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

T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition

About

Vision-language models such as CLIP have recently achieved strong performance on a wide range of visual understanding tasks. However, most existing models rely primarily on appearance-level supervision from images or videos, and do not explicitly model human motion, which is essential for fine-grained and human-centric action recognition task as actions are defined by temporally structured and physically grounded body movements. To address this problem, we propose Transferable skeleton MOtion Representation (T-MOR), a motion-aware framework that learns transferable action representations from skeleton sequences with the aid of video and language supervision during training. T-MOR adopts a multi-modal contrastive learning scheme that aligns skeleton motion with visual and textual representations, while performing inference using only lightweight skeleton inputs. To support large-scale pre-training, we construct PoseCap-1M, a new dataset that contains over one million synchronized video, skeleton, and text triplets covering diverse human activities. We evaluate T-MOR on a range of human-centric action recognition benchmarks, including action classification and frame-wise temporal detection. Experimental results show that T-MOR consistently improves performance across multiple datasets, such as Toyota Smarthome, Penn Action, UAV-Human, TSU, and Charades. In addition, T-MOR demonstrates strong generalization ability in few-shot and zero-shot settings, highlighting the effectiveness of motion-centric and embodied representations for transferable action understanding.

Di Yang, Mahmoud Ali, Quan Kong, Gianpiero Francesca, Francois Bremond• 2026

Related benchmarks

TaskDatasetResultRank
Action RecognitionUAV-Human (CSv2)
Accuracy70.8
30
Action ClassificationSmarthome (cross-view CV2)
Accuracy66.7
28
Action ClassificationSmarthome CS
Top-1 Accuracy66.2
21
Action ClassificationPenn-Action
Top-1 Accuracy98.2
19
Action DetectionCharades
mAP (%)26
18
Action DetectionToyota Smarthome Untrimmed (TSU) (Cross-Subject (CS))
CS Accuracy38.3
11
Action ClassificationUAV-Human CS1
CS1 Accuracy44.4
10
Action DetectionPKU-MMD (CS)
mAP@IoU 0.194.3
8
Showing 8 of 8 rows

Other info

Follow for update