collaborators

7 papers

cs.CV2026

The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering

Yuqian Fu, Tianwen Qian, Yanjun Li +30

EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scena…

cs.CV2026

Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation

Kailing Li, Tianwen Qian, Lijin Yang +4

Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions. Despite recent progress with vision-la…

cs.CV2026

CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning

Kailing Li, Qi'ao Xu, Tianwen Qian +3

Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and spatiotemporal reasoning in dynamic e…

cs.CV2026

ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos

Qi'ao Xu, Tianwen Qian, Yuqian Fu +5

A core capability towards general embodied intelligence lies in localizing task-relevant objects from an egocentric perspective, formulated as Spatio-Temporal Video Grounding (STVG…

cs.CV2026

StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding

Guowei Tang, Tianwen Qian, Huanran Zheng +2

Real-time, continuous understanding of visual signals is essential for real-world interactive AI applications, and poses a fundamental system-level challenge. Existing research on…

cs.CV2026

EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering

Yanjun Li, Yuqian Fu, Tianwen Qian +5

Recent advances in Multimodal Large Language Models (MLLMs) have significantly pushed the frontier of egocentric video question answering (EgocentricQA). However, existing benchmar…