5 papers
ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
Lala Shakti Swarup Ray, Mengxi Liu, Alcina Pinto +4
Wearable human activity recognition (HAR) has made steady progress, yet much of this progress remains grounded in fixed-window, closed-set classification benchmarks. This formulati…
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
Wenqi Liu, Yunxiao Wang, Shijie Ma +14
In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To addres…
PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
Yunxiao Wang, Meng Liu, Kaiyu Jiang +6
Emotional support conversations require more than fluent responses. Supporters need to understand the seeker's situation and emotions, adopt an appropriate strategy, and respond in…
Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding
Haoyu Zhang, Qiaohui Chu, Meng Liu +3
AI personal assistants, deployed through robots or wearables, require embodied understanding to collaborate effectively with humans. However, current Multimodal Large Language Mode…
TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs
Yunxiao Wang, Meng Liu, Wenqi Liu +7
Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal. To address thi…