Lab Group




Video Computing Group

The Video Computing Group at the University of California, Riverside conducts research on the foundations and applications of computer vision, image processing, and statistical learning from images/videos.

Principal Investigator: Amit K. Roy-Chowdhury

Current projects are related to camera networks, event recognition and prediction, visual learning with limited supervision, resource-constrained visual analysis, integrated sensing and navigation, and bio-image analysis. The work provides the scientific underpinnings behind applications in cyber-physical, autonomous and intelligent systems. Members of the group regularly publish in top-tier conferences and journals in computer vision and image processing. Past members work in major research labs and hold faculty positions across the world.

Open Positions

The Video Computing Group is looking for highly motivated and talented graduate and undergraduate students. If interested, prospective graduate students should check here for ECE students and here for CSE students. Interested undergraduate students should directly email the PI. Post-doc positions will be announced when available.

Recent News

Multiple papers on learning with limited supervision
VCG researchers have recently published a number of papers on learning in computer vision with limited supervision. Our paper in T-PAMI proposes a method for active learning by exploiting contextual data. The ECCV-18 work presents a framework for localizing activities in videos using weak supervision during training and our CVPR-…
Read More »about
Joint Image/Video and Text Analysis
Recent papers in CVPR, ACM MM, and ACM ICMR have analyzed the issue of jointly analyzing visual and textual data. The CVPR-19 paper focuses on video moment retrieval based on associated captions, the ACM MM-18 paper considers web supervision for retrieval in joint image-text databases with limited labeled data, while the ICMR…
Read More »about
Protecting Against Image/Video Manipualtions
A recent paper in T-IP proposed a novel deep network architecture for identifying image forgeries and presented results on multiple state-of-the-art datasets. A paper in NDSS-19 proposed how an adversary could design perturbations in video classification systems. Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image…
Read More »about
Papers in CVPR 2018 and ECCV 2018
Two papers have been accepted to IEEE Conf. on Computer Vision and Pattern Recognition, 2018. The details of the papers can be found here. Video Fast Forwarding via Reinforcement Learning, Exploiting Transitivity for Person Re-Identification Two papers have been accepted to the European Conf. on Computer Vision, 2018. The…
Read More »about


The Video Computing Group gratefully acknowledges the support received from a number of government agencies and private corporations.