In TREC-9, we participated in the English-Chinese Cross-Language Information Retrieval (CLIR) track. Our work involved two aspects: finding good methods for Chinese IR, and findin...
Jianfeng Gao, Jian-Yun Nie, Jian Zhang, Endong Xun...
Video transport over error prone channels may result in loss or erroneous decoding of the video. Error concealment is an effective mechanism to reconstruct the video content. In t...
Abstract-- As viruses become more complex, existing antivirus methods are inefficient to detect various forms of viruses, especially new variants and unknown viruses. Inspired by i...
This paper addresses the probabilistic inference of geometric structures from images. Specifically, of synthesizing range data to enhance the reconstruction of a 3D model of an in...
Pose and illumination changes from picture to picture are two main barriers toward full automatic face recognition. In this paper, a novel method to handle both pose and lighting c...