Filters








2,774 Hits in 2.5 sec

Reranking Methods for Visual Search

Winston H. Hsu, Lyndon S. Kennedy, Shih-Fu Chang
2007 IEEE Multimedia  
Here the authors introduce two reranking processes for image and video search that automatically reorder results from initial text-only searches based on visual features and content similarity.  ...  Most semantic video search methods use text-keyword queries or example video clips and images. But such methods have limitations.  ...  In the future, we'll develop new methods to speed the reranking processes in large-scale visual search systems.  ... 
doi:10.1109/mmul.2007.61 fatcat:2x7a5gdmhzds3gpdatl2t57umm

Visual Reranking: From Objectives to Strategies

xinmei tian, Dacheng Tao
2011 IEEE Multimedia  
To address the problems existing in current multimedia search, visual reranking has become a popular method in recent years.  ...  Visual reranking is an integrated framework (see Figure 1 ) that aims to obtain effective retrieval results efficiently. It leverages the advantages of content-based and text-based retrieval.  ...  Reranking objectives In multimedia search, the common objective of reranking is to obtain satisfactory search results for providing good search experiences for users.  ... 
doi:10.1109/mmul.2011.36 fatcat:ti34miqu4vbqnhto3oa6q7znpu

Intent based Image Ranking for Web Search Reranking

Kshitija H. Ghadge, Sunil M. Sangve
2016 IOSR Journal of Computer Engineering  
New approach is presented for reranking of the images. While searching images on the web to increase the accuracy of the image search result Image search reranking is used.  ...  Image search reranking is an effective approach to refine the initial text-based image search result. In the reranking process,image visual contents are used to refine the initial text based result.  ...  Acknowledgment Authors would like to thank the researchers as well as publishers for making their resources available and teachers for their guidance.  ... 
doi:10.9790/0661-1804029096 fatcat:fjw64622k5atzhwdikx3el5gla

Supervised reranking for web image search

Linjun Yang, Alan Hanjalic
2010 Proceedings of the international conference on Multimedia - MM '10  
Visual search reranking that aims to improve the text-based image search with the help from visual content analysis has rapidly grown into a hot research topic.  ...  the learning-to-rerank paradigm a promising alternative for robust and reliable Web-scale image search.  ...  result list, as shown by numerous existing methods for visual search reranking [26] [11] .  ... 
doi:10.1145/1873951.1873977 dblp:conf/mm/YangH10 fatcat:r2dcmmqmtvffpa6jouov76qzwa

Co-reranking by mutual reinforcement for image search

Ting Yao, Tao Mei, Chong-Wah Ngo
2010 Proceedings of the ACM International Conference on Image and Video Retrieval - CIVR '10  
Most existing reranking approaches to image search focus solely on mining "visual" cues within the initial search results.  ...  Observing that multi-modality cues carry complementary relevant information, we propose the idea of co-reranking for image search, by jointly exploring the visual and textual information.  ...  However, it is observed that most of existing reranking methods mainly exploit the visual cues from the initial search results.  ... 
doi:10.1145/1816041.1816048 dblp:conf/civr/YaoMN10 fatcat:6jeidijmmbbm3cqeb7sx5jwpam

CrowdReranking

Yuan Liu, Tao Mei, Xian-Sheng Hua
2009 Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval - SIGIR '09  
list which has visual search engines for reranking.  ...  [23], and a new method for visual search reranking called CrowdR- Live [16], build upon text search techniques by using the eranking, which is characterized by mining relevant  ... 
doi:10.1145/1571941.1572027 dblp:conf/sigir/LiuMH09 fatcat:clzelglgbvfivivaaspyipliuu

Video search reranking via online ordinal reranking

Yi-Hsuan Yang, Winston H. Hsu
2008 2008 IEEE International Conference on Multimedia and Expo  
To exploit co-occurrence patterns among features and target semantics while keeping the simplicity of the keywordbased visual search, a novel reranking methods is proposed.  ...  When evaluated in TRECVID search benchmark, ordinal reranking, while being extremely efficient, outperforms existing methods and offers 35.6% relative improvement over the text-based search baseline in  ...  Average precision of baseline and reranked search results for each query in TRECVID 2005.  ... 
doi:10.1109/icme.2008.4607427 dblp:conf/icmcs/YangH08 fatcat:wjmbfhsr4zc4pevpxvlvdyqqmy

Lightweight web image reranking

Adrian Popescu, Pierre-Alain Moëllic, Ioannis Kanellos, Rémi Landais
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
Our method is evaluated against a standard search engine using 210 diversified queries. Significant improvements are reported for both quantitative and qualitative tests.  ...  The success of visual reranking depends on the visual coherence of queries; we measure this coherence in order to evaluate the chances of success.  ...  Our reranking method is generic, fast and easy to integrate in existing Web image search architectures.  ... 
doi:10.1145/1631272.1631381 dblp:conf/mm/PopescuMKL09 fatcat:nxl3nb25zfhl5l4ke32e2ixu7y

Click-boosting multi-modality graph-based reranking for image search

Xiaopeng Yang, Yongdong Zhang, Ting Yao, Chong-Wah Ngo, Tao Mei
2014 Multimedia Systems  
Image reranking is an effective way for improving the retrieval performance of keyword-based image search engines.  ...  Encouraging results are reported for image reranking on a real-world image dataset collected from a commercial search engine with click-through data.  ...  A two-step reranking method which is a combination of using click-through data and detecting visual recurrent patterns for image search reranking.  ... 
doi:10.1007/s00530-014-0379-8 fatcat:thyd5lxa5zbl7jygne26ke3wam

Learning to judge image search results

Xinmei Tian, Yijuan Lu, Linjun Yang, Qi Tian
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
Experiments on two image search datasets show that our method achieves about 80% prediction accuracy for reranking ability assessment, and selects optimal search engine for about 70% queries correctly.  ...  Third, our method shows promising potential in applications such as reranking ability assessment and optimal search engine selection.  ...  For example, given different search algorithm settings (various visual features, visual reranking methods, etc.), our approach can automatically select the optimum settings for each query.  ... 
doi:10.1145/2072298.2072346 dblp:conf/mm/TianLYT11 fatcat:3ngtqbmgdreupejlvgfdoytrk4

A Survey on Visual Search Reranking

Thalla Shankar, Lalitha Manglaram, Murali Sadak
2014 IOSR Journal of Computer Engineering  
This paper suggests a new kind of reranking algorithm, the circular reranking, that supports the mutual exchange of information across multiple modalities for improving search performance, and follows  ...  Search reranking is considered as a best and common way to improves retrieval precision.  ...  Query-classdependent models for multimodal search by defining query classes through a clustering process according to search method performance and semantic features.  ... 
doi:10.9790/0661-16197881 fatcat:7txgqtlicnfcffteakolplwdji

Relevance Preserving Projection and Ranking for Web Image Search Reranking With Hierarchical Topic Awareness

2016 International Journal of Science and Research (IJSR)  
Image Search Reranking (ISR) technique aims at refining text-based search results by mining images' visual content. Feature extraction and ranking function design are two key steps in ISR.  ...  Here a new re-ranking method "Topic-Aware Reranking (TARerank)" is proposed.  ...  Recently for Image Search Reranking, learning to rank based method are promising technique. For example, Yang et al.  ... 
doi:10.21275/v5i3.nov161670 fatcat:x7konkpo6vd6ppttb7hnrj2mfu

Image search results refinement via outlier detection using deep contexts

Junyang Lu, Jiazhen Zhou, Jingdong Wang, Tao Mei, Xian-Sheng Hua, Shipeng Li
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
Visual reranking has become a widely-accepted method to improve traditional text-based image search results.  ...  The deep contexts for each image consist of sets of images that are returned by searches using the queries formed by the textual context of this image.  ...  Supervised reranking methods such as [7] are not used for comparison here, because these methods need training data while our methods do not. • Robust Visual Reranking (RVR) [18] -A kernel-based reranking  ... 
doi:10.1109/cvpr.2012.6248033 dblp:conf/cvpr/LuZWMHL12 fatcat:qewslq6b3fh2lpqpt3u7y6nnc4

Click-boosting random walk for image search reranking

Xiaopeng Yang, Yongdong Zhang, Ting Yao, Zheng-Jun Zha, Chong-Wah Ngo
2013 Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service - ICIMCS '13  
Image reranking is an effective way for improving the retrieval performance of keyword-based image search engines.  ...  the recurrent patterns that are potentially helpful for reranking.  ...  CONCLUSIONS In this paper, we demonstrate the effects of the combination of using click-through data and detecting visual recurrent patterns for image search reranking.  ... 
doi:10.1145/2499788.2499810 dblp:conf/icimcs/YangZYZN13 fatcat:4khgavq4vfgf5mmmzc63omotji

Online Reranking via Ordinal Informative Concepts for Context Fusion in Concept Detection and Video Search

Y.-H. Yang, W.H. Hsu, H.H. Chen
2009 IEEE transactions on circuits and systems for video technology (Print)  
While being extremely efficient, ordinal reranking outperforms existing methods by up to 40% in mean average precision (MAP) for the baseline text-based search and 12% for the baseline concept detection  ...  Ranking functions are by nature more effective than classification-based reranking methods in mining ordinal relationships.  ...  In this paper, to exploit contextual information for concept detection and visual search, we propose a novel reranking method, called ordinal reranking, that employs ranking algorithms such as RankSVM  ... 
doi:10.1109/tcsvt.2009.2026978 fatcat:vnkonvp4mvairpjeaoknam5s24
« Previous Showing results 1 — 15 out of 2,774 results