6 papers
CooperScene: Multi-Modal Cooperative Autonomy Benchmark with C-V2X Communication Characterization
Bo Wu, Ruoshen Mo, Justin Yue +6
Cellular vehicle-to-everything (C-V2X) enables cooperative perception, prediction, and planning beyond the field of view of individual agents. However, existing datasets often over…
Image-Specific Adaptation of Transformer Encoders for Compute-Efficient Segmentation
Manyi Yao, Abhishek Aich, Yumin Suh +3
Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segme…
COOPERTRIM: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception
Shilpa Mukhopadhyay, Amit Roy-Chowdhury, Hang Qiu
Cooperative perception enables autonomous agents to share encoded representations over wireless communication to enhance each other's live situational awareness. However, the tensi…
Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networks
Yash Garg, Nebiyou Yismaw, Rakib Hyder +2
Multi-task and multi-domain learning methods seek to learn multiple tasks/domains, jointly or one after another, using a single unified network. The primary challenge and opportuni…
iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning
Manyi Yao, Bingbing Zhuang, Sparsh Garg +4
Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of struc…
CARD: Correlation Aware Restoration with Diffusion
Niki Nezakati, Arnab Ghosh, Amit Roy-Chowdhury +1
Denoising diffusion models have achieved state-of-the-art performance in image restoration by modeling the process as sequential denoising steps. However, most approaches assume in…