Picture for Sicheng Zhao

Sicheng Zhao

TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval

Add code
Sep 02, 2024
Viaarxiv icon

Multi-source Domain Adaptation for Panoramic Semantic Segmentation

Add code
Aug 29, 2024
Viaarxiv icon

A Survey of Embodied Learning for Object-Centric Robotic Manipulation

Add code
Aug 21, 2024
Viaarxiv icon

LLMI3D: Empowering LLM with 3D Perception from a Single 2D Image

Add code
Aug 14, 2024
Viaarxiv icon

Local Manifold Learning for No-Reference Image Quality Assessment

Add code
Jun 27, 2024
Viaarxiv icon

More is Better: Deep Domain Adaptation with Multiple Sources

Add code
May 01, 2024
Viaarxiv icon

Re-parameterized Low-rank Prompt: Generalize a Vision-Language Model within 0.5K Parameters

Add code
Dec 17, 2023
Viaarxiv icon

MACP: Efficient Model Adaptation for Cooperative Perception

Add code
Nov 07, 2023
Viaarxiv icon

Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation

Add code
Sep 29, 2023
Viaarxiv icon

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs

Add code
Sep 27, 2023
Viaarxiv icon