GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4194-4203
Abstract
No abstract availableFunding Information
- National Science Foundation of China (62302093)
- National Science Foundation of China (52441503)
- Jiangsu Province Natural Science Fund (BK20230833)
This publication has 42 references indexed in Scilit:
- Multi-semantic Fusion Model For Generalized Zero-Shot Skeleton-Based Action Recognition2023
- TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts2022
- Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification2020
- Invertible Zero-Shot Recognition Flows2020
- Skeleton-Based Action Recognition With Shift Graph Convolutional Network2020
- Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders2019
- F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning2019
- Gesture Recognition: Focus on the Hands2018
- Feature Generating Networks for Zero-Shot Learning2018
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016