Picture for Yandong Guo

Yandong Guo

Urban4D: Semantic-Guided 4D Gaussian Splatting for Urban Scene Reconstruction

Add code
Dec 04, 2024
Viaarxiv icon

Technical Report for SoccerNet Challenge 2022 -- Replay Grounding Task

Add code
Oct 31, 2024
Figure 1 for Technical Report for SoccerNet Challenge 2022 -- Replay Grounding Task
Figure 2 for Technical Report for SoccerNet Challenge 2022 -- Replay Grounding Task
Figure 3 for Technical Report for SoccerNet Challenge 2022 -- Replay Grounding Task
Figure 4 for Technical Report for SoccerNet Challenge 2022 -- Replay Grounding Task
Viaarxiv icon

Technical Report for ActivityNet Challenge 2022 -- Temporal Action Localization

Add code
Oct 31, 2024
Viaarxiv icon

Training-Free Robust Interactive Video Object Segmentation

Add code
Jun 08, 2024
Figure 1 for Training-Free Robust Interactive Video Object Segmentation
Figure 2 for Training-Free Robust Interactive Video Object Segmentation
Figure 3 for Training-Free Robust Interactive Video Object Segmentation
Figure 4 for Training-Free Robust Interactive Video Object Segmentation
Viaarxiv icon

RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and Manipulation

Add code
Jun 06, 2024
Viaarxiv icon

The SkatingVerse Workshop & Challenge: Methods and Results

Add code
May 27, 2024
Viaarxiv icon

Debiased Novel Category Discovering and Localization

Add code
Feb 29, 2024
Viaarxiv icon

Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision

Add code
Feb 14, 2024
Viaarxiv icon

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

Add code
Dec 21, 2023
Viaarxiv icon

Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

Add code
Dec 19, 2023
Figure 1 for Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
Figure 2 for Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
Figure 3 for Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
Figure 4 for Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
Viaarxiv icon