Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization
By: Jingwei Peng , Zhixuan Qiu , Boyu Jin and more
Potential Business Impact:
Helps computers understand what's happening in videos.
Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods frequently encounter when dealing with diverse video data. Inspired by the remarkable capabilities of large language models, this paper introduces LVLM-VAR, a novel framework that pioneers the application of pre-trained Vision-Language Large Models (LVLMs) to video action recognition, emphasizing enhanced accuracy and interpretability. Our method features a Video-to-Semantic-Tokens (VST) Module, which innovatively transforms raw video sequences into discrete, semantically and temporally consistent "semantic action tokens," effectively crafting an "action narrative" that is comprehensible to an LVLM. These tokens, combined with natural language instructions, are then processed by a LoRA-fine-tuned LVLM (e.g., LLaVA-13B) for robust action classification and semantic reasoning. LVLM-VAR not only achieves state-of-the-art or highly competitive performance on challenging benchmarks such as NTU RGB+D and NTU RGB+D 120, demonstrating significant improvements (e.g., 94.1% on NTU RGB+D X-Sub and 90.0% on NTU RGB+D 120 X-Set), but also substantially boosts model interpretability by generating natural language explanations for its predictions.
Similar Papers
VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos
CV and Pattern Recognition
Helps computers understand actions in videos better.
Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes
CV and Pattern Recognition
Helps computers understand videos better by reading descriptions.
Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes
CV and Pattern Recognition
Helps computers understand actions from videos better.