Filters








2,158 Hits in 3.6 sec

Commercial Recognition in TV Streams Using Coarse-to-Fine Matching Strategy [chapter]

Nan Liu, Yao Zhao, Zhenfeng Zhu
2010 Lecture Notes in Computer Science  
In this paper, a coarse-to-fine matching strategy and corresponding approaches are proposed to address the two key research issues in commercial recognition, which are robust signature generation and efficient  ...  The promising experimental results show the effectiveness of the proposed strategy with respect to large video data collections.  ...  Introduction As one of the key mediums, TV commercials play a ubiquitous role in our society.  ... 
doi:10.1007/978-3-642-15702-8_27 fatcat:qcscg4c235g5nfiyo3ufatrbju

Robust Commercial Retrieval in Video Streams

Jinqiao Wang, Lingyu Duan, Qingshan Liu, Hanqing Lu, Jesse S. Jin
2007 Multimedia and Expo, 2007 IEEE International Conference on  
TV commercial video is a kind of informative medium.  ...  Different from previous work using clip or key frames-based matching, our scheme has incorporated the commercial production knowledge to search the candidate commercial positions.  ...  Aiming to determine an FMPI shot, FMPI recognition is applied to shot key frames.  ... 
doi:10.1109/icme.2007.4284636 dblp:conf/icmcs/WangDLLJ07 fatcat:7hkadddtejcpzi3vhhgrs6iukm

Digesting Commercial Clips from TV Streams

Ling-Yu Duan, Jinqiao Wang, Yan-Tao Zheng, Hanqing Lu, Jesse S. Jin
2008 IEEE Multimedia  
Acknowledgment The National Natural Science Foundation of China (Grant No. 60475010) partially supported this work.  ...  Shots or image sequences are a commonly used level of granularity, 1,4 because some useful features-for example, scene change rate 1 or shot frequency 4 -are based on shots directly, and some statistically  ...  A TV commercial classification approach. Figure 6 . 6 Examples Figure 7 7 Figure 7. The recognition yield results for a frame marked with product information.  ... 
doi:10.1109/mmul.2008.4 fatcat:iguft24u4vhjfdthvzwgyocuoa

A Semantic Image Category for Structuring TV Broadcast Video Streams [chapter]

Jinqiao Wang, Lingyu Duan, Hanqing Lu, Jesse S. Jin
2006 Lecture Notes in Computer Science  
TV broadcast video stream consists of various kinds of programs such as sitcoms, news, sports, commercials, weather, etc.  ...  The recognition of POIM, together with other audiovisual features, can be used to further determine program boundaries.  ...  The data points are represented as vertices in a graph, and spectral clustering aims at partitioning a graph into disjointed sub-graphs based on the eigenvectors of the similarity matrix.  ... 
doi:10.1007/11922162_33 fatcat:ayjra2qp5vhcnfp2fn7ndutjeq

LIVE@WEB.COM – Using CBIR Technology in InteractiveWeb-TV [article]

Felix Morsdorf, Stephan Volmer
2001 Eurographics Multimedia Workshop  
The increasing amount of internet based television broadcasts has lead to new approachs to interactivity in TV programs.  ...  time of the system enough to allow for web-based interactivity.  ...  The first step is the partitioning of the video in scenes of similar visual content, as for instance via shot detection.  ... 
doi:10.2312/egmm/egmm01/189-198 fatcat:axydehfanzh2hek223be4synsi

Segmentation, categorization, and identification of commercial clips from TV streams using multimodal analysis

Ling-Yu Duan, Jinqiao Wang, Yantao Zheng, Jesse S. Jin, Hanqing Lu, Changsheng Xu
2006 Proceedings of the 14th annual ACM international conference on Multimedia - MULTIMEDIA '06  
Based on these achievements, various applications such as an intelligent digital TV set-top box can be accomplished to enhance the TV viewer's capabilities in monitoring and managing commercials from TV  ...  For the first, the boundary detection of individual commercials is reduced to the problem of binary classification of shot boundaries via the mid-level features derived from two concepts: Image Frames  ...  The recognition of brand namesFig.13 TV commercial category distribution Fig.14 Commercials with brand names recognized by ASR & OCR Fig.15 F1 values of three classifications based on different sourcesIT  ... 
doi:10.1145/1180639.1180697 dblp:conf/mm/DuanWZJLX06 fatcat:p7f3zipnejcibkc5ko7i3xei6m

Improvement of Commercial Boundary Detection Using Audiovisual Features [chapter]

Jun-Cheng Chen, Jen-Hao Yeh, Wei-Ta Chu, Jin-Hau Kuo, Ja-Ling Wu
2005 Lecture Notes in Computer Science  
Detection of commercials in TV videos is difficult because the diversity of them puts up a high barrier to construct an appropriate model.  ...  We take account of the domain knowledge of commercial production and extract features that describe the characteristics of commercials.  ...  [3] mix audio features and detect video duplicate sequences to remove commercials in TV news programs; Juan et al. [4] use recognition of key frames on shots; Albiol et al.  ... 
doi:10.1007/11581772_68 fatcat:hvb37c5fsfaudnrzgtuvp65gxi

Constructing and application of multimedia TV-news archives

H.T. Pao, Y.H. Chen, P.S. Lai, Y.Y. Xu, Hsin-Chia Fu
2008 Expert systems with applications  
By adding acoustic analysis, a news program can be partitioned into news and commercial clips, with 90% accuracy on a data set of 400 h TV-news recorded off the air from July 2005 to August 2006.  ...  The goal is to construct a compact yet meaningful abstraction of broadcast TV-news, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency.  ...  After locating each anchor shot, a SVM model based video classifier (Sun, Tseng, Chen, Chuang, & Fu, 2004) is used to detect weather report shots.  ... 
doi:10.1016/j.eswa.2007.08.056 fatcat:6v25d3rifregpbae3ynvlvcwdq

A Multimodal Scheme for Program Segmentation and Representation in Broadcast Video Streams

Jinqiao Wang, Lingyu Duan, Qingshan Liu, Hanqing Lu, J.S. Jin
2008 IEEE transactions on multimedia  
Finally, we fuse the multimodal features of POIM, ASC, and TCS to detect the boundaries of programs including individual commercials (spots).  ...  In addition, latent semantic analysis (LSA) is adopted to calculate the textual content similarity (TCS) between shots to model the inter-program similarity and intra-program dissimilarity in terms of  ...  Usually, the beginning shot documents of both news and sitcoms are more similar to the shot documents of commercials because of deficient words from ASR transcripts.  ... 
doi:10.1109/tmm.2008.917362 fatcat:olc7ct3eyrftviv4a6ervidxx4

Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels [article]

Daniel Y. Fu, Will Crichton, James Hong, Xinwei Yao, Haotian Zhang, Anh Truong, Avanika Narayan, Maneesh Agrawala, Christopher Ré, Kayvon Fatahalian
2019 arXiv   pre-print
We demonstrate the use of Rekall in analyzing video from cable TV news broadcasts, films, static-camera vehicular video streams, and commercial autonomous vehicle logs.  ...  Many real-world video analysis applications require the ability to identify domain-specific events in video, such as interviews and commercials in TV news broadcasts, or action sequences in film.  ...  We gratefully acknowledge the support of DARPA under Nos.  ... 
arXiv:1910.02993v1 fatcat:grfxvproyrc5pmetcx62vhceui

News story clustering from both what and how aspects

Wei-Ta Chu, Chao-Chin Huang, Wen-Fang Cheng
2011 Proceedings of the 2011 ACM international workshop on Automated media analysis and production for novel TV services - AIEMPro '11  
The proposed system automatically removes commercial breaks and detects anchorpersons, and then determines boundaries of news stories.  ...  The 24-hour news TV channels repeat the same news stories again and again.  ...  Acknowledgement The work was partially supported by the National Science Council of Taiwan, Republic of China under research contract NSC 100-2221-E-194-061 and NSC 99-2221-E-194-036.  ... 
doi:10.1145/2072552.2072555 fatcat:tb2p2e5j7jaarciobimr2nkamq

DEEP-AD: A Multimodal Temporal Video Segmentation Framework for Online Video Advertising

Ruxandra Tapu, Bogdan Mocanu, Titus Zaharia
2020 IEEE Access  
The video stream is first divided into shots based on a graph partition method.  ...  The experimental results, carried out on a large dataset of more than 30 videos, taken from the French National Television and US TV series validate the proposed methodology with average accuracy and recognition  ...  The shot and some parts of the scene share the same audio pattern. The last cluster of shots is divided into two independent scenes: Scene 4 and 5 based on the place recognition methodology.  ... 
doi:10.1109/access.2020.2997949 fatcat:odg577q6nbcqffnt3ufjw5dol4

Hot Event Detection and Summarization by Graph Modeling and Matching [chapter]

Yuxin Peng, Chong-Wah Ngo
2005 Lecture Notes in Computer Science  
Finally, based on the cluster size and globality of events, hot events can be automatically detected and selected as the summaries of news videos across TV stations of various channels and languages.  ...  Initially, OM is employed to measure the visual similarity between all pairs of events under the one-to-one mapping constraint among video shots.  ...  Acknowledgements The work described in this paper was fully supported by two grants from City University of Hong Kong (Project No. 7001470 and Project No. 7001546).  ... 
doi:10.1007/11526346_29 fatcat:rp7bbzirmvctxag3qnjg4rn4tq

NF-SAVO: Neuro-Fuzzy system for Arabic Video OCR

Mohamed Ben, Hichem karray, Adel. M., Ana Fernández
2012 International Journal of Advanced Computer Science and Applications  
In Arabic video text recognition, a number of noise components provide the text relatively more complicated to separate from the background.  ...  In this paper we propose a robust approach for text extraction and recognition from video clips which is called Neuro-Fuzzy system for Arabic Video OCR.  ...  ACKNOWLEDGMENT The authors would like to acknowledge the financial support of this work by grants from General Direction of Scientific Research (DGRST), Tunisia, under the ARUB program.  ... 
doi:10.14569/ijacsa.2012.031022 fatcat:exnrssn7orgxpi73pyr275b3ze

Multi-modal characteristics analysis and fusion for TV commercial detection

Nan Liu, Yao Zhao, Zhenfeng Zhu, Hanqing Lu
2010 2010 IEEE International Conference on Multimedia and Expo  
Automatic TV commercial detection has become an indispensable part of content-based video analysis technique due to the explosive growth in TV commercial volume.  ...  Aiming at exploring the power of these semantic characteristics, a kind of novel commercial-oriented descriptor from textual modality is proposed, besides taking advantage of those commonly used description  ...  Furthermore, while some recognition-based methods [5] [6] [7] achieved excellent performance on commercial detection resorting to the robust video fingerprint and efficient indexing structure, the disadvantage  ... 
doi:10.1109/icme.2010.5583867 dblp:conf/icmcs/LiuZZL10 fatcat:kklntbnil5hctkctr74wmny7pe
« Previous Showing results 1 — 15 out of 2,158 results