Thomas H. Li

11

Papers

0

Total Citations

Papers (11)

BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning

Deep Image Spatial Transformation for Person Image Generation

Neural Texture Extraction and Distribution for Controllable Person Image Synthesis

Hard Sample Matters a Lot in Zero-Shot Quantization

Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring

CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection

Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering

Masked Motion Encoding for Self-Supervised Video Representation Learning

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

Structure-Transformed Texture-Enhanced Network for Person Image Synthesis

Learning Vision-and-Language Navigation from YouTube Videos