Research
3D Reconstruction and Generation (2020~present)
Generate 3D objects from single or multiple images.
Human Pose Estimation (2019~2021)
Automatic extract 2D/3D human poses from monocular RGB videos.
High Dynamic Range Video Processing (2015~2018)
Automatic conversion from Standard Dynamic Range (SDR) video to High Dynamic Range (HDR) video by deep learning.
Hardware friendly HDR tone mapping, i.e., display HDR videos on various TVs with different luminance and color capability. This include dynamic luminance compression, dynamic color space conversion, local contrast compensation, and etc.
Deep network optimization for hardware use by trimming weak filters without obviously losing performance.
Video scene analysis and object recognition by deep learning.
Image Super-Resolution (2013~2014)
Fast hardware friendly image super-resolution by edge aware local gradient propagation.
Multi-Target Tracking (2011~2015)
Automatic tracking multiple targets in real scenes.
Weijun Wang, Ram Nevatia, and Bo Yang. Beyond Pedestrians: A Hybrid Approach of Tracking Multiple Articulating Humans. In IEEE Computer Society's Workshop on Applications of Computer Vision (WACV), Waikoloa Beach, USA, Jan. 2015.
Bo Yang and Ram Nevatia. Multi-Target Tracking by Online Learning a CRF Model of Appearance and Motion Patterns. In International Journal of Computer Vision (IJCV), vol. 107, no. 2, pp. 203-217, Apr. 2014.
Bo Yang and Ram Nevatia. Online Learned Discriminative Part-Based Appearance Models for Multi-Human Tracking. In Proceedings of European Conference on Computer Vision (ECCV), Firenze, Italy, Oct. 2012. video
Bo Yang and Ram Nevatia. An Online Learned CRF Model for Multi-Target Tracking. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), Providence, USA, Jun. 2012. video
Bo Yang and Ram Nevatia. Multi-Target Tracking by Online Learning of Non-linear Motion Patterns and Robust Appearance Models. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), Providence, USA, Jun. 2012. video
Bo Yang, Chang Huang, and Ram Nevatia. Learning Affinities and Dependencies for Multi-Target Tracking using a CRF Model. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1233-1240, Colorado Springs, USA, Jun. 2011. video
Object Segmentation (2009~2010)
Automatic segmenting an object of a pre-known category from a detection response produced by an offline learned detector.
Bo Yang, Chang Huang, and Ram Nevatia. Segmentation of Objects in a Detection Window by Nonparametric Inhomogeneous CRFs. In Computer Vision and Image Understanding (CVIU), vol. 115, no. 11, pp. 1473-1482, Nov. 2011.
Vehicle Detection fomr Lidar Data (2010~2010)
Automatic detecting vehicles from low quality aerial Lidar data. The detector is trained from few samples, and vehicle locating patterns are used to partially overcome the missing points problem.
Bo Yang, Pramod Sharma, and Ram Nevatia. Vehicle Detection from Low Quality Aerial LIDAR Data. In IEEE Computer Society's Workshop on Applications of Computer Vision (WACV), pp. 541-548, Kona, USA, Jan. 2011.
Articulated Human Detection (2008~2009)
Automatic detecting humans with articulated poses. Humans may be bending, crouching, standing, etc.
Bo Yang, Chang Huang, and Ram Nevatia. Extensive Articulated Human Detection by Voting Cluster Boosted Tree. In IEEE Computer Society's Workshop on Applications of Computer Vision (WACV), pp. 1-8, Snowbird, USA, Dec. 2009.
Video Collage (2007~2008)
Automatic generating a visually pleasing image to represent a video.
Tao Mei, Bo Yang, Shi-Qiang Yang, and Xian-Sheng Hua. Video collage: presenting a video sequence using a single image. The Visual Computer, vol. 25, no. 1, pp. 39-51, Jan. 2009.
Bo Yang, Tao Mei, Li-Feng Sun, Shi-Qiang Yang, and Xian-Sheng Hua. Free-Shaped Video Collage. In Proceedings of IEEE International Multimedia Modeling Conference (MMM), pp. 175-185, Tokyo, Japan, Jan. 2008.
Xueliang Liu, Tao Mei, Xian-Sheng Hua, Bo Yang, and He-Qin Zhou. Video Collage. In Proceedings of ACM Multimedia (MM), pp. 461-462, Augsburg, Bavaria, Germany, Sep. 2007, Demo Session.
Video Recommendation (2006~2007)
Recommend relative videos according to users' click through history.
Tao Mei, Bo Yang, and Xian-Sheng Hua. Contextual Video Recommendation by Multimodal Relevance and User Feedback. In ACM Transactions on Information Systems (TOIS), vol. 29, no. 2, pp. 10:1-10:24, Apr. 2011.
Bo Yang, Tao Mei, Xian-Sheng Hua, Linjun Yang, Shi-Qiang Yang, and Mingjing Li. Online Video Recommendation Based on Multimodal Fusion and Relevance Feedback. In Proceedings of ACM International Conference on Image and Video Retrieval (CIVR), pp. 73-80, Amsterdam, Netherland, Jul. 2007.
Tao Mei, Bo Yang, Xian-Sheng Hua, Linjun Yang, Shi-Qiang Yang, and Shipeng Li. VideoReach: An Online Video Recommendation System. In Proceedings of ACM SIGIR, pp. 767-768, Amsterdam, Netherland, Jul. 2007, Poster Session.
Soccer Video Analysis (2006~2007)
Analysis contents and key semantic regions from soccer videos.
Jia Liu, Xiaofeng Tong, Wenlong Li, Tao Wang, Yimin Zhang, Hongqi Wang, Bo Yang, Lifeng Sun, Shiqiang Yang. Automatic Player Detection, Labeling and Tracking in Broadcast Soccer Video. In Proceedings of the British Machine Vision Conference (BMVC), pp. 103-113, University of Warwick, UK. 2007.
Xiaofeng Tong, Tao Wang, Wenlong Li, Yimin Zhang, Bo Yang, Fei Wang, Lifeng Sun, and Shiqiang Yang. A Three-Level Scheme for Real-Time Ball Tracking. In Proceedings of International Workshop on Multimedia Content Analysis and Mining (MCAM), pp. 161-171, Weihai, China, Jun. 2007.
Bo Yang, Lifeng Sun, Fei Wang, Peng Wang, and Shi-Qiang Yang. Mid-Level Descriptors Extraction of Soccer Video with Domain Knowledge. In Proceedings of IEEE International Conference on System, Man, and Cybernetics (ICSMC), pp. 4937-4941, Taiwan, Oct. 2006.
Fei Wang, Lifeng Sun, Bo Yang, and Shi-Qiang Yang. Fast Arc Detection Algorithm for Play Field Registration in Soccer Video Mining. In Proceedings of IEEE International Conference on System, Man, and Cybernetics (ICSMC), pp. 4932-4936, Taiwan, Oct. 2006.
Video Enhancement (2008~2008)
Enhance videos which may suffer from under- and over-exposure at the same time
Chao Wang, Li-Feng Sun, Bo Yang, Yi-Ming liu, and Shi-Qiang Yang. Video Enhancement Using Adaptive Spatio-Temporal Connective Filter and Piecewise Mapping. EURASIP Journal on Advances in Signal Processing, vol. 2008.
Topic Mining on Web Videos (2008~2008)
Automatic mining topics from unstructured web videos
Lu Liu, Yong Rui, Li-Feng Sun, Bo Yang, Jianwei Zhang, and Shi-Qiang Yang. Topic Mining on Web-Shared Videos. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 2145-2148, Las Vegas, Nevada, U.S.A., Mar. 2008.
