3 papers
cs.CV2026
FALCON: Future-Aware Learning with Contextual Object-Centric Pretraining for UAV Action Recognition
Ruiqi Xian, Xiyang Wu, Tianrui Guan +3
We introduce FALCON, a unified self-supervised video pretraining approach for UAV action recognition from raw RGB aerial footage, requiring no additional preprocessing at inference…
cs.CV2025
EgoSocial: Benchmarking Proactive Intervention Ability of Omnimodal LLMs via Egocentric Social Interaction Perception
Xijun Wang, Tanay Sharma, Achin Kulshrestha +3
As AR/VR technologies become integral to daily life, there's a growing need for AI that understands human social dynamics from an egocentric perspective. However, current LLMs ofte…
cs.CV2025
Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models
Xijun Wang, Junyun Huang, Rayyan Abdalla +3
We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth bits) we can use for highe…