CN103927366B - Method and system for automatically playing songs according to pictures - Google Patents
Method and system for automatically playing songs according to pictures Download PDFInfo
- Publication number
- CN103927366B CN103927366B CN201410161263.0A CN201410161263A CN103927366B CN 103927366 B CN103927366 B CN 103927366B CN 201410161263 A CN201410161263 A CN 201410161263A CN 103927366 B CN103927366 B CN 103927366B
- Authority
- CN
- China
- Prior art keywords
- picture
- label
- lyrics
- library
- theme
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000012634 fragment Substances 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- 238000003064 k means clustering Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/685—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 automatically derived transcript of audio data, e.g. lyrics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and system for automatically playing songs according to pictures. The method comprises the following steps that S1, all the pictures in a picture library are marked with labels, and lyrics of all the songs in the song library are marked with labels; S2, all the pictures in the picture library are preprocessed to obtain a dictionary, and all the pictures in the picture library are reconstructed according to the dictionary; S3, the reconstructed pictures are scanned, subjects of the pictures are obtained through LDA, the labels corresponding to the pictures are added to the subjects of the pictures, subjects of the lyrics in the song library are obtained through the LDA, and the labels corresponding to the lyrics are added to the subjects of the lyrics; S4, the labels of the pictures are obtained according to the subjects of the pictures in the picture library, the lyrics with the labels which are the same as the labels of the pictures are found in the song library, and the corresponding songs are played.
Description
Technical field
The invention belongs to machine learning and area of pattern recognition, and in particular to a kind of side for playing automatically song according to picture
Method and system.
Background technology
With informationalized rapid popularization, all kinds(Such as text, audio frequency, video etc.)Information bring quantity of information
Sharply increase.How content close but different types of information to be integrated, which is classified according to content, makes people exist
During the information of a certain certain content of demand, it is not necessary to be limited to the type of information, so as to reach the purpose of diversification acquisition of information, mesh
Before become problem demanding prompt solution.
In order to process these different types of information, need various types of information are carried out dividing based on topic model
Class.Wherein, LDA (Latent Dirichlet Allocation) topic model algorithm is that the implicit theme of word is modeled
Method, it be one set probabilistic model, mainly for the treatment of discrete data acquisition system, be used primarily at present data mining and
In natural language processing, it is possible to decrease dimension.It overcomes the shortcoming of document similarity calculating method in conventional IR, and
The semantic topic between word can be found out by automatic seeking in magnanimity internet data.
Additionally, PLSI(Probability potential applications are indexed, probabilistic latent semantic indexing)It is
A kind of conventional probability semantic model, the sample that it is modeled as each word in document to take out in mixed model.Wherein,
Composition in mixed model is the stochastic variable for meeting multinomial distribution.In document, different words is probably by different semantic institutes
Produce.Each document is represented as a series of mixing ingredient, therefore dimensionality reduction becomes in fixed set semantically
One probability distribution.The generating process of LDA models is inherently identical with PLSI.PLSI is obtained from potential class model
A mixed decomposition is taken, it is now widely used for the retrieval of information and filtration, natural language processing, machine learning and some phases
The field of pass.LDA is main difference is that with PLSI:Distribution and theme of the LDA document on theme are on word list
Stochastic variable is all regarded in distribution as, is controlled by super ginseng;And PLSI regards the two distributions as parameter as.This cause with
The increase of Training document number, in test set, may result in the phenomenon of over-fitting by the model that training set draws.
Currently existing many scholars are in potential Di Li Crays model(That is LDA)On the basis of, by add label, the time because
Relevance factors, supervision or unsupervised factor etc. between element, author, are made that further improvement.At present, topic model should
With covering the multiple fields such as text mining, information processing, image procossing.
In view of the foregoing, the present invention using LDA topic models will have analog information content but difference information types
(Picture and text)Information classified, there is provided a kind of method and system for playing automatically song according to picture.So that using
Family can improve living standard and the sentiment mastery of people to listen attentively to the music close with picture situation when picture is appreciated.And
And child can increase the understanding to things to hear the song of the lyrics corresponding with picture theme when picture is seen, the present invention is right
Father and mother carry out child's early education and have positive meaning.
The content of the invention
The present invention provides a kind of method for playing automatically song according to picture, comprises the following steps:
S1, label is marked to all pictures in picture library, the lyrics mark label to all songs in library;
S2, pretreatment is carried out to all pictures in picture library obtain dictionary, reconstructed in the picture library according to the dictionary
All pictures;
The reconstructed picture of S3, scanning, obtains the theme of the picture by LDA, by the picture corresponding label
It is added in the theme of its own, while the theme of the lyrics in library is obtained by the LDA, and will be the lyrics corresponding
Label is added in the theme of its own;
S4, the label for obtaining the picture according to the theme of picture in picture library, find label and institute in library
The label identical lyrics of picture are stated, and plays correspondence song.
Preferably, same set is belonging to the label that the picture and the lyrics are marked respectively in step S1.
Preferably, the process of pretreatment described in step S2 is:N number of fragment is selected in every pictures from picture library,
The SIFT vector representations of each fragment, from all of fragment, obtain T central point with k-means clustering algorithms, and the T is individual
Central point constitutes dictionary.
Preferably, in step s3, if picture or the lyrics do not have corresponding label, by the picture or lyrics theme
Label is used as the picture or the label of the lyrics.
Preferably, the LDA that picture described in step S3 and the lyrics pass through is identical topic model algorithm.
Preferably, a label only belongs to a theme.
The present invention also provides a kind of system for playing automatically song according to picture, locates including label for labelling module, picture in advance
Reason module, cluster module and matching module, the label for labelling module connect picture pretreatment module, the picture pretreatment mould
Block connection cluster module, the cluster module matching connection module, the matching module connection player, the cluster module,
Including scanning device, LDA pictures cluster module and LDA text cluster modules, the scanning device connects LDA picture cluster modules.Institute
Label for labelling module is stated, the lyrics mark mark for label being marked to all pictures in picture library, to all songs in library
Sign.The picture pretreatment module, obtains dictionary for carrying out pretreatment to all pictures in picture library, and according to the dictionary
Reconstruct all pictures in the picture library.The cluster module, for scanning after reconstructed picture, obtains institute by LDA
The theme of picture is stated, the picture corresponding label is added in the theme of its own, while song is obtained by the LDA
The theme of the lyrics in storehouse, and the lyrics corresponding label is added in the theme of its own.The matching module, for root
The label of the picture is obtained according to the theme of picture in picture library, the label phase of label and the picture is found in library
The same lyrics.The player, for playing the song corresponding to the label identical lyrics with the picture.
The method and system for playing automatically song according to picture provided by the present invention, first to the picture in picture library
And in library song lyrics mark label, then carry out pretreatment to picture and obtain dictionary reconstructed picture, so as to for LDA
Automatically obtain picture theme and carry out place mat.After obtaining picture theme, picture corresponding label is added in the theme of its own,
Obtain the theme of the lyrics in library simultaneously by LDA, and the lyrics corresponding label is added in the theme of its own, finally
Its label is obtained according to the theme of picture in picture library, the label identical lyrics is found in library and is played correspondence song
It is bent.Thus, when new picture is found, you can played and the close music of picture situation by the system automatically, be child's morning
Religion is there is provided a kind of easily mode.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the method flow diagram for playing automatically song according to picture that present pre-ferred embodiments are provided;
Fig. 2 is the system schematic for playing automatically song according to picture that present pre-ferred embodiments are provided.
Specific embodiment
Below with reference to accompanying drawing and in conjunction with the embodiments describing the present invention in detail.It should be noted that not conflicting
In the case of, the feature in embodiment and embodiment in the application can be mutually combined.
Fig. 1 is the method flow diagram for playing automatically song according to picture that present pre-ferred embodiments are provided.Such as Fig. 1 institutes
Show, the method for playing automatically song according to picture that present pre-ferred embodiments are provided includes step S1 to S4.
Step S1:Label is marked to all pictures in picture library, the lyrics mark label to all songs in library.
Specifically, the samples pictures in picture library are parts through mark, and the label is for example set, the sun or meadow
Deng.Meanwhile, the song in existing library is processed, to the process of song mainly according to the lyrics, and the lyrics are exactly text.
The song is also that part is marked.
In this, same set is belonging to the label that the picture and the lyrics are marked respectively.Such as tree, the sun or meadow
Deng.
Step S2:Pretreatment is carried out to all pictures in picture library and obtains dictionary, the picture is reconstructed according to the dictionary
All pictures in storehouse.
Specifically, in the present embodiment, picture SIFT (Scale-invariant feature transform, yardstick
Invariant features are changed) extracted vector feature.The process of pretreatment is:N number of fragment is selected in every pictures from picture library, often
The SIFT vector representations of individual fragment, from all of fragment, obtain T central point with k-means clustering algorithms, in the T
Heart point constitutes dictionary.Generally, k-means clustering algorithms think two objects using distance as the evaluation index of similarity
Distance it is nearer, its similarity is bigger.
Step S3:The reconstructed picture of scanning, obtains the theme of the picture by LDA, will be the picture corresponding
Label is added in the theme of its own, while obtain the theme of the lyrics in library by the LDA, and by the lyrics pair
The label answered is added in the theme of its own.
Specifically, after based on all pictures in dictionary reconstruct image valut, using all pictures as LDA input.If setting
Determine theme number K, the output of LDA training patterns is picture theme distribution, and the distribution of theme dictionary.
For example, when scanning is to a new picture, the expression of dictionary is first reconstructed into, is placed into
Row test, obtains picture theme distribution, selects explanation of the big theme of probability as the picture in theme distribution.By diagram piece
Label be added in the middle of this theme, now just obtain represented by the label of the theme represented by the picture, the i.e. picture
Content.
In the present embodiment, if picture or the lyrics do not have corresponding label, the label of the picture or lyrics theme is made
For the picture or the label of the lyrics.In this, a label only belongs to a theme.
Additionally, the LDA that the picture and the lyrics pass through is identical topic model algorithm.
Step S4:The label of the picture is obtained according to the theme of picture in picture library, label is found in library
With the label identical lyrics of the picture, and play correspondence song.
Specifically, after picture has marked label by LDA, its lyrics label corresponding to library is carried out
Match somebody with somebody, in the label correspondence song for matching, randomly select a song and played out by player.
Fig. 2 is the system schematic for playing automatically song according to picture that present pre-ferred embodiments are provided.Such as Fig. 2 institutes
Show, the system for playing automatically song according to picture that present pre-ferred embodiments are provided includes that label for labelling module 1, picture is located in advance
Reason module 2, cluster module 3 and matching module 4, the connection picture of label for labelling module 1 pretreatment module 2, the picture is pre-
Processing module 2 connects cluster module 3,3 matching connection module 4 of the cluster module, the connection player 5 of the matching module 4.Institute
Cluster module 3 is stated, including scanning device 31, LDA pictures cluster module 32 and LDA text clusters module 33, the scanning device 31 connects
Connect LDA pictures cluster module 32.The label for labelling module 1, for marking label to all pictures in picture library, to library
In all songs the lyrics mark label.The picture pretreatment module 2, for carrying out pretreatment to all pictures in picture library
Dictionary is obtained, and all pictures in the picture library are reconstructed according to the dictionary.The cluster module 3, has weighed for scanning
After the picture of structure, the theme of the picture is obtained by LDA, the picture corresponding label is added to into the theme of its own
In, while obtaining the theme of the lyrics in library by the LDA, and the lyrics corresponding label is added to into its own
In theme.The matching module 4, for obtaining the label of the picture according to the theme of picture in picture library, in library
Find the label identical lyrics of label and the picture.The player 5 is identical with the label of the picture for playing
The lyrics corresponding to song.It is similar with said method with regard to the operating process of said system, therefore repeat no more in this.
In sum, the method and system for playing automatically song according to picture for being provided according to present pre-ferred embodiments,
Lyrics mark label first to song in the picture and library in picture library, then carries out pretreatment to picture and obtains dictionary
And reconstructed picture, so that picture theme is automatically obtained for LDA carry out place mat.After obtaining picture theme, by picture corresponding label
It is added in the theme of its own, while obtaining the theme of the lyrics in library by LDA, and the lyrics corresponding label is added
To in the theme of its own, its label is obtained finally according to the theme of picture in picture library, find label phase in library
The same lyrics simultaneously play correspondence song.Thus, the song of correspondence style of song according to image content, can be played automatically, people are improve
Living standard and sentiment mastery.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
Various modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized without departing from the spirit or scope of the present invention in other embodiments.Therefore, the present invention
Embodiment illustrated herein is not intended to be limited to, and is to fit to consistent with principles disclosed herein and features of novelty
Most wide scope.The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or use this
It is bright.Various modifications to these embodiments will be apparent for those skilled in the art, determined herein
The General Principle of justice can be realized without departing from the spirit or scope of the present invention in other embodiments.Therefore, originally
Invention is not intended to be limited to embodiment illustrated herein, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope for causing.
Claims (7)
1. a kind of method that song is played automatically according to picture, it is characterised in that comprise the following steps:
S1, label is marked to all pictures in picture library, the lyrics mark label to all songs in library;
S2, pretreatment is carried out to all pictures in picture library obtain dictionary, reconstructed in the picture library according to the dictionary and owned
Picture;
The reconstructed picture of S3, scanning, obtains the theme of the picture by latent Dirichletal location, by the picture pair
The label answered is added in the theme of its own, while obtaining the master of the lyrics in library by the latent Dirichletal location
Topic, and the lyrics corresponding label is added in the theme of its own;
S4, the label for obtaining the picture according to the theme of picture in picture library, find label in library with the figure
The label identical lyrics of piece, and play correspondence song.
2. method according to claim 1, it is characterised in that the mark picture and the lyrics marked respectively in step S1
Label are belonging to same set.
3. method according to claim 1, it is characterised in that the process of pretreatment described in step S2 is:From picture library
In every pictures in select N number of fragment, the SIFT vector representations of each fragment, from all of fragment, are clustered with k-means
Algorithm obtains T central point, and the T central point constitutes dictionary.
4. method according to claim 1, it is characterised in that in step s3, if picture or the lyrics do not have corresponding mark
Sign, then using the label of the picture or lyrics theme as the picture or the label of the lyrics.
5. method according to claim 1, it is characterised in that the potential Di Li that picture described in step S3 and the lyrics pass through
Cray is assigned as identical topic model algorithm.
6. method according to claim 1 a, it is characterised in that label only belongs to a theme.
7. a kind of system that song is played automatically according to picture, it is characterised in that including label for labelling module, picture pretreatment mould
Block, cluster module, matching module and player, the label for labelling module connect picture pretreatment module, and the picture is located in advance
Reason module connection cluster module, the cluster module matching connection module, the matching module connect player, the cluster mould
Block, it is including scanning device, latent Dirichletal location picture cluster module and latent Dirichletal location text cluster module, described
Scanning device connects latent Dirichletal location picture cluster module,
The label for labelling module, for marking label, the lyrics to all songs in library to all pictures in picture library
Mark label;
The picture pretreatment module, obtains dictionary for carrying out pretreatment to all pictures in picture library, and according to the word
Allusion quotation reconstructs all pictures in the picture library;
The cluster module, for scanning after reconstructed picture, obtains the picture by latent Dirichletal location
Theme, the picture corresponding label is added in the theme of its own, while being obtained by the latent Dirichletal location
The theme of the lyrics in library, and the lyrics corresponding label is added in the theme of its own;
The matching module, for obtaining the label of the picture according to the theme of picture in picture library, searches in library
To the label identical lyrics of label and the picture;
The player, for playing the song corresponding to the label identical lyrics with the picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410161263.0A CN103927366B (en) | 2014-04-21 | 2014-04-21 | Method and system for automatically playing songs according to pictures |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410161263.0A CN103927366B (en) | 2014-04-21 | 2014-04-21 | Method and system for automatically playing songs according to pictures |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103927366A CN103927366A (en) | 2014-07-16 |
CN103927366B true CN103927366B (en) | 2017-03-22 |
Family
ID=51145587
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410161263.0A Expired - Fee Related CN103927366B (en) | 2014-04-21 | 2014-04-21 | Method and system for automatically playing songs according to pictures |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103927366B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104599307B (en) * | 2015-02-11 | 2018-05-15 | 成都品果科技有限公司 | A kind of method for showing picture using animation on mobile terminals |
CN105930485A (en) * | 2016-04-28 | 2016-09-07 | 深圳市金立通信设备有限公司 | Audio media playing method, communication device and network system |
CN107918614B (en) * | 2016-10-08 | 2020-11-10 | 北京小唱科技有限公司 | Recommendation method and server for singing accompaniment |
CN109599079B (en) * | 2017-09-30 | 2022-09-23 | 腾讯科技(深圳)有限公司 | Music generation method and device |
CN108920648B (en) * | 2018-07-03 | 2021-06-22 | 四川大学 | Cross-modal matching method based on music-image semantic relation |
CN109903783A (en) * | 2019-02-27 | 2019-06-18 | 百度在线网络技术(北京)有限公司 | Multimedia control method, device and terminal |
CN112182281B (en) * | 2019-07-05 | 2023-09-19 | 腾讯科技(深圳)有限公司 | Audio recommendation method, device and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008056872A1 (en) * | 2006-11-09 | 2008-05-15 | Kyoung Jun Lee | Contents generation equipment and method compounding rf tag information and contents |
CN101312565A (en) * | 2007-05-25 | 2008-11-26 | 上海美通无线网络信息有限公司 | Method for synchronous lyrics browsing when playing music on mobile phone |
CN101567203A (en) * | 2008-04-24 | 2009-10-28 | 深圳富泰宏精密工业有限公司 | System and method for automatically searching and playing music |
CN103677776A (en) * | 2012-09-19 | 2014-03-26 | 腾讯科技(深圳)有限公司 | Music player and automatic skin switching method and system thereof |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006127694A (en) * | 2004-11-01 | 2006-05-18 | Sony Corp | Recording medium, recorder, recording method, data retrieval device, data retrieval method and data generator |
US20120166414A1 (en) * | 2008-08-11 | 2012-06-28 | Ultra Unilimited Corporation (dba Publish) | Systems and methods for relevance scoring |
-
2014
- 2014-04-21 CN CN201410161263.0A patent/CN103927366B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008056872A1 (en) * | 2006-11-09 | 2008-05-15 | Kyoung Jun Lee | Contents generation equipment and method compounding rf tag information and contents |
CN101312565A (en) * | 2007-05-25 | 2008-11-26 | 上海美通无线网络信息有限公司 | Method for synchronous lyrics browsing when playing music on mobile phone |
CN101567203A (en) * | 2008-04-24 | 2009-10-28 | 深圳富泰宏精密工业有限公司 | System and method for automatically searching and playing music |
CN103677776A (en) * | 2012-09-19 | 2014-03-26 | 腾讯科技(深圳)有限公司 | Music player and automatic skin switching method and system thereof |
Non-Patent Citations (1)
Title |
---|
一种基于社会性标注的网页排序算法;刘凯鹏,方滨兴;《计算机学报》;20100615;第33卷(第6期);第1016页-1017页 * |
Also Published As
Publication number | Publication date |
---|---|
CN103927366A (en) | 2014-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103927366B (en) | Method and system for automatically playing songs according to pictures | |
Bruni et al. | Multimodal distributional semantics | |
KR101061391B1 (en) | Relationship Extraction System between Technical Terms in Large-capacity Literature Information Using Verb-based Patterns | |
CN106570708A (en) | Management method and management system of intelligent customer service knowledge base | |
CN104899596B (en) | A kind of multi-tag sorting technique and its device | |
Cheung et al. | Sequence clustering and labeling for unsupervised query intent discovery | |
CN108664599B (en) | Intelligent question-answering method and device, intelligent question-answering server and storage medium | |
Sperberg‐McQueen | Classification and its Structures | |
Chang et al. | A novel content based image retrieval system using k-means/knn with feature extraction | |
CN105608199A (en) | Extension method and device for standard questions in intelligent question answering system | |
CN106294500B (en) | Content item pushing method, device and system | |
CN102262634A (en) | Automatic questioning and answering method and system | |
Gupta et al. | Vico: Word embeddings from visual co-occurrences | |
Hu et al. | The mood of Chinese Pop music: Representation and recognition | |
Warikoo et al. | LPTK: a linguistic pattern-aware dependency tree kernel approach for the BioCreative VI CHEMPROT task | |
Zubiaga et al. | Content-based clustering for tag cloud visualization | |
CN108304381B (en) | Entity edge establishing method, device and equipment based on artificial intelligence and storage medium | |
CN107679121B (en) | Mapping method and device of classification system, storage medium and computing equipment | |
Akella et al. | Mood classification with lyrics and convnets | |
Ruta et al. | Stylebabel: Artistic style tagging and captioning | |
CN110413882A (en) | Information-pushing method, device and equipment | |
CN111680493B (en) | English text analysis method and device, readable storage medium and computer equipment | |
CN106844743B (en) | Emotion classification method and device for Uygur language text | |
Broadwell et al. | The tell-tale hat: Surfacing the uncertainty in folklore classification | |
Bodó et al. | Connecting the last. fm dataset to lyricwiki and musicbrainz. lyrics-based experiments in genre classification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170322 |
|
CF01 | Termination of patent right due to non-payment of annual fee |