6 papers
FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models
Kaili Zheng, Kaiwen Wang, Xun Zhu +3
Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of Multimodal Large Language Models (MLLMs) in this setting remain undere…
InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery
Kaili Zheng, Kaiwen Wang, Xun Zhu +2
Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework, capture inter-human relatio…
BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing
Kaiwen Wang, Kaili Zheng, Rongrong Deng +3
Recent multimodal large language models (MLLMs) have shown strong capabilities in general video understanding, driving growing interest in automatic sports commentary generation. H…
BoxMind: Closed-loop AI strategy optimization for elite boxing validated in the 2024 Olympics
Kaiwen Wang, Kaili Zheng, Rongrong Deng +8
Competitive sports require sophisticated tactical analysis, yet combat disciplines like boxing remain underdeveloped in AI-driven analytics due to the complexity of action dynamics…
Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
Kaiwen Wang, Kaili Zheng, Yiming Shi +2
Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-t…
Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model
Yiming Shi, Xun Zhu, Kaiwen Wang +4
3D medical image analysis is essential for modern healthcare, yet traditional task-specific models are inadequate due to limited generalizability across diverse clinical scenarios.…