Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 13743-13750
Abstract
No abstract availableAll Related Versions
Funding Information
- National Natural Science Foundation of China (72192821)
- National Natural Science Foundation of China (62302297)
- National Natural Science Foundation of China (62472282)
- Young Elite Scientists Sponsorship Program by CAST (2022QNRC001)
- Fundamental Research Funds for the Central Universities (YG2023QNA35)
This publication has 19 references indexed in Scilit:
- Still-Moving: Customized Video Generation without Customized Video DataACM Transactions on Graphics, 2024
- PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding2024
- VBench: Comprehensive Benchmark Suite for Video Generative Models2024
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2024
- AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation2023
- AutoGAN-Synthesizer: Neural Architecture Search for Cross-Modality MRI Synthesis2022
- MUSIQ: Multi-scale Image Quality Transformer2021
- Optimized HRNet for image semantic segmentationExpert Systems with Applications, 2021
- Face Super-Resolution Guided by 3D Facial Priors2020
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition2019