target video,
In, the slice rule is determined according to video genre and content；
Target fragment determining module 620, for predicting the excellent degree of the video clip, and according to the video clip
Excellent degree determine target fragment；
Video Roundup generation module 630, for generating Video Roundup according to the target fragment.
Optionally, the video genre includes match video, correspondingly,
The video clip cutting module 610, comprising:
Video clip cutting unit, for according to round rule from match video in cutting bout segment；
Correspondingly, the target fragment determining module 620, comprising:
Target fragment determination unit, for predicting the excellent degree of the bout segment, and according to the bout segment
Excellent degree determines target fragment.
Optionally, the round rule includes at least one of: halfway line, score, exchange ball are crossed in baseline service
Power and countdown in 24 seconds terminate.
Optionally, the video clip cutting unit, is specifically used for,
The time range of target fragment is determined by the round rule；
The bout segment is syncopated as from the match video according to the time range.
Optionally, described device further include: characteristic information adding module, for according to the target fragment content and/
Or temporal characteristics add characteristic information corresponding with target fragment in the target fragment,
Correspondingly, the Video Roundup generation module 630 is specifically used for,
Video Roundup is generated according to the target fragment and corresponding characteristic information.
Optionally, the excellent degree of the video clip is determined according to preset excellent degree judgment models, described default
The sample datas of excellent degree judgment models include: the wonderful and non-wonderful for belonging to same video.
Optionally, the preset excellent degree judgment models are that the loss function training based on Huber loss obtains.
The generating means of Video Roundup provided by the embodiment of the present invention can be performed provided by any embodiment of the invention
The generation method of Video Roundup has the corresponding functional module of execution method and beneficial effect.It is not detailed in the present embodiment to retouch
The technical detail stated, reference can be made to a kind of generation method for Video Roundup that any embodiment of that present invention provides.
Example IV
Referring to Fig. 7, a kind of electronic equipment 700 is present embodiments provided comprising: one or more processors 720；Storage
Device 710, for storing one or more programs, when one or more of programs are by one or more of processors 720
It executes, so that one or more of processors 720 realize a kind of generation side of Video Roundup provided by the embodiment of the present invention
Method, comprising:
According to preset slice rule cutting video clip from target video, wherein the slice rule is according to view
Frequency type and content determine；
It predicts the excellent degree of the video clip, and target fragment is determined according to the excellent degree of the video clip；
Video Roundup is generated according to the target fragment.
Certainly, it will be understood by those skilled in the art that processor 720 can also realize that any embodiment of that present invention is provided
A kind of Video Roundup generation method technical solution.
The electronic equipment 700 that Fig. 7 is shown is only an example, should not function and use scope to the embodiment of the present invention
Bring any restrictions.
As shown in fig. 7, electronic equipment 700 is showed in the form of universal computing device.The component of electronic equipment 700 can wrap
Include but be not limited to: one or more processor 720, storage device 710 connect different system components (including storage device 710
With processor 720) bus 750.
Bus 750 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Electronic equipment 700 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that electronic equipment 700 accesses, including volatile and non-volatile media, moveable and immovable medium.
Storage device 710 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 711 and/or cache memory 712.Electronic equipment 700 may further include it is other it is removable/can not
Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 713 can be used for reading and writing not
Movably, non-volatile magnetic media (Fig. 7 do not show, commonly referred to as " hard disk drive ").It, can be with although being not shown in Fig. 7
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") is provided, and non-volatile to moving
The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 750.Storage device 710 may include at least one journey
Sequence product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this hair
The function of bright each embodiment.
Program/utility 714 with one group of (at least one) program module 715 can store in such as storage dress
It sets in 710, such program module 715 includes but is not limited to operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.Program module
715 usually execute function and/or method in any embodiment described in the invention.
Electronic equipment 700 can also be with one or more external equipments 760 (such as keyboard, sensing equipment, display 770
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 700 communicate, and/or with make
Any equipment (such as network interface card, the modem that the electronic equipment 700 can be communicated with one or more of the other calculating equipment
Etc.) communication.This communication can be carried out by input/output (I/O) interface 730.Also, electronic equipment 700 can also lead to
Cross network adapter 740 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, example
Such as internet) communication.As shown in fig. 7, network adapter 740 is communicated by bus 750 with other modules of electronic equipment 700.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 700, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
The program that processor 720 is stored in storage device 710 by operation, thereby executing various function application and number
According to processing, such as realize a kind of generation method of Video Roundup provided by the embodiment of the present invention.
Embodiment five
The embodiment of the present invention five provides a kind of storage medium comprising computer executable instructions, and the computer is executable
It instructs when being executed by computer processor for executing a kind of generation method of Video Roundup, this method comprises:
According to preset slice rule cutting video clip from target video, wherein the slice rule is according to view
Frequency type and content determine；
It predicts the excellent degree of the video clip, and target fragment is determined according to the excellent degree of the video clip；
Video Roundup is generated according to the target fragment.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed a kind of video provided by any embodiment of the invention
Relevant operation in the generation method of the collection of choice specimens.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of generation method of Video Roundup, which is characterized in that the described method includes:
According to preset slice rule cutting video clip from target video, wherein the slice rule is according to video kind
Class and content determine；
It predicts the excellent degree of the video clip, and target fragment is determined according to the excellent degree of the video clip；
Video Roundup is generated according to the target fragment.
2. the method according to claim 1, wherein the video genre include match video, correspondingly,
According to preset slice rule cutting video clip from target video, comprising:
According to round rule from match video in cutting bout segment；
Correspondingly, predicting the excellent degree of the video clip, and target patch is determined according to the excellent degree of the video clip
Section, comprising:
It predicts the excellent degree of the bout segment, and target fragment is determined according to the excellent degree of the bout segment.
3. according to the method described in claim 2, it is characterized in that, the round rule includes at least one of: bottom
Line serves a ball, crosses halfway line, score, exchange ball is weighed and countdown in 24 seconds terminates.
4. according to the method described in claim 2, it is characterized in that, according to round rule from match video in cutting bout
Segment, comprising:
The time range of bout segment is determined by the round rule；
The bout segment is syncopated as from the match video according to the time range.
5. the method according to claim 1, wherein according to the target fragment generate the Video Roundup it
Before, further includes:
Content and/or temporal characteristics according to the target fragment add spy corresponding with target fragment in the target fragment
Reference breath,
Correspondingly, described generate Video Roundup according to the target fragment, comprising:
Video Roundup is generated according to the target fragment and corresponding characteristic information.
6. the method according to claim 1, wherein the excellent degree of the video clip is according to preset excellent
Degree judgment models determine that the sample data of the preset excellent degree judgment models includes: belong to same video excellent
Segment and non-wonderful.
7. according to the method described in claim 6, it is characterized in that, the preset excellent degree judgment models are to be based on
The loss function training of Huber loss obtains.
8. a kind of generating means of Video Roundup, which is characterized in that described device includes:
Video clip cutting module, for according to preset slice rule cutting video clip from target video, wherein described
Slice rule is determined according to video genre and content；
Target fragment determining module, for predicting the excellent degree of the video clip, and according to the excellent of the video clip
Degree determines target fragment；
Video Roundup generation module, for generating Video Roundup according to the target fragment.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
A kind of now generation method of Video Roundup as described in any in claim 1-7.
10. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
For executing a kind of generation method of Video Roundup as described in any in claim 1-7 when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811137931.0A CN109121021A (en) | 2018-09-28 | 2018-09-28 | A kind of generation method of Video Roundup, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811137931.0A CN109121021A (en) | 2018-09-28 | 2018-09-28 | A kind of generation method of Video Roundup, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109121021A true CN109121021A (en) | 2019-01-01 |
Family
ID=64857067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811137931.0A Pending CN109121021A (en) | 2018-09-28 | 2018-09-28 | A kind of generation method of Video Roundup, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109121021A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657100A (en) * | 2019-01-25 | 2019-04-19 | 深圳市商汤科技有限公司 | Video Roundup generation method and device, electronic equipment and storage medium |
| CN109889920A (en) * | 2019-04-16 | 2019-06-14 | 威比网络科技(上海)有限公司 | Network courses video clipping method, system, equipment and storage medium |
| CN109922379A (en) * | 2019-02-22 | 2019-06-21 | 深圳前海微众银行股份有限公司 | Advertisement video optimization method, device, equipment and computer readable storage medium |
| CN110012348A (en) * | 2019-06-04 | 2019-07-12 | 成都索贝数码科技股份有限公司 | A kind of automatic collection of choice specimens system and method for race program |
| CN110008374A (en) * | 2019-06-04 | 2019-07-12 | 成都索贝数码科技股份有限公司 | It is a kind of to select edit methods for what race intelligently made |
| CN110166828A (en) * | 2019-02-19 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of method for processing video frequency and device |
| CN110191357A (en) * | 2019-06-28 | 2019-08-30 | 北京奇艺世纪科技有限公司 | The excellent degree assessment of video clip, dynamic seal face generate method and device |
| CN110188237A (en) * | 2019-06-04 | 2019-08-30 | 成都索贝数码科技股份有限公司 | A kind of data collecting system intelligently made for race and method |
| CN110188241A (en) * | 2019-06-04 | 2019-08-30 | 成都索贝数码科技股份有限公司 | A kind of race intelligence manufacturing system and production method |
| CN110263217A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | A kind of video clip label identification method and device |
| CN110263220A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | A kind of video highlight segment recognition methods and device |
| CN110267119A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | The evaluation method and relevant device of video highlight degree |
| CN110314361A (en) * | 2019-05-10 | 2019-10-11 | 新华智云科技有限公司 | A kind of basketball goal score judgment method and system based on convolutional neural networks |
| CN110347872A (en) * | 2019-07-04 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Video cover image extracting method and device, storage medium and electronic equipment |
| CN110381371A (en) * | 2019-07-30 | 2019-10-25 | 维沃移动通信有限公司 | A kind of video clipping method and electronic equipment |
| CN110381366A (en) * | 2019-07-09 | 2019-10-25 | 新华智云科技有限公司 | Race automates report method, system, server and storage medium |
| CN110401873A (en) * | 2019-06-17 | 2019-11-01 | 北京奇艺世纪科技有限公司 | Video clipping method, device, electronic equipment and computer-readable medium |
| CN110505519A (en) * | 2019-08-14 | 2019-11-26 | 咪咕文化科技有限公司 | A kind of video clipping method, electronic equipment and storage medium |
| CN110730380A (en) * | 2019-08-28 | 2020-01-24 | 咪咕文化科技有限公司 | Video synthesis method, electronic device and storage medium |
| CN110969133A (en) * | 2019-12-05 | 2020-04-07 | 浙江大学 | Intelligent data acquisition method for table tennis game video |
| CN111182367A (en) * | 2019-12-30 | 2020-05-19 | 苏宁云计算有限公司 | Video generation method and device and computer system |
| CN111225236A (en) * | 2020-01-20 | 2020-06-02 | 北京百度网讯科技有限公司 | Method and device for generating video cover, electronic equipment and computer-readable storage medium |
| CN111526424A (en) * | 2020-04-30 | 2020-08-11 | 北京奇艺世纪科技有限公司 | Method and device for extracting wonderful video segment, electronic equipment and storage medium |
| CN111836118A (en) * | 2019-04-19 | 2020-10-27 | 百度在线网络技术（北京）有限公司 | Video processing method, device, server and storage medium |
| CN111866610A (en) * | 2019-04-08 | 2020-10-30 | 百度时代网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN112689200A (en) * | 2020-12-15 | 2021-04-20 | 万兴科技集团股份有限公司 | Video editing method, electronic device and storage medium |
| CN112995756A (en) * | 2021-03-01 | 2021-06-18 | 央视国际网络有限公司 | Short video generation method and device and short video generation system |
| CN113329263A (en) * | 2021-05-28 | 2021-08-31 | 努比亚技术有限公司 | Game video collection manufacturing method and device and computer readable storage medium |
| WO2022007545A1 (en) * | 2020-07-06 | 2022-01-13 | 聚好看科技股份有限公司 | Video collection generation method and display device |
| CN114007084A (en) * | 2022-01-04 | 2022-02-01 | 秒影工场(北京)科技有限公司 | Video clip cloud storage method and device |
| CN114363641A (en) * | 2020-10-13 | 2022-04-15 | 阿里巴巴集团控股有限公司 | Target video generation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599179A (en) * | 2009-07-17 | 2009-12-09 | 北京邮电大学 | Method for automatically generating field motion wonderful scene highlights |
| CN102263907A (en) * | 2011-08-04 | 2011-11-30 | 央视国际网络有限公司 | Play control method of competition video, and generation method and device for clip information of competition video |
| US20160337718A1 (en) * | 2014-09-23 | 2016-11-17 | Joshua Allen Talbott | Automated video production from a plurality of electronic devices |
| CN106971010A (en) * | 2017-05-12 | 2017-07-21 | 深圳市唯特视科技有限公司 | A kind of video abstraction generating method suitable for text query |
| CN107464228A (en) * | 2017-08-24 | 2017-12-12 | 深圳市唯特视科技有限公司 | A kind of image analysis method based on adaptive regularization |
| CN108495259A (en) * | 2018-03-26 | 2018-09-04 | 上海工程技术大学 | A kind of gradual indoor positioning server and localization method |
-
2018
- 2018-09-28 CN CN201811137931.0A patent/CN109121021A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599179A (en) * | 2009-07-17 | 2009-12-09 | 北京邮电大学 | Method for automatically generating field motion wonderful scene highlights |
| CN102263907A (en) * | 2011-08-04 | 2011-11-30 | 央视国际网络有限公司 | Play control method of competition video, and generation method and device for clip information of competition video |
| US20160337718A1 (en) * | 2014-09-23 | 2016-11-17 | Joshua Allen Talbott | Automated video production from a plurality of electronic devices |
| CN106971010A (en) * | 2017-05-12 | 2017-07-21 | 深圳市唯特视科技有限公司 | A kind of video abstraction generating method suitable for text query |
| CN107464228A (en) * | 2017-08-24 | 2017-12-12 | 深圳市唯特视科技有限公司 | A kind of image analysis method based on adaptive regularization |
| CN108495259A (en) * | 2018-03-26 | 2018-09-04 | 上海工程技术大学 | A kind of gradual indoor positioning server and localization method |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657100B (en) * | 2019-01-25 | 2021-10-29 | 深圳市商汤科技有限公司 | Video collection generation method and device, electronic equipment and storage medium |
| CN109657100A (en) * | 2019-01-25 | 2019-04-19 | 深圳市商汤科技有限公司 | Video Roundup generation method and device, electronic equipment and storage medium |
| CN110166828A (en) * | 2019-02-19 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of method for processing video frequency and device |
| CN109922379A (en) * | 2019-02-22 | 2019-06-21 | 深圳前海微众银行股份有限公司 | Advertisement video optimization method, device, equipment and computer readable storage medium |
| CN111866610A (en) * | 2019-04-08 | 2020-10-30 | 百度时代网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN109889920A (en) * | 2019-04-16 | 2019-06-14 | 威比网络科技(上海)有限公司 | Network courses video clipping method, system, equipment and storage medium |
| CN109889920B (en) * | 2019-04-16 | 2022-08-05 | 上海平安智慧教育科技有限公司 | Network course video editing method, system, equipment and storage medium |
| CN111836118A (en) * | 2019-04-19 | 2020-10-27 | 百度在线网络技术（北京）有限公司 | Video processing method, device, server and storage medium |
| CN110314361A (en) * | 2019-05-10 | 2019-10-11 | 新华智云科技有限公司 | A kind of basketball goal score judgment method and system based on convolutional neural networks |
| CN110314361B (en) * | 2019-05-10 | 2021-03-30 | 新华智云科技有限公司 | Method and system for judging basketball goal score based on convolutional neural network |
| CN110188237A (en) * | 2019-06-04 | 2019-08-30 | 成都索贝数码科技股份有限公司 | A kind of data collecting system intelligently made for race and method |
| CN110008374A (en) * | 2019-06-04 | 2019-07-12 | 成都索贝数码科技股份有限公司 | It is a kind of to select edit methods for what race intelligently made |
| CN110012348B (en) * | 2019-06-04 | 2019-09-10 | 成都索贝数码科技股份有限公司 | A kind of automatic collection of choice specimens system and method for race program |
| CN110188241B (en) * | 2019-06-04 | 2023-07-25 | 成都索贝数码科技股份有限公司 | Intelligent manufacturing system and manufacturing method for events |
| CN110008374B (en) * | 2019-06-04 | 2019-09-13 | 成都索贝数码科技股份有限公司 | It is a kind of to select edit methods for what race intelligently made |
| CN110188237B (en) * | 2019-06-04 | 2023-07-25 | 成都索贝数码科技股份有限公司 | Data aggregation system and method for intelligent manufacturing of events |
| CN110012348A (en) * | 2019-06-04 | 2019-07-12 | 成都索贝数码科技股份有限公司 | A kind of automatic collection of choice specimens system and method for race program |
| CN110188241A (en) * | 2019-06-04 | 2019-08-30 | 成都索贝数码科技股份有限公司 | A kind of race intelligence manufacturing system and production method |
| CN110401873A (en) * | 2019-06-17 | 2019-11-01 | 北京奇艺世纪科技有限公司 | Video clipping method, device, electronic equipment and computer-readable medium |
| CN110191357A (en) * | 2019-06-28 | 2019-08-30 | 北京奇艺世纪科技有限公司 | The excellent degree assessment of video clip, dynamic seal face generate method and device |
| CN110263217A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | A kind of video clip label identification method and device |
| CN110267119A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | The evaluation method and relevant device of video highlight degree |
| CN110267119B (en) * | 2019-06-28 | 2023-06-30 | 北京奇艺世纪科技有限公司 | Video precision and chroma evaluation method and related equipment |
| CN110263220A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | A kind of video highlight segment recognition methods and device |
| CN110347872A (en) * | 2019-07-04 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Video cover image extracting method and device, storage medium and electronic equipment |
| CN110347872B (en) * | 2019-07-04 | 2023-10-24 | 腾讯科技（深圳）有限公司 | Video cover image extraction method and device, storage medium and electronic equipment |
| CN110381366B (en) * | 2019-07-09 | 2021-12-17 | 新华智云科技有限公司 | Automatic event reporting method, system, server and storage medium |
| CN110381366A (en) * | 2019-07-09 | 2019-10-25 | 新华智云科技有限公司 | Race automates report method, system, server and storage medium |
| CN110381371B (en) * | 2019-07-30 | 2021-08-31 | 维沃移动通信有限公司 | Video editing method and electronic equipment |
| CN110381371A (en) * | 2019-07-30 | 2019-10-25 | 维沃移动通信有限公司 | A kind of video clipping method and electronic equipment |
| CN110505519B (en) * | 2019-08-14 | 2021-12-03 | 咪咕文化科技有限公司 | Video editing method, electronic equipment and storage medium |
| CN110505519A (en) * | 2019-08-14 | 2019-11-26 | 咪咕文化科技有限公司 | A kind of video clipping method, electronic equipment and storage medium |
| CN110730380B (en) * | 2019-08-28 | 2022-11-22 | 咪咕文化科技有限公司 | Video synthesis method, electronic device and storage medium |
| CN110730380A (en) * | 2019-08-28 | 2020-01-24 | 咪咕文化科技有限公司 | Video synthesis method, electronic device and storage medium |
| CN110969133A (en) * | 2019-12-05 | 2020-04-07 | 浙江大学 | Intelligent data acquisition method for table tennis game video |
| CN110969133B (en) * | 2019-12-05 | 2023-04-07 | 浙江大学 | Intelligent data acquisition method for table tennis game video |
| CN111182367A (en) * | 2019-12-30 | 2020-05-19 | 苏宁云计算有限公司 | Video generation method and device and computer system |
| CN111225236A (en) * | 2020-01-20 | 2020-06-02 | 北京百度网讯科技有限公司 | Method and device for generating video cover, electronic equipment and computer-readable storage medium |
| CN111225236B (en) * | 2020-01-20 | 2022-03-25 | 北京百度网讯科技有限公司 | Method and device for generating video cover, electronic equipment and computer-readable storage medium |
| CN111526424A (en) * | 2020-04-30 | 2020-08-11 | 北京奇艺世纪科技有限公司 | Method and device for extracting wonderful video segment, electronic equipment and storage medium |
| WO2022007545A1 (en) * | 2020-07-06 | 2022-01-13 | 聚好看科技股份有限公司 | Video collection generation method and display device |
| CN114363641A (en) * | 2020-10-13 | 2022-04-15 | 阿里巴巴集团控股有限公司 | Target video generation method and device |
| CN112689200A (en) * | 2020-12-15 | 2021-04-20 | 万兴科技集团股份有限公司 | Video editing method, electronic device and storage medium |
| CN112995756A (en) * | 2021-03-01 | 2021-06-18 | 央视国际网络有限公司 | Short video generation method and device and short video generation system |
| CN113329263A (en) * | 2021-05-28 | 2021-08-31 | 努比亚技术有限公司 | Game video collection manufacturing method and device and computer readable storage medium |
| CN113329263B (en) * | 2021-05-28 | 2023-10-17 | 努比亚技术有限公司 | Game video highlight production method, equipment and computer readable storage medium |
| CN114007084A (en) * | 2022-01-04 | 2022-02-01 | 秒影工场(北京)科技有限公司 | Video clip cloud storage method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109121021A (en) | A kind of generation method of Video Roundup, device, electronic equipment and storage medium | |
| US10987596B2 (en) | Spectator audio analysis in online gaming environments | |
| EP3856375B1 (en) | Implementing a graphical overlay for a streaming game based on current game scenario | |
| US9463388B2 (en) | Fantasy sports transition score estimates | |
| CN104288992B (en) | For automatically creating the system and method for video-game highlight | |
| US10293260B1 (en) | Player audio analysis in online gaming environments | |
| US11679334B2 (en) | Dynamic gameplay session content generation system | |
| KR102599975B1 (en) | Automated creation of game tags | |
| CN108601980B (en) | Information processing system, information processing method, program, server, and information processing terminal | |
| CN101807393A (en) | KTV system, implement method thereof and TV set | |
| CN113966247A (en) | Predictive data preloading | |
| Nitsche | Machinima as media | |
| US20210394060A1 (en) | Method and system for automatically generating video highlights for a video game player using artificial intelligence (ai) | |
| Salge et al. | Generative design in minecraft: Chronicle challenge | |
| Shaker et al. | A progressive approach to content generation | |
| CN103413018B (en) | Method for providing dynamic exercise content | |
| CN116963809A (en) | In-game dynamic camera angle adjustment | |
| US11878239B2 (en) | Replay editor in video games | |
| KR20240005086A (en) | Automatic presentation of appropriate content | |
| KR20140119288A (en) | Game system and operation method thereof | |
| KR20210068016A (en) | Data management and performance tracking system for walking or interactive virtual reality | |
| US20230326208A1 (en) | Systems and methods for user-generated content with machine-generated metadata | |
| CN115396685B (en) | Live interaction method and device, readable storage medium and electronic equipment | |
| US20230232083A1 (en) | Systems and methods for predicting user-generated content trends with machine-generated metadata | |
| US11443512B1 (en) | Systems and methods for querying video information of electronic games |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190101 |
|
| RJ01 | Rejection of invention patent application after publication |