2,000 Hits in 6.2 sec

A Comparison of Score, Rank and Probability-Based Fusion Methods for Video Shot Retrieval [chapter]

Kieran Mc Donald, Alan F. Smeaton
2005 Lecture Notes in Computer Science  
Using three TRECVid collections and the TRECVid search task, we specically compare fusion methods based on normalised score and rank that use either the average, weighted average or maximum of retrieval  ...  In this paper we investigate a range of fusion methods for combining based on multiple visual features (colour, edge and texture), for combining based on multiple visual examples in the query and for combining  ...  For all score and rank based fusion methods we truncate the input result lists to their top N results.  ... 
doi:10.1007/11526346_10 fatcat:u6cm5yb2mrh7paimr2xml4toya

Hierarchical feedback algorithm based on visual community discovery for interactive video retrieval

Lin Pang, Juan Cao, Yongdong Zhang, Shouxun Lin
2010 Proceedings of the ACM International Conference on Image and Video Retrieval - CIVR '10  
of video shots.  ...  Since it re-ranks video shots respectively through diffusion process in inter-community and intra-community level, HieCommunityRank can guarantee both the global diverse distribution and the local consistency  ...  community-based ranking score and the initial ranking score.  ... 
doi:10.1145/1816041.1816095 dblp:conf/civr/PangCZL10 fatcat:wes6vhinpvf4vclpzwwtb2kjai

Video search re-ranking via multi-graph propagation

Jingjing Liu, Wei Lai, Xian-Sheng Hua, Yalou Huang, Shipeng Li
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
In this PageRank-like scheme, we construct a set of graphs with the video shots as vertexes, and the conceptual and visual similarity between video shots as "hyperlinks."  ...  Then, we propose a PageRank-like graph-based approach to text-based search result re-ranking.  ...  Visual Content-Based Semantic Concept Detection Content-based semantic concept detection is a widely used method for video annotation and retrieval.  ... 
doi:10.1145/1291233.1291279 dblp:conf/mm/LiuLHHL07 fatcat:sp47lkrnmzegzpcfxootw7whxm

Semantic concept based video retrieval using convolutional neural network

Nitin Janwe, Kishor Bhoyar
2019 SN Applied Sciences  
In the proposed ranked intersection filtering technique, an intersection of ranked concept probability scores is taken from key-frames associated with a query shot to identify concepts to be used in retrieval  ...  The aim of the work presented here is to propose an improved semantic concept-based video retrieval method using a novel ranked intersection filtering technique and a foreground driven concept co-occurrence  ...  Compliance with ethical standards Conflict of interest On behalf of all authors, the corresponding author states that there is no conflict of interest.  ... 
doi:10.1007/s42452-019-1870-9 fatcat:4oablrlvsvbhdoxdtl54xu4fcm

Probabilistic optimized ranking for multimedia semantic concept detection via RVM

Yan-Tao Zheng, Shi-Yong Neo, Tat-Seng Chua, Qi Tian
2008 Proceedings of the 2008 international conference on Content-based image and video retrieval - CIVR '08  
Most existing concept detection systems utilize Support Vector Machines (SVM) to perform the detection and ranking of retrieved video shots.  ...  We present a probabilistic ranking-driven classifier for the detection of video semantic concept, such as airplane, building, etc.  ...  The target of HLF detection is that for each unseen video shots x * , we want to determine the presence of a given concept and rank x * in the retrieval list in order of its relevance.  ... 
doi:10.1145/1386352.1386378 dblp:conf/civr/ZhengNCT08 fatcat:66as6qbcqzdpfahxlqkcy2k6vm

Efficient Spatio-Temporal Edge Descriptor [chapter]

Claudiu Tănase, Bernard Merialdo
2012 Lecture Notes in Computer Science  
Concept-based video retrieval is a developing area of current multimedia content analysis research.  ...  The use of spatio-temporal descriptors in content-based video retrieval has always seemed like a promising way to bridge the semantic gap problem in ways that typical visual retrieval methods cannot.  ...  Given the classifier's output as relevance scores on a set of shots, we rank the shots in descending order of their score, and compute AP as the average of the precisions of this ranked list truncated  ... 
doi:10.1007/978-3-642-27355-1_21 fatcat:u5ashqiba5gelhj2rc3h3uijye

Waseda at TRECVID 2016: Ad-hoc Video Search

Kazuya Ueki, Kotaro Kikuchi, Susumu Saito, Tetsunori Kobayashi
2016 TREC Video Retrieval Evaluation  
Our approach used the following processing steps: manually creating several search keywords based on the given query phrase, calculating a score for each concept using visual features, and combining the  ...  Our best run achieved a mean Average Precision (mAP) of 17.7%. It was ranked the highest among all the runs submitted.  ...  Acknowledgments This work was partially supported by JSPS KAKENHI Grant Number 15K00249 and Waseda University Grant for Special Research Projects 2016A-026.  ... 
dblp:conf/trecvid/UekiKSK16 fatcat:w5k7abadnnc6jlnbqfbi5gx7j4

Waseda_Meisei at TRECVID 2017: Ad-hoc Video Search

Kazuya Ueki, Koji Hirakawa, Kotaro Kikuchi, Tetsuji Ogawa, Tetsunori Kobayashi
2017 TREC Video Retrieval Evaluation  
Concept scores for the test videos were calculated using two methods: directly using features from the output layers of the CNN, or calculating the scores from the SVMs.  ...  score for all test videos (IACC 3), manually or automatically extracting several search keywords based on the given query phrases, and combining the semantic concept scores to obtain the final search  ...  Acknowledgments This work was partially supported by JSPS KAKENHI Grant Number 15K00249 and 17H01831.  ... 
dblp:conf/trecvid/UekiHKOK17 fatcat:5bzye36bvzeevgrhueap2hsa4q

A Multimodal and Multilevel Ranking Scheme for Large-Scale Video Retrieval

Steven C. H. Hoi, Michael R. Lyu
2008 IEEE transactions on multimedia  
In this paper, we propose a novel multimodal and multilevel (MMML) ranking framework to attack the challenging ranking problem of content-based video retrieval.  ...  This problem is particularly challenging for content-based video retrieval due to some issues such as short text queries, insufficient sample learning, fusion of multimodal contents, and large-scale learning  ...  Based on the video shots, the basic NN ranking method is engaged to rerank the video shots through a linear combination of text ranking scores and visual similarity scores.  ... 
doi:10.1109/tmm.2008.921735 fatcat:xqd2wrocyjgvpetsslthr4u344

Beyond Shot Retrieval: Searching for Broadcast News Items Using Language Models of Concepts [chapter]

Robin Aly, Aiden Doherty, Djoerd Hiemstra, Alan Smeaton
2010 Lecture Notes in Computer Science  
We believe that users may better relate to longer, semantic video units and propose a retrieval framework for news story items, which consist of multiple shots.  ...  In this paper we use a method to evaluate the performance of story retrieval, based on the TRECVID shot-based retrieval groundtruth.  ...  Acknowledgments CLARITY authors AD & AS wish to acknowledge the support of Science Foundation Ireland (grant number 07/CE/I1147).  ... 
doi:10.1007/978-3-642-12275-0_23 fatcat:36rarwnsvfe37e2hynwk4rffgq

University of Central Florida at TRECVID 2007 Semantic Video Classification and Automatic Search

Jingen Liu, Yusuf Aytar, Omer Bilal Orhan, Jenny Han, Mubarak Shah
2007 TREC Video Retrieval Evaluation  
A novel earth mover's distance (EMD) based relevance procedure that finds the similarity between queries and videos through the high level features and semantic word similarity measures.  ...  Two types of discriminative low level features, Spatial Pyramid Edge/Color Histograms and Bag of Visterms, are extracted from the key-frames of the shots.  ...  Finally, the video shots are ranked and retrieved based on these relevance scores.  ... 
dblp:conf/trecvid/LiuAOHS07 fatcat:nr2j2kjryvc3vgvnjkzb3exp3a

Integrating Features, Models, and Semantics for TREC Video Retrieval

John R. Smith, Savitha Srinivasan, Arnon Amir, Sankar Basu, Giridharan Iyengar, Ching-Yung Lin, Milind R. Naphade, Dulce B. Ponceleon, Belle L. Tseng
2001 Text Retrieval Conference  
In this paper, we describe a system for automatic and interactive content-based retrieval of video that integrates features, models, and semantics.  ...  We describe our effort of applying the content-based retrieval system to the TREC video retrieval benchmark.  ...  The user can retrieve results for a model by issuing a query for a particular semantic label. The target video shots are then ranked by confidence score (higher score gives lower rank).  ... 
dblp:conf/trec/SmithSABILNPT01 fatcat:ohr7f7ernbhwtfrnylwatwnq2u

IBM Research TREC 2002 Video Retrieval System

Bill Adams, Giridharan Iyengar, Chalapathy Neti, Harriet J. Nock, Arnon Amir, Haim H. Permuter, Savitha Srinivasan, Chitra Dorai, Alejandro Jaimes, Christian A. Lang, Ching-Yung Lin, Apostol Natsev (+7 others)
2002 Text Retrieval Conference  
In this paper, we describe the IBM Research system for analysis, indexing, and retrieval of video, which was applied to the TREC-2002 video retrieval benchmark.  ...  Additional interactive methods for querying include multiple-example and relevance feedback searching, cluster, concept, and storyboard browsing, and iterative fusion based on user-selected aggregation  ...  Chiou-Ting Hsu, National Tsing-Hua University, Hsinchu, Taiwan and her students for their assistance in annotating the feature training data sets.  ... 
dblp:conf/trec/AdamsINNAPSDJLLNNSTGSAZ02 fatcat:jyjfpzawanavbjvfvlsvj64h7y

Fudan University at TRECVID 2007

Xiangyang Xue, Hui Yu, Hong Lu, Yue-Fei Guo, Yuejie Zhang, Shile Zhang, Bin Li, Bolan Su, Yingbin Zheng, Wenjian Zhou, Lei Cen, Jie Zhang (+6 others)
2007 TREC Video Retrieval Evaluation  
Fudan_T: textual retrieval Fudan_I: image retrieval Evaluation results illustrate that the AP-based fusion method yields higher precision while the MGR fusion method finds more positive shots than other  ...  Evaluation results illustrate that there are both advantages and disadvantages exist in all methods. For search, we submitted 5 interactive runs. Fudan_P: using multi-model and AP-based fusion.  ...  Acknowledgement This work was supported in part by MoE Foundation under contract 104075 and Shanghai Municipal R&D Foundation under contracts 05QMH1403, 065115017 and 06DZ15008.  ... 
dblp:conf/trecvid/XueYLGZZLSZZCZJQLDSS07 fatcat:tdbe24lxozbl7pvvhaapk4sfza

National Institute of Informatics, Japan at TRECVID 2012

Duy-Dinh Le, Cai-Zhi Zhu, Sébastien Poullot, Vu Lam, Vu Hoang Nguyen, Chi Nhan Duong, Thanh Duc Ngo, Duc Anh Duong, Shin'ichi Satoh
2012 TREC Video Retrieval Evaluation  
As for the multimedia event detection task, we only use global features to serve as a baseline method for comparison with other complicated systems using local features and multi-modal features.  ...  For the instance search task, we use the same approach as the last year's system with some modifications in quantization and fusion of query representations.  ...  In the case of a shot consisting of several sub-shots, only the maximum score among subshots' scores is used for that shot.  ... 
dblp:conf/trecvid/LeZPLNDNDS12 fatcat:vnfucuk3evfpnnhmgy3humbey4
« Previous Showing results 1 — 15 out of 2,000 results