Xi Shen

10

Papers

107

Total Citations

Papers (10)

DEIM: DETR with Improved Matching for Fast Convergence

SURE: SUrvey REcipes for building reliable and robust deep networks

Depth-aware Test-Time Training for Zero-shot Video Object Segmentation

Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning

Self-Supervised Transformers for Unsupervised Object Discovery Using Normalized Cut

Generating Human Motion From Textual Descriptions With Discrete Representations

SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Explicit Visual Prompting for Low-Level Structure Segmentations

LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation

RANSAC-Flow: Generic Two-stage Image Alignment