VLG authors are presenting 2 papers at CVPR 2026 . 1. CARD: Correlation Aware Restoration with Diffusion, N. Nezakati, A. Ghosh, A. Roy-Chowdhury, V. Saragadam. 2. SAGA: Source Attribution of Generative AI Videos, R. Kundu, V. Mohanty, H. Xiong, S. Jia, A. Balachandran, A. Roy-Chowdhury.
Shilpa Mukhopadhyay is the first author on a paper that enables autonomous agents to enhance each other’s live situational awareness. Details can be found in the pre-print below:- COOPERTRIM: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception, S. Mukhopadhyay, A. Roy-Chowdhury, H. Qiu. Udita Ghosh is the first author on a paper that utilizes preference data...
VLG authors are presenting 2 papers at NeurIPS 2025. 1. Manyi Yao is the first author on a paper that shows how spatial grounding helps with improved LLM reasoning. Details can be found in the pre-print below:- iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning, M. Yao, B. Zhuang, S. Garg, A. Roy-Chowdhury...
A number of papers from the Vision and Learning Group at UCR have recently been featured in the News which were published in prestigious venues such as CVPR 2025 and ICML 2025. 1. Deepfake Detection in Videos ( UNITE published in CVPR 2025) featured in UC News and New Scientist. 2. Machine Unlearning ( paper...
VLG authors have 5 papers accepted in total ICCV , MICCAI and EMNLP 2025! CHROME: Clothed Human REconstruction with Occlusion Resilience and Multiview-Consistency from a single image, Arindam Dutta, Meng Zheng, Zhongpai Gao, Benjamin Planche, Anwesha Choudhuri, Terrence Chen, Amit K. Roy Chowdhury, Ziyan Wu at ICCV 2025. Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes...
VLG authors have 2 papers at ICML 2025. L ayer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision-Language Models, Saketh Bachu, Erfan Shayegani, Rohit Lal, Trishna Chakraborty, Arindam Dutta, Chengyu Song, Yue Dong, Nael B. Abu-Ghazaleh, Amit K. Roy-Chowdhury A Certified Unlearning Approach without Access to Source Data, Umit Yigit Basaran, Sk Miraj...
VLG authors will be presenting 5 papers at CVPR 2025! Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI Generated Content, Rohit Kundu, Hao Xiong, Vishal Mohanty, Athula Balachandran and Amit K. Roy Chowdhury Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation, Sayak Nag, Udita Ghosh, Calvin...
VLG authors will be presenting a paper in AI-STATS 2025 Provable Benefits of Task-Specific Prompts for In-context Learning, X. Chang, Y. Li, M. Kara, S. Oymak, A. Roy-Chowdhury AI-STATS 2025 Robust Offline Imitation Learning from Diverse Auxiliary Data Udita Ghosh, Dripta Raychaudhuri, Jiachen Li, Konstantinos Karydis, Amit K. Roy-Chowdhury
VLG authors will be presenting 3 papers in NeurIPS and EMNLP 2024. CONTRAST: Continual Multi-Source Adaptation to Dynamic Distributions, Sk M. Ahmed, F. F. Niloy, D. Raychaudhuri, X. Chang, S. Oymak, A. Roy-Chowdhury NeurIPS 2024 Selective Attention: Enhancing Transformer through Principled Context Control, X. Zhang, X. Chang, M. Li, A. Roy-Chowdhury, J. Chen, S. Oymak...
Google is supporting research on deepfake detection in videos at VLG@UCR. Rohit Kundu is the first author on a CVPR paper ,who was supported by this research and is leading the project.
Three papers accepted to ICCV 2023. 1. Prior-guided Source-free Domain Adaptation for Human Pose Estimation, D. Raychaudhuri, C-K Ta, A. Dutta, R. Lal, A. Roy-Chowdhury 2. SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets, C. Simons, D. Raychaudhuri, Sk. M. Ahmed, S. You, K. Karydis, A. Roy-Chowdhury 3. Efficient Controllable Multi-Task Architectures, A. Aich...
The task of dynamic scene graph generation (SGG) from videos is complicated and challenging due to the inherent dynamics of a scene, temporal fluctuation of model predictions, and the long-tailed distribution of the visual relationships in addition to the already existing challenges in image-based SGG. Existing methods for dynamic SGG have primarily focused on capturing...
The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes include multiple dominant objects that are semantically related. Thus, it is crucial to explore designing attack strategies that look beyond learning on single-object scenes or attack single-object victim...
Cost-effective depth and infrared sensors as alternatives to usual RGB sensors are now a reality and have some advantages over RGB in domains like autonomous navigation and remote sensing. Building computer vision and deep learning systems for depth and infrared data are crucial. However, large labeled datasets for these modalities are still lacking. In such...
Image enhancement approaches often assume that the noise is signal independent, and approximate the degradation model as zero-mean additive Gaussian noise. However, this assumption does not hold for biomedical imaging systems where sensor-based sources of noise are proportional to signal strengths, and the noise is better represented as a Poisson process. The MICCAI paper explores...
Multi-task learning commonly encounters competition for resources among tasks, specifically when model capacity is limited. This challenge motivates models which allow control over the relative importance of tasks and total compute cost during inference time. In this work, we propose such a controllable multi-task network that dynamically adjusts its architecture and weights to match the...
The majority of the existing attack mechanisms today are targeted toward misclassifying specific objects and activities. However, most scenes contain multiple objects and there is usually some relationship among the objects in the scene, e.g., certain objects co-occur more frequently than others. This is often referred to as context in computer vision. We have shown...
VCG researchers are involved in two projects related to machine learning for robot autonomy. The first, funded under the National Robotics Initiative, will help monitor the health of crops. It is a collaboration with UC Merced. The second, funded by the UC Office of the President, will study the impact of agricultural technology on workforce...
