Picture for Min-Hung Chen

Min-Hung Chen

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation

Add code
Apr 05, 2024
Viaarxiv icon

DoRA: Weight-Decomposed Low-Rank Adaptation

Add code
Feb 14, 2024
Viaarxiv icon

SemPLeS: Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation

Add code
Jan 22, 2024
Viaarxiv icon

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

Add code
Dec 07, 2023
Viaarxiv icon

Conditional Modeling Based Automatic Video Summarization

Add code
Nov 20, 2023
Figure 1 for Conditional Modeling Based Automatic Video Summarization
Figure 2 for Conditional Modeling Based Automatic Video Summarization
Figure 3 for Conditional Modeling Based Automatic Video Summarization
Figure 4 for Conditional Modeling Based Automatic Video Summarization
Viaarxiv icon

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision

Add code
Oct 19, 2023
Viaarxiv icon

Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter

Add code
Sep 26, 2023
Figure 1 for Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter
Figure 2 for Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter
Figure 3 for Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter
Figure 4 for Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter
Viaarxiv icon

Frequency-Aware Self-Supervised Long-Tailed Learning

Add code
Sep 15, 2023
Figure 1 for Frequency-Aware Self-Supervised Long-Tailed Learning
Figure 2 for Frequency-Aware Self-Supervised Long-Tailed Learning
Figure 3 for Frequency-Aware Self-Supervised Long-Tailed Learning
Figure 4 for Frequency-Aware Self-Supervised Long-Tailed Learning
Viaarxiv icon

Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction

Add code
Sep 07, 2023
Viaarxiv icon

QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge

Add code
Jun 30, 2023
Figure 1 for QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge
Figure 2 for QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge
Figure 3 for QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge
Figure 4 for QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge
Viaarxiv icon