Welcome to the i-VisionGroup

The Intelligent Vision Group (IVG) is affiliated with the Department of Automation, Tsinghua University. Our research areas include computer vision, pattern recognition, and machine learning. Currently, we focus on three main research topics including intelligent imaging, visual analysis (visual object segmentation, detection, matching, tracking, recognition and search), and person recognition (face, body, fingerprint, and palmprint).

News

23-Oct-2018: One paper on deep network compression is accepted by the IEEE Trans. on Pattern Analysis and Machine Intelligence.
7-Oct-2018: One paper on RGB-D action recognition is accepted by the IEEE Trans. on Circuits and Systems for Video Technology.
18-Sep-2018: Prof. Zihan Zhou from the Pennsylvania State University was invited to deliver a talk on 3D computer vision in our group.
23-Aug-2018: Prof. Vishal M. Patel from the Johns Hopkins University was invited to deliver a talk on crowd analytics in our group.
17-Jul-2018: One paper on deep binary descriptor learning is accepted by the IEEE Trans. on Pattern Analysis and Machine Intelligence.
3-Jul-2018: Seven papers on deformable face tracking, single-object tracking, multi-object tracking, large-scale image search, action prediction, pedestrian detection and deep metric learning are accepted by ECCV 2018, including one paper for oral presentation.
1-Jul-2018: One paper on group activity recognition is accepted by ACM MM 2018 for oral presentation.
29-Jun-2018: One paper on visual object tracking is accepted by IROS 2018.
26-May-2018: Two papers on medical image segmenation and search are accepted by MICCAI 2018.
17-May-2018: One paper on deformable fingerprint recognition is accepted by the IEEE Trans. on Information Forensics and Security.
30-Apr-2018: One paper on binary descriptor learning with unsupervised deep learning is accepted by the IEEE Trans. on Pattern Analysis and Machine Intelligence.
23-Apr-2018: Prof. Andreas Geiger from the University of Tübingen was invited to deliver a talk on 3D reconstruction in our group.
19-Feb-2018: Five papers on deep metric learning, binary representation learning, large-scale image search, human activity recognition, and object detection are accepted by IEEE CVPR 2018, including two spolight papers.
3-Feb-2018: One paper on large-scale image search is accepted by the Pattern Recognition journal.
2-Feb-2018: One paper on partial face recognition is accepted by the IEEE Trans. on Information Forensics and Security.
9-Dec-2017: One paper on facial age estimation is accepted by the IEEE Trans. on Circuits and Systems for Video Technology.
10-Sep-2017: One paper on facial age estimation is accepted by the IEEE Trans. on Information Forensics and Security.
6-Sep-2017: One paper on fingerprint recognition is accepted by the IEEE Trans. on Information Forensics and Security.
5-Sep-2017: One paper on deep network compression is accepted by NIPS 2017.
5-Aug-2017: One paper on feature learning for face recognition is accepted by the IEEE Trans. on Pattern Analysis and Machine Intelligence.
28-Jul-2017: One paper on deep learning for video-based face alignment is accepted by the IEEE Trans. on Pattern Analysis and Machine Intelligence.
17-Jul-2017: Three papers on deep learning for video face recognition and cross-modal multimedia search are accepted by IEEE ICCV 2017.
2-Jul-2017: One paper on RGB-D multi-modal person re-identification is accepted by the Pattern Recognition journal.
15-Jun-2017: One paper on deep metric learning is accepted by the IEEE Trans. on Image Processing.
6-Jun-2017: One paper on video face recognition is accepted by the IEEE Trans. on Image Processing.
28-May-2017: One paper on deep metric learning is accepted by the IEEE Trans. on Circuits and Systems for Video Technology.
26-May-2017: One paper on feature learning for face recognition is accepted by the IEEE Trans. on Pattern Analysis and Machine Intelligence.
25-May-2017: Our group will organize a workshop on human identification in multimedia (The Second Workshop on Human Identification in Multimedia Workshop) at IEEE ICME 2017.
16-May-2017: Mr. Zhixiang Chen is awarded for the National Postdoctoral Program for Innovative Talents.
11-May-2017: One paper on local binary descriptor learning is accepted by the IEEE Trans. on Image Processing.
11-May-2017: One paper on large-scale image search is accepted by the IEEE Trans. on Multimedia.
2-May-2017: Four papers on action recognition, image clustering, video person re-identification and fingerprint recognition are accepted by IEEE ICIP 2017.
15-Apr-2017: Dr. Jingdong Wang from the Microsoft Research Asia was invited to deliver a talk on deep network design in our group.
11-Apr-2017: Dr. Wanli Ouyang from the Chinese University of Hong Kong was invited to deliver a talk on deep learning for object detection and human pose estimation in our group.
10-Mar-2017: Two papers on person re-identification in a camera network and binary feature learning are accepted by IEEE CVPR 2017.
10-Mar-2017: Two papers on large-scale image search and partial face recognition are accepted by IEEE ICME 2017.
1-Mar-2017: One paper on large-scale image search is accepted by the IEEE Trans. on Image Processing.
22-Feb-2017: One paper on large-scale image search is accepted by the Pattern Recognition journal.
11-Feb-2017: One paper on large-scale video search is accepted by the IEEE Trans. on Circuits and Systems for Video Technology.
24-Jan-2017: One paper on facial age estimation is accepted by the IEEE FG 2017.
18-Jan-2017: One paper on face alignment in the wild is accepted by the IEEE Trans. on Image Processing.
26-Dec-2016: Prof. Xiaoming Liu from the Michigan State University was invited to deliver a talk on face analysis in our group.
20-Oct-2016: One paper on facial age estimation is accepted by the Pattern Recognition journal.
17-Oct-2016: One paper on large-scale image search is accepted by the IEEE Trans. on Multimedia.
20-Sep-2016: One paper on fingerprint registration is accepted by the Pattern Recognition journal.
5-Jan-2016: Dr. Kaiming He and Dr. Jifeng Dai from the Microsoft Research Asia were invited to deliver talks on deep learning for object detection and recognition in our group.