Picture for Haiying Wang

Haiying Wang

School of Automation, Harbin University of Science and Technology, Harbin, 150080, China

Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification

Add code
Jun 21, 2024
Figure 1 for Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification
Figure 2 for Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification
Figure 3 for Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification
Figure 4 for Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification
Viaarxiv icon

EAR-U-Net: EfficientNet and attention-based residual U-Net for automatic liver segmentation in CT

Add code
Oct 03, 2021
Figure 1 for EAR-U-Net: EfficientNet and attention-based residual U-Net for automatic liver segmentation in CT
Figure 2 for EAR-U-Net: EfficientNet and attention-based residual U-Net for automatic liver segmentation in CT
Figure 3 for EAR-U-Net: EfficientNet and attention-based residual U-Net for automatic liver segmentation in CT
Figure 4 for EAR-U-Net: EfficientNet and attention-based residual U-Net for automatic liver segmentation in CT
Viaarxiv icon

Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing

Add code
May 30, 2021
Figure 1 for Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing
Figure 2 for Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing
Figure 3 for Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing
Figure 4 for Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing
Viaarxiv icon

Taylor saves for later: disentanglement for video prediction using Taylor representation

Add code
May 24, 2021
Figure 1 for Taylor saves for later: disentanglement for video prediction using Taylor representation
Figure 2 for Taylor saves for later: disentanglement for video prediction using Taylor representation
Figure 3 for Taylor saves for later: disentanglement for video prediction using Taylor representation
Figure 4 for Taylor saves for later: disentanglement for video prediction using Taylor representation
Viaarxiv icon

SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver CT segmentation

Add code
Mar 11, 2021
Figure 1 for SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver CT segmentation
Figure 2 for SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver CT segmentation
Figure 3 for SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver CT segmentation
Figure 4 for SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver CT segmentation
Viaarxiv icon

Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details

Add code
Jan 20, 2021
Figure 1 for Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
Figure 2 for Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
Figure 3 for Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
Figure 4 for Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
Viaarxiv icon

Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References

Add code
Jan 04, 2021
Figure 1 for Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
Figure 2 for Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
Figure 3 for Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
Figure 4 for Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
Viaarxiv icon

A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement

Add code
Jan 03, 2021
Figure 1 for A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement
Figure 2 for A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement
Figure 3 for A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement
Figure 4 for A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement
Viaarxiv icon

Incremental Transductive Learning Approaches to Schistosomiasis Vector Classification

Add code
Apr 06, 2017
Figure 1 for Incremental Transductive Learning Approaches to Schistosomiasis Vector Classification
Figure 2 for Incremental Transductive Learning Approaches to Schistosomiasis Vector Classification
Figure 3 for Incremental Transductive Learning Approaches to Schistosomiasis Vector Classification
Figure 4 for Incremental Transductive Learning Approaches to Schistosomiasis Vector Classification
Viaarxiv icon