TNT logo
   

Publications


1   Journal

Image Search Reranking With Hierarchical Topic Awareness

Xinmei Tian, Member, IEEE, Linjun Yang, Member, IEEE, Yijuan Lu, Member, IEEE, Qi Tian, Senior Member, IEEE, and Dacheng Tao, Fellow, IEEE.

IEEE TRANSACTIONS ON CYBERNETICS (TOC), 2015
With much attention from both academia and industrial communities, visual search reranking has recently been proposed to refine image search results obtained from text-based image search engines...
PDF

Query Difficulty Estimation for Image Search With Query Reconstruction Error

Xinmei Tian, Member, IEEE, Qianghuai Jia, and Tao Mei, Senior Member, IEEE.

IEEE Transactions on Multimedia (TMM), 2015
Current image search engines suffer from a radical variance in retrieval performance over different queries.It is therefore desirable to identify those “difficult” queries in order to handle them properly...
PDF

Multi-task proximalsupportvectormachine

Ya Li, XinmeiTian, MingliSong, DachengTao.

Pattern Recognition, 2015
With the explosive growth of the use of imagery, visual recognition plays an important role in many applications and attracts increasing research attention...
PDF

Query difficulty estimation via relevance prediction for image retrieval

Qianghuai Jia,XinmeiTian.

Signal Processing, 2014
Query difficulty estimation(QDE) attempts to automatically predict the performance of the search results returned for a given query...
PDF

Discriminative codebook learning for Web image search

Xinmei Tian and Yijuan Lu.

Signal Processing, 93(8), pp. 951-962, 2013.
Given the explosive growth of the Web images, image search plays an increasingly important role in our daily lives. The visual representation of image is the fundamental factor to the quality of content-based image search...
PDF

Sparse Transfer Learning for Interactive Video Search Reranking

Xinmei Tian, Dacheng Tao and Yong Rui.

ACM Transactions on Multimedia Computing, Communica-tions, and Applications (TOMCCAP), 8(3), Artical No. 26, 2012.
Visual reranking is effective to improve the performance of the text-based video search. However, existing reranking algorithms can only achieve limited improvement because of the well-known semantic gap between low-level visual features and high-level semantic concepts...
PDF

Query Difficulty Prediction for Web Image Search

Xinmei Tian, Yijuan Lu and Linjun Yang.

IEEE Transactions on Multimedia (TMM), 14(4), pp. 951-962, 2012.
Image search plays an important role in our daily life. Given a query, the image search engine is to retrieve images related to it. However, different queries have different search dif fi culty levels...
PDF

Visual Reranking:From Objectivesto Strategies

Xinmei Tianand Dacheng Tao.

IEEE Multimedia, 18(3), pp. 12-21, 2011.
With the rapid development of recording and storage devices, as well as the signif-icant improvement of trans-mission and compression techniques, the amount of multimedia data (for example, image, video, and audio) on the Web is increas-ing and the video- and image-sharing sites are becoming more and more popular...
PDF

Real-Time Video Copy-Location Detection in Large-Scale Repositories.

Bo Liu, Zhu Li, Linjun Yang andXinmei Tian.

IEEE Multimedia, 18(3), pp. 22-31, 2011
Video copy-detection, the purpose of which is to find a video copy in a repository, is important for many applications.Our research focuses on locating video clips that are copied but maintain frame correspondence...
PDF

Bayesian Visual Reranking

Xinmei Tian, Linjun Yang, Jingdong Wang, Xiuqing Wu, and Xian-Sheng Hua.

IEEE Transactions on Multimedia (TMM), 13(4), pp. 639-652, 2011.
Visual reranking has been proven effective to refine text-based video and image search results. It utilizes visual infor-mation to recover “true” ranking list from the noisy one generated by text-based search, by incorporating both textual and visual information...
PDF

Active Reranking for Web Image Search

Xinmei Tian, Dacheng Tao, Xian-Sheng Hua, and Xiuqing Wu.

IEEE Transactions on Image Processing (TIP), 19(3), pp. 805-820, 2010.
Image search reranking methods usually fail to capture the user’s intention when the query term is ambiguous. Therefore, reranking with user interactions, or active reranking, is highly demanded to effectively improve the search performance. The essential problem in active reranking is how to target the user’s intention...
PDF

2   Conference

USER SPECIFIC FRIEND RECOMMENDATION IN SOCIAL MEDIA COMMUNITY

Cong Guo, Xinmei Tian and Tao Mei.

IEEE International Conference on Multimedia & Expo (ICME), ChengDu, Sichuan, China, 2014. (Poster)
Social networks nowadays have become an important form of communication in which users can post their current status or share their lives by mobile phones or the Web....
PDF

QUERY DIFFICULTY ESTIMATION VIA PSEUDO RELEVANCE FEEDBACK FOR IMAGE SEARCH

Qianghuai Jia, Xinmei Tian and Tao Mei.

IEEE International Conference on Multimedia & Expo (ICME), ChengDu, Sichuan, China, 2014. (Poster)
Query difficulty estimation (QDE) attempts to automatically predict the performance of the search results returned for a given query. QDE has been widely investigated in text document retrieval for many years....
PDF

SEMANTIC-SPATIAL MATCHING FOR IMAGE CLASSIFICATION

Yupeng Yan,Xinmei Tian, Linjun Yang, Yijuan Lu, and Houqiang Li.

IEEE International Conference on Multimedia & Expo (ICME), San Jose, California, USA, 2013. (Oral)
Spatial Pyramid Matching (SPM) has been proven a simple but effective extension to bag-of-visual-words image repre-sentation for spatial layout information compensation...
PDF

LEARNING IMAGE SALIENCY FROM HUMAN TOUCH BEHAVIORS

Fang, Shaomin, Yijuan Lu, and Xinmei Tian. 

Multimedia and Expo Workshops (ICMEW), 2013 
The concept of touch saliency was recently introduced to gen-erate image saliency maps based on human simple zoom be-havior on touch devices...
PDF

Learning to Judge Image Search Results

Xinmei Tian, Yijuan Lu, Linjun Yang and Qi Tian.

ACM International Conference on Multimedia (ACM MM), pp. 363–372, Scottsdale, Arizona, USA, 2011. (full paper)
Given the explosive growth of the Web and the popularity of image sharing Web sites, image retrieval plays an increas-ingly important role in our daily lives. Search engines aim to provide beneficial image search results to users in response to queries...
PDF

Visual Reranking with Local Learning Consistency

Xinmei Tian, Linjun Yang, Xiuqing Wu, and Xian-Sheng Hua.

International Conference on Multimedia Modeling (MMM), pp. 163-173, Springer-Verlag Berlin Heidelberg, 2010. (full paper)
The graph-based reranking methods have been proven effective in image and video search. The basic assumption behind them is the ranking score consistency, i.e., neighboring nodes (visually similar
images or video shots) in a graph having close ranking scores, which is modeled through a regularizer term...
PDF

Constrained Metric Learning via Distance Gap Maximization

Wei Liu,Xinmei Tian, Dacheng Tao and Jianzhuang Liu.

International Conference on Arti cial Intelligence (AAAI), pp. 518-524, Atlanta, Georgia, USA, 2010.
Vectored data frequently occur in a variety of fields, which are easy to handle since they can be mathematically abstracted as points residing in a Euclidean space. An appropriate distance
metric in the data space is quite demanding for a great number of applications...
PDF

Query Aware Visual Similarity Propagation for Image Search Reranking

Li Wang, Linjun Yang, andXinmei Tian.

ACM International Conference on Multimedia (ACM MM), pp. 725-728, Beijing, China, 2009. (short paper)
Image search reranking is an effective approach to refining the text-based image search result. In the reranking process, the estimation of visual similarity is critical to the perfor mance. However, the existing measures, based on global or local features, cannot be adapted to different queries...
PDF

MSRA AT TRECVID 2008:HIGH-LEVEL FEATURE EXTRACTION AND AUTOMATIC SEARCH

Mei, T., Zha, Z. J., Liu, Y., Wang, M., Qi, G. J., Tian, X., ... & Hua, X. S. 

Proceedings of NIST TRECVID workshop. 2008.
This paper describes the MSRA experiments for TRECVID 2008. We performed the experiments in high-level feature extraction and automatic search tasks...
PDF

Bayesian Video Search Reranking

Xinmei Tian, Linjun Yang, Jingdong Wang, Yichen Yang, Xiuqing Wu, and Xian-Sheng Hua.

ACM International Conference on Multimedia (ACM MM), pp. 131-140, Vancouver, Canada, 2008. (full paper)
Content-based video search reranking can be regarded as a process that uses visual content to recover the “true” ranking list from the noisy one generated based on textual information....
PDF

TRANSDUCTIVE VIDEO ANNOTATION VIA LOCAL LEARNABLE KERNEL CLASSIFIER

Xinmei Tian, Linjun Yang, Jingdong Wang, Xiuqing Wu, and Xian-Sheng Hua.

IEEE International Conference on Multimedia & Expo (ICME), pp. 1509-1512, Hannover, Germany, 2008.
One crucial problem in transductive video annotation is how to estimate the label from the neighboring samples. Existing methods such as graph-based Gaussian random filed only considered the pair-wise similarity and then propagated the labels based on it....
PDF

OPTIMIZED VIDEO SCENE SEGMENTATION

Jingdong Wang, Xinmei Tian, Linjun Yang, and Xian-Sheng Hua

IEEE International Conference on Multimedia & Expo (ICME), pp. 301-304, Hannover, Germany, 2008.
In this paper, we propose an optimized video scene segmentation approach with considering both content coherence and temporally contextual dissimilarity. First, a chain structure is constructed by connecting temporally adjacent shots to represent a video.....
PDF

3   Dissertation for doctor's degree
Research on Content-based Image Search Reranking
(A dissertation for doctor's degree)
PDF