Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition

About

Large Language Models (LLMs) hold rich implicit knowledge and powerful transferability. In this paper, we explore the combination of LLMs with the human skeleton to perform action classification and description. However, when treating LLM as a recognizer, two questions arise: 1) How can LLMs understand skeleton? 2) How can LLMs distinguish among actions? To address these problems, we introduce a novel paradigm named learning Skeleton representation with visUal-motion knowledGe for Action Recognition (SUGAR). In our pipeline, we first utilize off-the-shelf large-scale video models as a knowledge base to generate visual, motion information related to actions. Then, we propose to supervise skeleton learning through this prior knowledge to yield discrete representations. Finally, we use the LLM with untouched pre-training weights to understand these representations and generate the desired action targets and descriptions. Notably, we present a Temporal Query Projection (TQP) module to continuously model the skeleton signals with long sequences. Experiments on several skeleton-based action classification benchmarks demonstrate the efficacy of our SUGAR. Moreover, experiments on zero-shot scenarios show that SUGAR is more versatile than linear-based methods.

Qilang Ye, Yu Zhou, Lian He, Jie Zhang, Xuanming Guo, Jiayu Zhang, Mingkui Tan, Weicheng Xie, Yue Sun, Tao Tan, Xiaochen Yuan, Ghada Khoriba, Zitong Yu• 2025

Related benchmarks

TaskDatasetResultRank
Action RecognitionNTU RGB+D 120 (X-set)
Accuracy89.7
770
Action RecognitionNTU RGB+D 60 (X-sub)
Accuracy95.2
496
Action RecognitionNTU RGB+D X-sub 120
Accuracy90.1
473
Action RecognitionNTU RGB+D X-View 60
Accuracy97.8
218
Showing 4 of 4 rows

Other info

Follow for update