Picture for Junwei Zheng

Junwei Zheng

Exploring Video-Based Driver Activity Recognition under Noisy Labels

Add code
Apr 16, 2025
Viaarxiv icon

Scene-agnostic Pose Regression for Visual Localization

Add code
Mar 25, 2025
Viaarxiv icon

Graph-based Document Structure Analysis

Add code
Feb 04, 2025
Figure 1 for Graph-based Document Structure Analysis
Figure 2 for Graph-based Document Structure Analysis
Figure 3 for Graph-based Document Structure Analysis
Figure 4 for Graph-based Document Structure Analysis
Viaarxiv icon

Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization

Add code
Dec 24, 2024
Figure 1 for Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Figure 2 for Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Figure 3 for Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Figure 4 for Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Viaarxiv icon

ObjectFinder: Open-Vocabulary Assistive System for Interactive Object Search by Blind People

Add code
Dec 04, 2024
Figure 1 for ObjectFinder: Open-Vocabulary Assistive System for Interactive Object Search by Blind People
Figure 2 for ObjectFinder: Open-Vocabulary Assistive System for Interactive Object Search by Blind People
Figure 3 for ObjectFinder: Open-Vocabulary Assistive System for Interactive Object Search by Blind People
Figure 4 for ObjectFinder: Open-Vocabulary Assistive System for Interactive Object Search by Blind People
Viaarxiv icon

Deformable Mamba for Wide Field of View Segmentation

Add code
Nov 25, 2024
Figure 1 for Deformable Mamba for Wide Field of View Segmentation
Figure 2 for Deformable Mamba for Wide Field of View Segmentation
Figure 3 for Deformable Mamba for Wide Field of View Segmentation
Figure 4 for Deformable Mamba for Wide Field of View Segmentation
Viaarxiv icon

@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology

Add code
Sep 21, 2024
Figure 1 for @Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
Figure 2 for @Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
Figure 3 for @Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
Figure 4 for @Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
Viaarxiv icon

OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping

Add code
Sep 20, 2024
Viaarxiv icon

Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression

Add code
Aug 06, 2024
Viaarxiv icon

Rethinking Attention Module Design for Point Cloud Analysis

Add code
Jul 27, 2024
Viaarxiv icon