Picture for Weihao Gan

Weihao Gan

Adaptive Rotated Convolution for Rotated Object Detection

Mar 14, 2023
Figure 1 for Adaptive Rotated Convolution for Rotated Object Detection
Figure 2 for Adaptive Rotated Convolution for Rotated Object Detection
Figure 3 for Adaptive Rotated Convolution for Rotated Object Detection
Figure 4 for Adaptive Rotated Convolution for Rotated Object Detection
Viaarxiv icon

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

Add code
May 03, 2022
Figure 1 for Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
Figure 2 for Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
Figure 3 for Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
Figure 4 for Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
Viaarxiv icon

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

Add code
Apr 17, 2022
Figure 1 for Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Figure 2 for Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Figure 3 for Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Figure 4 for Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Viaarxiv icon

Unsupervised Learning of Accurate Siamese Tracking

Add code
Apr 04, 2022
Figure 1 for Unsupervised Learning of Accurate Siamese Tracking
Figure 2 for Unsupervised Learning of Accurate Siamese Tracking
Figure 3 for Unsupervised Learning of Accurate Siamese Tracking
Figure 4 for Unsupervised Learning of Accurate Siamese Tracking
Viaarxiv icon

ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation

Add code
Mar 15, 2022
Figure 1 for ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation
Figure 2 for ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation
Figure 3 for ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation
Figure 4 for ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation
Viaarxiv icon

Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking

Add code
Mar 10, 2022
Figure 1 for Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Figure 2 for Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Figure 3 for Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Figure 4 for Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Viaarxiv icon

Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection

Dec 08, 2021
Figure 1 for Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
Figure 2 for Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
Figure 3 for Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
Figure 4 for Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
Viaarxiv icon

Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021

Jul 27, 2021
Figure 1 for Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
Figure 2 for Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
Figure 3 for Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
Figure 4 for Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
Viaarxiv icon

TSI: Temporal Saliency Integration for Video Action Recognition

Jun 02, 2021
Figure 1 for TSI: Temporal Saliency Integration for Video Action Recognition
Figure 2 for TSI: Temporal Saliency Integration for Video Action Recognition
Figure 3 for TSI: Temporal Saliency Integration for Video Action Recognition
Figure 4 for TSI: Temporal Saliency Integration for Video Action Recognition
Viaarxiv icon

Temporal Context Aggregation Network for Temporal Action Proposal Refinement

Mar 24, 2021
Figure 1 for Temporal Context Aggregation Network for Temporal Action Proposal Refinement
Figure 2 for Temporal Context Aggregation Network for Temporal Action Proposal Refinement
Figure 3 for Temporal Context Aggregation Network for Temporal Action Proposal Refinement
Figure 4 for Temporal Context Aggregation Network for Temporal Action Proposal Refinement
Viaarxiv icon