Picture for Junwei Zheng

Junwei Zheng

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

Add code
Mar 21, 2024
Figure 1 for RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Figure 2 for RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Figure 3 for RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Figure 4 for RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Viaarxiv icon

Skeleton-Based Human Action Recognition with Noisy Labels

Add code
Mar 15, 2024
Figure 1 for Skeleton-Based Human Action Recognition with Noisy Labels
Figure 2 for Skeleton-Based Human Action Recognition with Noisy Labels
Figure 3 for Skeleton-Based Human Action Recognition with Noisy Labels
Figure 4 for Skeleton-Based Human Action Recognition with Noisy Labels
Viaarxiv icon

Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation

Add code
Jan 30, 2024
Viaarxiv icon

Navigating Open Set Scenarios for Skeleton-based Action Recognition

Add code
Dec 11, 2023
Viaarxiv icon

Unveiling the Hidden Realm: Self-supervised Skeleton-based Action Recognition in Occluded Environments

Add code
Sep 21, 2023
Figure 1 for Unveiling the Hidden Realm: Self-supervised Skeleton-based Action Recognition in Occluded Environments
Figure 2 for Unveiling the Hidden Realm: Self-supervised Skeleton-based Action Recognition in Occluded Environments
Figure 3 for Unveiling the Hidden Realm: Self-supervised Skeleton-based Action Recognition in Occluded Environments
Figure 4 for Unveiling the Hidden Realm: Self-supervised Skeleton-based Action Recognition in Occluded Environments
Viaarxiv icon

Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision

Add code
Sep 21, 2023
Figure 1 for Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
Figure 2 for Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
Viaarxiv icon

S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection

Add code
Sep 02, 2023
Figure 1 for S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
Figure 2 for S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
Figure 3 for S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
Figure 4 for S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
Viaarxiv icon

Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments

Add code
Jul 15, 2023
Figure 1 for Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
Figure 2 for Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
Figure 3 for Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
Figure 4 for Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
Viaarxiv icon

Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents

Jul 15, 2023
Figure 1 for Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents
Figure 2 for Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents
Figure 3 for Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents
Figure 4 for Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents
Viaarxiv icon

Attention-based Part Assembly for 3D Volumetric Shape Modeling

Apr 17, 2023
Figure 1 for Attention-based Part Assembly for 3D Volumetric Shape Modeling
Figure 2 for Attention-based Part Assembly for 3D Volumetric Shape Modeling
Figure 3 for Attention-based Part Assembly for 3D Volumetric Shape Modeling
Figure 4 for Attention-based Part Assembly for 3D Volumetric Shape Modeling
Viaarxiv icon