CN105072457A - Method and device for processing television program images - Google Patents
Method and device for processing television program images Download PDFInfo
- Publication number
- CN105072457A CN105072457A CN201510506025.3A CN201510506025A CN105072457A CN 105072457 A CN105072457 A CN 105072457A CN 201510506025 A CN201510506025 A CN 201510506025A CN 105072457 A CN105072457 A CN 105072457A
- Authority
- CN
- China
- Prior art keywords
- vocabulary
- programme picture
- cluster
- word
- programme
- 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
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]
- H04N21/20—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
- H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- 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
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for processing television program images. The method comprises the following steps of acquiring the television program images; identifying characters in the television program images; and classifying the television program images according to the identified characters. According to the method, the television program images are classified according to the characters in the television program images, numerous television program images can be classified effectively, and the classified television program images are more convenient to manage, look up and use.
Description
Technical field
The present invention relates to technical field of image processing, more specifically, relate to a kind of method and apparatus processing TV programme picture.
Background technology
When TV programme is play, when particularly being play by intelligent terminals such as computers, user can intercept the picture of a certain frame as TV programme of TV programme.Such as, when there is user favorite actor, article, scene in TV programme, user can intercept frame of video as TV programme picture.
The picture uploading of TV programme can also be watched for other users to website or download by user.Further, these TV programme pictures that user can also upload by video website, as the summary picture of video comprising this TV programme, to provide the relevant information of video.
But the TV programme picture uploaded along with user gets more and more, the TV programme picture how processing One's name is legion is efficiently problem demanding prompt solution.
Summary of the invention
In view of this, the object of the embodiment of the present invention proposes a kind of method and apparatus processing TV programme picture, can process TV programme picture efficiently.
In order to achieve the above object, the embodiment of the present invention proposes a kind of method processing TV programme picture, comprises the following steps:
Obtain TV programme picture;
Identify the word in TV programme picture;
Word according to identifying is classified to TV programme picture.
In one embodiment of the invention, the described word according to identifying is classified to TV programme picture, comprising:
Participle is carried out to the word identified and obtains vocabulary;
The vocabulary of acquisition is carried out cluster;
The TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class.
In one embodiment of the invention, described method also comprises:
The title of the vocabulary of acquisition with existing classification is mated;
When the match is successful, TV programme picture corresponding for all vocabulary in class belonging to the vocabulary of the name-matches with described existing classification is joined described existing classification.
In one embodiment of the invention, described the vocabulary of acquisition is carried out cluster, comprising: the vocabulary of the vocabulary of acquisition and existing classification is carried out cluster;
The TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class, also comprises:
TV programme picture corresponding to the vocabulary belonging to described existing classification after cluster is joined described existing classification.
In one embodiment of the invention, described the vocabulary of acquisition is carried out cluster, comprising:
Obtain the semantic similarity between vocabulary;
Semantic similarity is converged to a class higher than the word of preset value.
The embodiment of the present invention also proposes a kind of device processing TV programme picture, comprising:
Acquisition device, for obtaining TV programme picture;
Identification module, for identifying the word in TV programme picture;
Sort module, for classifying to TV programme picture according to the word identified.
In one embodiment of the invention, described sort module, comprising:
Participle submodule, obtains vocabulary for carrying out participle to the word identified;
Cluster submodule, for carrying out cluster by the vocabulary of acquisition;
Described sort module, also for the TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class.
In one embodiment of the invention, described device also comprises:
Matching module, for mating the title of the vocabulary of acquisition with existing classification;
Described sort module, also for when the match is successful, joins described existing classification by TV programme picture corresponding for all vocabulary in class belonging to the vocabulary of the name-matches with described existing classification.
In one embodiment of the invention, described cluster submodule, also for:
The vocabulary of the vocabulary of acquisition and existing classification is carried out cluster;
Described sort module, also for the TV programme picture corresponding to the vocabulary belonging to described existing classification after cluster is joined described existing classification.
In one embodiment of the invention, described cluster submodule, also for:
Obtain the semantic similarity between vocabulary;
Semantic similarity is converged to a class higher than the word of preset value.
The technical scheme that the embodiment of the present invention provides can comprise following beneficial effect:
In the embodiment of the present invention, classify according to the word in TV programme picture to TV programme picture, the TV programme picture of One's name is legion effectively can be classified, sorted TV programme picture is more conducive to management, searches and use.
The further feature of the embodiment of the present invention and advantage will be set forth in the following description, and, partly become apparent from specification, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in write specification, claims and accompanying drawing and obtain.
Below by drawings and Examples, the technical scheme of the embodiment of the present invention is described in further detail.
Accompanying drawing explanation
Accompanying drawing is used to provide the further understanding to the embodiment of the present invention, and forms a part for specification, together with embodiments of the present invention for explaining the present invention, does not form the restriction to the embodiment of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the method for process TV programme picture in one embodiment of the invention.
Fig. 2 is the flow chart of the method for process TV programme picture in one embodiment of the invention.
Fig. 3 is the flow chart of the method for process TV programme picture in one embodiment of the invention.
Fig. 4 is the flow chart of the method for process TV programme picture in one embodiment of the invention.
Fig. 5 is the structural representation of the device of process TV programme picture in one embodiment of the invention.
Fig. 6 is the structural representation of the device of process TV programme picture in one embodiment of the invention.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the embodiment of the present invention, is not intended to limit the present invention embodiment.
TV programme picture can be user intercept when watching TV and upload, also can be that editorial staff intercepts.TV programme picture can as the summary picture of TV programme (video of this TV programme).
Be illustrated in figure 1 the flow chart of the method for the process TV programme picture in the embodiment of the present invention, the method comprises:
Step S11: obtain TV programme picture.
Step S12: identify the word in TV programme picture.
Step S13: the word according to identifying is classified to TV programme picture.
Such as, the TV programme picture including the word of identical and/or semantic similitude can be divided into a class.
In the embodiment of the present invention, classify according to the word in TV programme picture to TV programme picture, the TV programme picture of One's name is legion effectively can be classified, sorted TV programme picture is more conducive to management, searches and use.
Be illustrated in figure 2 the flow chart of the method for the process TV programme picture that another embodiment of the present invention provides, in this embodiment, comprise the following steps:
Step S21: receive the TV programme picture that user uploads.
The TV programme picture that user uploads can be that user's screenshotss when watching TV generate.
Step S22: image recognition is carried out to the TV programme picture received, identifies the word in TV programme picture.
Image recognition processes such as can comprise Image semantic classification, Iamge Segmentation, image characteristics extraction and judgement coupling.Wherein, Image semantic classification: elimination interference, noise, when the faint None-identified of image information, also will strengthen image, set adjustment, color correction etc.; Iamge Segmentation: different objects to be identified is isolated in location, input entire image, exports pixel image; Image feature extraction: extract feature; Judge coupling: the feature of extraction is mated by the model according to presetting.
Word in TV programme picture can be such as the station symbol of the textual representation in TV programme picture, also can be the title of the TV programme shown in TV programme picture, can also be other captions in TV programme, such as, show actor names, scene title etc.
Step S23: participle is carried out to the word identified and obtains vocabulary.
Segmentation methods such as has: based on the segmenting method of string matching, the segmenting method based on the segmenting method understood and Corpus--based Method.
Segmenting method based on string matching is called mechanical segmentation method again, according to certain strategy, the entry in Chinese character string to be analyzed and " fully large " machine dictionary is joined, if find certain character string in dictionary, then the match is successful (identifying a word), according to the difference of scanning direction, String matching segmenting method can be divided into forward to mate and reverse coupling; According to the situation of different length priority match, maximum (the longest) can be divided into mate and minimum (the shortest) coupling.
That reach the effect identifying word, its basic thought is exactly carry out syntax, semantic analysis while participle, utilizes syntactic information and semantic information to process Ambiguity by allowing the understanding of anthropomorphic distich of computer mould based on the segmenting method understood.
The segmenting method of Corpus--based Method: formally see, word is stable combinatorics on words, and therefore within a context, the number of times that adjacent word occurs simultaneously is more, more likely forms a word.Therefore the frequency of word co-occurrence adjacent with word or probability can reflect into the confidence level of word preferably.Can add up the frequency of each combinatorics on words of co-occurrence adjacent in language material, calculate their information that appears alternatively.The information that appears alternatively of definition two words, calculates the adjacent co-occurrence probabilities of two Chinese characters.The information of appearing alternatively embodies the tightness degree of marriage relation between Chinese character.When tightness degree is higher than some threshold values, just can think that this word group may constitute a word.Also has the method for Corpus--based Method machine learning in addition: the text first providing a large amount of participle, utilizes the rule of statistical machine learning model learning word segmentation (being called training), thus realizes the cutting to unknown text.
Step S24: the vocabulary of acquisition is carried out cluster.
In other embodiments of the invention, according to the semantic similarity between vocabulary, the vocabulary of acquisition can be carried out cluster.If the semantic similarity between two vocabulary is greater than a preset value, then illustrates that these two vocabulary are closely similar, a class can be classified as.
The calculated example of semantic similarity is as can based on word distance or based on amount of information.Method based on word distance is more directly perceived, and amount of calculation is less, and efficiency is higher.The distance of two words is larger, and its similarity is lower; Otherwise the distance of two words is less, its similarity is larger.The computational methods that word distance has two classes common, one calculates according to certain World Affairs (Ontology), and one utilizes large-scale corpus to add up.
Step S25: the TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class.
In the present embodiment, the word identified is carried out further participle and obtain vocabulary, according to words clustering by TV programme picture classification.This classification according to vocabulary accurate and effective more.Such as, include " Spring Festival " in TV programme picture A, include " the Spring Festival " in TV programme picture B, so these two TV programme pictures can be classified as a class.
Be illustrated in figure 3 the flow chart of the method for the process TV programme picture that another embodiment of the present invention provides, in this embodiment, comprise the following steps:
Step S31: obtain TV programme picture.
Step S32: identify the word in TV programme picture.
Step S33: participle is carried out to the word identified and obtains vocabulary.
Step S34: the vocabulary of acquisition is carried out cluster.
Step S35: the TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class.
Step S36: the title of the vocabulary of acquisition with existing classification is mated.
Wherein, the title of existing classification is arranged after classifying before being.Such as, the name of existing classification is called " running ", namely illustrates that the TV programme picture during such is not is all relevant with running.When the vocabulary obtained in this step mates with the title " running " of existing classification, the TV programme picture in such can be joined in the existing classification of this coupling.Such as, when the vocabulary of acquisition is for " hurrying up ", mate with the title " running " of existing classification.
Coupling can be carried out according to the semantic similarity between vocabulary, when the semantic similarity between vocabulary is greater than preset value, confirms this vocabulary and such other name-matches.
Step S37: when the match is successful, joins described existing classification by a class TV programme picture corresponding for all vocabulary in class belonging to this vocabulary.
Be illustrated in figure 4 the flow chart of the method for the process TV programme picture that another embodiment of the present invention provides, in this embodiment, comprise the following steps:
Step S41: obtain TV programme picture.
Step S42: identify the word in TV programme picture.
Step S43: participle is carried out to the word identified and obtains vocabulary.
Step S44: the vocabulary vocabulary of acquisition being combined existing classification carries out cluster.
Can carry out cluster according to the semantic similarity between vocabulary, when the semantic similarity between vocabulary is greater than preset value, confirm that the vocabulary in this vocabulary and this classification is a class, namely this vocabulary belongs to this classification.
Step S45: the TV programme picture corresponding to the vocabulary belonging to described existing classification after cluster is joined described existing classification.
In the present embodiment, cluster can be carried out with the vocabulary of existing classification, thus TV programme picture is joined in existing classification.
As shown in Figure 5, the embodiment of the present invention also proposes a kind of device processing TV programme picture,
Acquisition module 501, for obtaining TV programme picture;
Identification module 502, for identifying the word in TV programme picture;
Sort module 503, for classifying to TV programme picture according to the word identified.
Described sort module 503, comprising:
Participle submodule, obtains vocabulary for carrying out participle to the word identified;
Cluster submodule, for carrying out cluster by the vocabulary of acquisition;
Described sort module, also for the TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class.
As shown in Figure 6, described device also comprises:
Matching module 504, for mating the title of the vocabulary of acquisition with existing classification;
Described sort module 503, also for when the match is successful, joins described existing classification by TV programme picture corresponding for all vocabulary in class belonging to this vocabulary.
Described cluster submodule, also for: the vocabulary of the vocabulary of acquisition and existing classification is carried out cluster;
Described sort module 503, also for the TV programme picture corresponding to the vocabulary belonging to described existing classification after cluster is joined described existing classification.
Described cluster submodule, also for: obtain the semantic similarity between vocabulary; Semantic similarity is converged to a class higher than the word of preset value.
Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the present invention can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disc store and optical memory etc.) of computer usable program code.
The present invention describes with reference to according to the flow chart of the method for the embodiment of the present invention, equipment (system) and computer program and/or block diagram.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame.These computer program instructions can being provided to the processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computer or other programmable data processing device produce device for realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices is provided for the step realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. process a method for TV programme picture, it is characterized in that, comprise the following steps:
Obtain TV programme picture;
Identify the word in TV programme picture;
Word according to identifying is classified to TV programme picture.
2. method according to claim 1, is characterized in that, the described word according to identifying is classified to TV programme picture, comprising:
Participle is carried out to the word identified and obtains vocabulary;
The vocabulary of acquisition is carried out cluster;
The TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class.
3. method according to claim 2, is characterized in that, described method also comprises:
The title of the vocabulary of acquisition with existing classification is mated;
When the match is successful, TV programme picture corresponding for all vocabulary in class belonging to the vocabulary of the name-matches with described existing classification is joined described existing classification.
4. method according to claim 2, is characterized in that, described the vocabulary of acquisition is carried out cluster, comprising: the vocabulary of the vocabulary of acquisition and existing classification is carried out cluster;
The TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class, also comprises:
TV programme picture corresponding to the vocabulary belonging to described existing classification after cluster is joined described existing classification.
5. method according to claim 2, is characterized in that, described the vocabulary of acquisition is carried out cluster, comprising:
Obtain the semantic similarity between vocabulary;
Semantic similarity is converged to a class higher than the word of preset value.
6. process a device for TV programme picture, it is characterized in that, comprising:
Acquisition device, for obtaining TV programme picture;
Identification module, for identifying the word in TV programme picture;
Sort module, for classifying to TV programme picture according to the word identified.
7. device according to claim 6, is characterized in that, described sort module, comprising:
Participle submodule, obtains vocabulary for carrying out participle to the word identified;
Cluster submodule, for carrying out cluster by the vocabulary of acquisition;
Described sort module, also for the TV programme picture belonged to after cluster corresponding to of a sort vocabulary is divided into a class.
8. device according to claim 7, is characterized in that, described device also comprises:
Matching module, for mating the title of the vocabulary of acquisition with existing classification;
Described sort module, also for when the match is successful, joins described existing classification by TV programme picture corresponding for all vocabulary in class belonging to the vocabulary of the name-matches with described existing classification.
9. device according to claim 7, is characterized in that, described cluster submodule, also for:
The vocabulary of the vocabulary of acquisition and existing classification is carried out cluster;
Described sort module, also for the TV programme picture corresponding to the vocabulary belonging to described existing classification after cluster is joined described existing classification.
10. device according to claim 7, is characterized in that, described cluster submodule, also for:
Obtain the semantic similarity between vocabulary;
Semantic similarity is converged to a class higher than the word of preset value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510506025.3A CN105072457A (en) | 2015-08-17 | 2015-08-17 | Method and device for processing television program images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510506025.3A CN105072457A (en) | 2015-08-17 | 2015-08-17 | Method and device for processing television program images |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105072457A true CN105072457A (en) | 2015-11-18 |
Family
ID=54501717
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510506025.3A Pending CN105072457A (en) | 2015-08-17 | 2015-08-17 | Method and device for processing television program images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105072457A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105554519A (en) * | 2015-12-24 | 2016-05-04 | 北京酷云互动科技有限公司 | EPG (electrical program guide) information analyzing method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077206A (en) * | 2012-12-27 | 2013-05-01 | 浙江大学 | Image semantic classifying searching method based on event-related potential |
CN103425640A (en) * | 2012-05-14 | 2013-12-04 | 华为技术有限公司 | Multimedia questioning-answering system and method |
CN103632388A (en) * | 2013-12-19 | 2014-03-12 | 百度在线网络技术(北京)有限公司 | Semantic annotation method, device and client for image |
CN104572735A (en) * | 2013-10-23 | 2015-04-29 | 华为技术有限公司 | Photo tagging word recommending method and device |
-
2015
- 2015-08-17 CN CN201510506025.3A patent/CN105072457A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103425640A (en) * | 2012-05-14 | 2013-12-04 | 华为技术有限公司 | Multimedia questioning-answering system and method |
CN103077206A (en) * | 2012-12-27 | 2013-05-01 | 浙江大学 | Image semantic classifying searching method based on event-related potential |
CN104572735A (en) * | 2013-10-23 | 2015-04-29 | 华为技术有限公司 | Photo tagging word recommending method and device |
CN103632388A (en) * | 2013-12-19 | 2014-03-12 | 百度在线网络技术(北京)有限公司 | Semantic annotation method, device and client for image |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105554519A (en) * | 2015-12-24 | 2016-05-04 | 北京酷云互动科技有限公司 | EPG (electrical program guide) information analyzing method and system |
CN105554519B (en) * | 2015-12-24 | 2019-02-22 | 北京酷云互动科技有限公司 | EPG information analytic method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102276728B1 (en) | Multimodal content analysis system and method | |
CN103052953B (en) | Messaging device, information processing method | |
US20180109843A1 (en) | Methods and systems for aggregation and organization of multimedia data acquired from a plurality of sources | |
CN102663015B (en) | Video semantic labeling method based on characteristics bag models and supervised learning | |
CN110555136B (en) | Video tag generation method and device and computer storage medium | |
CN104994426B (en) | Program video identification method and system | |
CN109408672B (en) | Article generation method, article generation device, server and storage medium | |
WO2023159765A1 (en) | Video search method and apparatus, electronic device and storage medium | |
CN103384883B (en) | Top-K process is utilized to make semantic abundant | |
WO2009061434A1 (en) | System and method for processing digital media | |
CN113052169A (en) | Video subtitle recognition method, device, medium, and electronic device | |
CN106484774B (en) | Correlation method and system for multi-source video metadata | |
CN103914513A (en) | Entity input method and device | |
CN103984772A (en) | Method and device for generating text retrieval subtitle library and video retrieval method and device | |
CN107992937B (en) | Unstructured data judgment method and device based on deep learning | |
CN104063701B (en) | Fast electric television stations TV station symbol recognition system and its implementation based on SURF words trees and template matches | |
CN112000024B (en) | Method, device and equipment for controlling household appliance | |
CN113779303A (en) | Video set indexing method and device, storage medium and electronic equipment | |
US9866894B2 (en) | Method for annotating an object in a multimedia asset | |
CN118035489A (en) | Video searching method and device, storage medium and electronic equipment | |
CN117764115A (en) | Multi-mode model multi-task pre-training method, multi-mode recognition method and equipment | |
Rasheed et al. | A deep learning-based method for Turkish text detection from videos | |
CN105072457A (en) | Method and device for processing television program images | |
CN117093600A (en) | Search prompt word generation method and device, electronic equipment and storage medium | |
CN105120335A (en) | A method and apparatus for processing television program pictures |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151118 |