CrossDiffAE: Cross-Modal Masked Diffusion Autoencoding for Zero-Shot Skeleton Action Recognition
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12243-12254
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62495094)
- Shanghai Science and Technology Commission (25ZR1401356)
- Natural Science Foundation of Chongqing (CSTB2023NSCQ-MSX0063)
- Shanghai Municipal Science and Shanghai Automotive Industry Science and Technology Development Foundation (2407)
- National Key R&D Program of China (2024YFE0115400)
This publication has 50 references indexed in Scilit:
- Zero-shot skeleton-based action recognition with dual visual-text alignmentPattern Recognition, 2025
- SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders2024
- MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion2024
- Multi-semantic Fusion Model For Generalized Zero-Shot Skeleton-Based Action Recognition2023
- Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition2023
- Smart city as a smart service system: Human-computer interaction and smart city surveillance systemsComputers in Human Behavior, 2021
- A Human–Computer Interaction framework for emotion recognition through time-series thermal video sequencesComputers and Electrical Engineering, 2021
- Towards the sustainable development of smart cities through mass video surveillance: A response to the COVID-19 pandemicSustainable Cities and Society, 2021
- Multi-view recognition system for human activity based on multiple features for video surveillance systemMultimedia Tools and Applications, 2019
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016