Filters








96,751 Hits in 4.5 sec

Video Retrieval Based on Words-of-Interest Selection [chapter]

Lei Wang, Dawei Song, Eyad Elyan
2011 Lecture Notes in Computer Science  
In this paper, we present a content based video retrieval technique based on selected Words-of-Interest (WoI) that utilizes visual words spatial proximity constraint identified from the query.  ...  One of the state-of-art approaches is the Bag-of-visual Words (BoW) based technique, where images are described by a set of local features mapped to a discrete set of visual words.  ...  Introduction The rapid growth of video resources available on the internet requires effective content based video retrieval technology.  ... 
doi:10.1007/978-3-642-20161-5_71 fatcat:2chlkma7dncelnbg5y6wcgcnv4

Words-of-interest selection based on temporal motion coherence for video retrieval

Lei Wang, Dawei Song, Eyad Elyan
2011 Proceedings of the 34th international ACM SIGIR conference on Research and development in Information - SIGIR '11  
In this paper, we propose a novel technique to enhance BoW by the selection of Word-of-Interest (WoI) that utilizes the quantified temporal motion coherence of the visual words between the adjacent frames  ...  The "Bag of Visual Words" (BoW) framework has been widely used in query-by-example video retrieval to model the visual content by a set of quantized local feature descriptors.  ...  In context of queryby-example video retrieval, we believe that some selected visual words, called Words-of-Interest (WoI), are more related to the user's interest than others.  ... 
doi:10.1145/2009916.2010117 dblp:conf/sigir/WangSE11 fatcat:bipoiengojehhmrao2ymrsr6zu

A framework for surveillance video indexing and retrieval

Thi-Lan Le, Alain Boucher, Monique Thonnat, Francois Bremond
2008 2008 International Workshop on Content-Based Multimedia Indexing  
In this paper, we focus on the following features: (1) combine recognized video contents (at higher level and output from a video analysis module) with visual words (at low level computed over all the  ...  raw video frames) to enrich the video indexation in a complimentary way; using this scheme user can make queries about objects of interest even when the video analysis output is not available; (2) support  ...  We have presented in section 5 separate results of two indexing approach aspects (one is based on the recognized video content and the other is based on the visual words).  ... 
doi:10.1109/cbmi.2008.4564966 dblp:conf/cbmi/LeBTB08 fatcat:lhxgdo6u35dfdlphnom4sxgkim

Video Indexing and Retrieval based on Key Frame Extraction

Wenshi Wang
2018 International Journal of Performability Engineering  
This paper presents a key frame based method that employs shot boundary detection and "bag-ofvisual-words (BoW)" based on local keypoints for key frame extraction and semantic concept detection.  ...  Finally, this paper performs a query by concept search for video retrieval. The experimental results demonstrate that the proposed approach is capable of retrieving videos.  ...  Acknowledgements The work was supported by the National Natural Science Foundation of China (No. 61502018).  ... 
doi:10.23940/ijpe.18.08.p19.18241832 fatcat:cj55t6urknas3hwmg2qhpqac4y

Design and Achievement of Teaching Video Retrieval System Based on Key Frame

Huang Lanying, Xiong Zenggang, Zhang Xuemin, Li Zhimin, Ye Conghuan
2014 Open Cybernetics and Systemics Journal  
In case of inquiry and retrieval, such a video retrieval method as combines key word and key frame is applied.  ...  Now, a teaching video retrieval system based on key frame has been designed and achieved. The system uses mutual information extraction for the video key frame extraction.  ...  The retrieval based on key word or text uses precise matching of key word or text; the retrieval based on key frame relies on computing and inquiring the similarity matching in terms of visual feature  ... 
doi:10.2174/1874110x01408010676 fatcat:gw6ergne6vfr5lw6wtpiipikp4

Analysis of Using Metric Access Methods for Visual Search of Objects in Video Databases

Henrique Batista Silva, Zenilton Kleber Gonçalves Patrocínio, Silvio Jamil Ferzoli Guimarães
2014 Revista de Informática Teórica e Aplicada  
Our proposal is based on text-retrieval methods in which video key frames are represented by a dense set of viewpoint invariant region descriptors that enable recognition to proceed successfully despite  ...  In addition, a ranking strategy based on the spatial layout of the regions (spatial consistency) is fully described and evaluated.  ...  In [25] , an approach for video retrieval based on text retrieval methods was presented.  ... 
doi:10.22456/2175-2745.37349 fatcat:zjaglcwvdrgipfibnxaivo64oq

CUNI at MediaEval 2015 Search and Anchoring in Video Archives: Anchoring via Information Retrieval

Petra Galuscáková, Pavel Pecina
2015 MediaEval Benchmarking Initiative for Multimedia Evaluation  
We present two approaches, one based on metadata, the second one based on frequencies of proper names and numbers contained in the segments.  ...  Using the hyperlinks, the users can easily navigate through the collection and find more information about the topic of their interest.  ...  Hyperlinking [2, 3] can be further applied on the selected segments and more segments similar to the anchoring ones can be retrieved.  ... 
dblp:conf/mediaeval/GaluscakovaP15 fatcat:iyxfay4ppjhqre7hxyp6xq32ay

Searching Live Meeting Documents "Show me the Action"

Laurent Denoue, Scott Carter, Matthew Cooper
2015 Proceedings of the 2015 ACM Symposium on Document Engineering - DocEng '15  
Based on observations of real meetings, we focus on two important signals: text editing and mouse cursor motion.  ...  based on these extracted actions.  ...  If this area overlaps a word, the system detects a text selection; it also keeps track of the number of times this word was selected, which is used later for retrieval.  ... 
doi:10.1145/2682571.2797082 dblp:conf/doceng/DenoueCC15 fatcat:dlbnyr5dwjhebgudfkkjjkdtty

Improving bag-of-visual-words model with spatial-temporal correlation for video retrieval

Lei Wang, Dawei Song, Eyad Elyan
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
Most of the state-of-art approaches to Query-by-Example (QBE) video retrieval are based on the Bag-of-visual-Words (BovW) representation of visual content.  ...  Our approach is evaluated on the TRECVID2002 and CC WEB VIDEO datasets for two typical QBE video retrieval tasks respectively.  ...  Most state-of-art approaches to large scale content based visual retrieval are based on the Bag-of-visual-Words (BovW) model.  ... 
doi:10.1145/2396761.2398433 dblp:conf/cikm/WangSE12 fatcat:gtcucguihnc3ff7ygefqxypvty

Content based video retrieval system using principal object analysis

Bui Van Thinh, Tran Anh Tuan, Ngo Quoc Viet, Pham The Bao
2019 Tạp chí Khoa học  
Video retrieval is a searching problem on videos or clips based on the content of video clips which relates to the input image or video.  ...  Then, the model "Bag-of-words" in accompanied by SVM classification are applied to obtain the retrieval result.  ...  Context-based video retrieval is an approach using information such as text or audio. Advantages of such information are to search video based on the content from spoken words in the conversations.  ... 
doi:10.54607/hcmue.js.14.9.291(2017) fatcat:fxnqes75cfhxjoy4wmmgytfy6u

Intelligent Sports Video Classification Based on Deep Neural Network (DNN) Algorithm and Transfer Learning

Xiaoping Guo, Suneet Kumar Gupta
2021 Computational Intelligence and Neuroscience  
Traditional content-based video retrieval uses convolutional neural networks to extract the underlying feature information of images to build indexes and achieves similarity retrieval of video feature  ...  In this paper, by studying the characteristics of sports videos, we propose the histogram difference method based on using transfer learning and the four-step method based on block matching for mutation  ...  A video retrieval system is a retrieval system for users, and the ultimate goal is to ensure that users can retrieve the video information of interest.  ... 
doi:10.1155/2021/1825273 pmid:34868286 pmcid:PMC8635908 fatcat:4sglxathbzatnkf7sejohhhbru

A proposal of Smart TV System focused on findability

Toru Kobayashi
2013 2013 IEEE 2nd Global Conference on Consumer Electronics (GCCE)  
It also allows us to see retrieved information via multi-screen environment based on the intuitive user interface.  ...  I propose a Smart TV System focused on findability. This system allows us to retrieve information without typing-in search key words.  ...  When the user selects the one of hot words, the associated information will be displayed on the second contact zone. The shared video or the private video/photos are shown as thumbnails.  ... 
doi:10.1109/gcce.2013.6664904 dblp:conf/gcce/Kobayashi13 fatcat:ymq7xzbe5bcjnfnxkxam5ngaau

VideoQA

Hui Yang, Lekha Chaisorn, Yunlong Zhao, Shi-Yong Neo, Tat-Seng Chua
2003 Proceedings of the eleventh ACM international conference on Multimedia - MULTIMEDIA '03  
When querying a news video archive, the users are interested in retrieving precise answers in the form of a summary that best answers the query.  ...  However, current video retrieval systems, including the search engines on the web, are designed to retrieve documents instead of precise answers.  ...  The conventional video retrieval based on transcript suffers a lot from the numerous speech recognition errors.  ... 
doi:10.1145/957142.957146 fatcat:62vsxiawurf6zpv6qwl4llcn24

VideoQA

Hui Yang, Lekha Chaisorn, Yunlong Zhao, Shi-Yong Neo, Tat-Seng Chua
2003 Proceedings of the eleventh ACM international conference on Multimedia - MULTIMEDIA '03  
When querying a news video archive, the users are interested in retrieving precise answers in the form of a summary that best answers the query.  ...  However, current video retrieval systems, including the search engines on the web, are designed to retrieve documents instead of precise answers.  ...  The conventional video retrieval based on transcript suffers a lot from the numerous speech recognition errors.  ... 
doi:10.1145/957013.957146 dblp:conf/mm/YangCZNC03 fatcat:437qo4lfsfbrtkleaoy7jtln54

A Content-Based Video Retrieval Method Using a Visualized Sound Pattern [chapter]

Katsunobu Fushikida, Yoshitsugu Hiwatari, Hideyo Waki
1998 Visual Database Systems 4 (VDB4)  
A content-based video scene retrieval method using a multimodal index is proposed. Representative images of video scenes and corresponding visualized sound patterns are used as the multimodal index.  ...  The results of video index browsing experiments indicate the effectiveness of the image-sound combined index method for efficient video queries and understanding the content.  ...  Multimodal retrieval for video database Typical video indexes such as text indexes, image indexes and sound indexes have been discussed for content-based retrieval.  ... 
doi:10.1007/978-0-387-35372-2_18 fatcat:cxj56pyx4nd6njqtnuvltvfqb4
« Previous Showing results 1 — 15 out of 96,751 results