MSRA-USTC-SJTU AT TRECVID 2007: HIGH-LEVEL FEATURE EXTRACTION AND SEARCH

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 investigated the benefit of unlabeled data by semi-supervised learning, and the multi-layer (ML) multi-instance (MI) relation embedded in video by MLMI kernel, as well as the correlations between concepts by correlative multi-label learning. For automatic search, we fuse text, visual example, and concept-based models while using temporal consistency and face information for re-ranking and result refinement.

• Type: Conference
• Year: 2007
• Where: TRECVID
• Authors: Tao Mei, Xian-Sheng Hua, Wei Lai, Linjun Yang, Zheng-Jun Zha, Yuan Liu, Zhiwei Gu, Guo-Jun Qi, Meng Wang, Jinhui Tang, Xun Yuan, Zheng Lu, Jingjing Liu
• Keywords: Automatic Search, Automatic Search Tasks, Correlative Multi-label Learning, TRECVID 2007, TRECVID 2008