Mengmeng Xu

9

Papers

13

Total Citations

Papers (9)

Move Anything with Layered Scene Diffusion

GenTron: Diffusion Transformers for Image and Video Generation

G-TAD: Sub-Graph Localization for Temporal Action Detection

Ego4D: Around the World in 3,000 Hours of Egocentric Video

NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation

Where Is My Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization

Boundary-Sensitive Pre-Training for Temporal Localization in Videos

Learning Flow Fields in Attention for Controllable Person Image Generation

Low-Fidelity Video Encoder Optimization for Temporal Action Localization