Picture for Ling Shao

Ling Shao

Terminus Group, Beijing, China

Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network

Add code
Mar 03, 2019
Figure 1 for Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
Figure 2 for Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
Figure 3 for Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
Figure 4 for Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
Viaarxiv icon

Pixelated Semantic Colorization

Add code
Feb 07, 2019
Figure 1 for Pixelated Semantic Colorization
Figure 2 for Pixelated Semantic Colorization
Figure 3 for Pixelated Semantic Colorization
Figure 4 for Pixelated Semantic Colorization
Viaarxiv icon

Max-margin Class Imbalanced Learning with Gaussian Affinity

Add code
Jan 23, 2019
Figure 1 for Max-margin Class Imbalanced Learning with Gaussian Affinity
Figure 2 for Max-margin Class Imbalanced Learning with Gaussian Affinity
Figure 3 for Max-margin Class Imbalanced Learning with Gaussian Affinity
Figure 4 for Max-margin Class Imbalanced Learning with Gaussian Affinity
Viaarxiv icon

Striking the Right Balance with Uncertainty

Add code
Jan 22, 2019
Figure 1 for Striking the Right Balance with Uncertainty
Figure 2 for Striking the Right Balance with Uncertainty
Figure 3 for Striking the Right Balance with Uncertainty
Figure 4 for Striking the Right Balance with Uncertainty
Viaarxiv icon

Image Super-Resolution as a Defense Against Adversarial Attacks

Add code
Jan 07, 2019
Figure 1 for Image Super-Resolution as a Defense Against Adversarial Attacks
Figure 2 for Image Super-Resolution as a Defense Against Adversarial Attacks
Figure 3 for Image Super-Resolution as a Defense Against Adversarial Attacks
Figure 4 for Image Super-Resolution as a Defense Against Adversarial Attacks
Viaarxiv icon

3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification

Add code
Jan 04, 2019
Figure 1 for 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
Figure 2 for 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
Figure 3 for 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
Figure 4 for 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
Viaarxiv icon

Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video

Add code
Dec 11, 2018
Figure 1 for Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
Figure 2 for Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
Figure 3 for Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
Figure 4 for Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
Viaarxiv icon

ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition

Add code
Oct 29, 2018
Figure 1 for ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
Figure 2 for ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
Figure 3 for ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
Figure 4 for ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
Viaarxiv icon

Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval

Add code
Oct 29, 2018
Figure 1 for Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
Figure 2 for Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
Figure 3 for Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
Figure 4 for Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
Viaarxiv icon

Highly-Economized Multi-View Binary Compression for Scalable Image Clustering

Add code
Sep 17, 2018
Figure 1 for Highly-Economized Multi-View Binary Compression for Scalable Image Clustering
Figure 2 for Highly-Economized Multi-View Binary Compression for Scalable Image Clustering
Figure 3 for Highly-Economized Multi-View Binary Compression for Scalable Image Clustering
Figure 4 for Highly-Economized Multi-View Binary Compression for Scalable Image Clustering
Viaarxiv icon