5 papers
Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer
Bohao Xing, Deng Li, Rong Gao +2
Recently, Transformer has made significant progress in various vision tasks. To balance computation and efficiency in video tasks, recent works heavily rely on factorized or window…
OmniInfer: System-Wide Acceleration Techniques for Optimizing LLM Serving Throughput and Latency
Jun Wang, Yunxiang Yao, Wenwei Kuang +11
Large Language Models drive a wide range of modern AI applications but impose substantial challenges on large-scale serving systems due to intensive computation, strict latency con…
DEEMO: De-identity Multimodal Emotion Recognition and Reasoning
Deng Li, Bohao Xing, Xin Liu +3
Emotion understanding is a critical yet challenging task. Most existing approaches rely heavily on identity-sensitive information, such as facial expressions and speech, which rais…
MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition
Deng Li, Jun Shao, Bohao Xing +4
Micro-gesture recognition (MGR) targets the identification of subtle and fine-grained human motions and requires accurate modeling of both long-range and local spatiotemporal depen…
EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model
Deng Li, Xin Liu, Bohao Xing +4
Emotion AI is the ability of computers to understand human emotional states. Existing works have achieved promising progress, but two limitations remain to be solved: 1) Previous s…