HIGH-LEVEL FEATURE EXTRACTION AND RUSHES EXPLOITATION (2008)
Xian-sheng Hua, Tao Mei, Wei Lai, Meng Wang, Jinhui Tang, Guo-jun Qi, ...
In this paper, we describe the MSRA experiments for TRECVID 2006, including details of the approaches and performance analyses for high-level feature extraction task and rushes exploitation task. For...
MSRA-USTC-SJTU AT TRECVID 2007: HIGH-LEVEL FEATURE EXTRACTION AND SEARCH (2008)
Tao Mei, Xian-sheng Hua, Wei Lai, Linjun Yang, Zheng-jun Zha, Yuan Liu, ...
This paper describes the MSRA-USTC-SJTU experiments for TRECVID 2007. We performed the experiments in high-level feature extraction and automatic search tasks. For high-level feature extraction, we...
Learning Concepts by Modeling Relationships (2008)
Abstract. Supporting multimedia search has emerged as an important research topic. There are three paradigms on the research spectrum that ranges from the least automatic to the most automatic. On...
Learning Concepts by Modeling Relationships (2008)
Abstract. Supporting multimedia search has emerged as an important research topic. There are three paradigms on the research spectrum that ranges from the least automatic to the most automatic. On...
ABSTRACT Correlative Multi-Label Video Annotation (2008)
Guo-jun Qi, Jinhui Tang, Tao Mei
Automatically annotating concepts for video is a key to semantic-level video browsing, search and navigation. The research on this topic evolved through two paradigms. The first paradigm used binary...
ABSTRACT Structure-Sensitive Manifold Ranking for Video Concept Detection (2008)
Jinhui Tang, Xian-sheng Hua, Meng Wang, Tao Mei, Guo-jun Qi, Xiuqing Wu
Pairwise similarity of samples is an essential factor in graph propagation based semi-supervised learning methods. Usually it is estimated based on Euclidean distance. However, the structural...
Concurrent multiple instance learning for image categorization (2007)
Guo-jun Qi, Xian-sheng Hua, Yong Rui, Tao Mei, Jinhui Tang, Hong-jiang Zhang
We propose a new multiple instance learning (MIL) algorithm to learn image categories. Unlike existing MIL algorithms, in which the individual instances in a bag are assumed to be independent with...