Picture for Yanbei Chen

Yanbei Chen

Self-Supervised Multi-Object Tracking with Path Consistency

Add code
Apr 08, 2024
Figure 1 for Self-Supervised Multi-Object Tracking with Path Consistency
Figure 2 for Self-Supervised Multi-Object Tracking with Path Consistency
Figure 3 for Self-Supervised Multi-Object Tracking with Path Consistency
Figure 4 for Self-Supervised Multi-Object Tracking with Path Consistency
Viaarxiv icon

Hyperbolic Learning with Synthetic Captions for Open-World Detection

Add code
Apr 07, 2024
Figure 1 for Hyperbolic Learning with Synthetic Captions for Open-World Detection
Figure 2 for Hyperbolic Learning with Synthetic Captions for Open-World Detection
Figure 3 for Hyperbolic Learning with Synthetic Captions for Open-World Detection
Figure 4 for Hyperbolic Learning with Synthetic Captions for Open-World Detection
Viaarxiv icon

Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation

Add code
Sep 29, 2023
Figure 1 for Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation
Figure 2 for Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation
Figure 3 for Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation
Figure 4 for Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation
Viaarxiv icon

Challenges of Zero-Shot Recognition with Vision-Language Models: Granularity and Correctness

Add code
Jun 28, 2023
Figure 1 for Challenges of Zero-Shot Recognition with Vision-Language Models: Granularity and Correctness
Figure 2 for Challenges of Zero-Shot Recognition with Vision-Language Models: Granularity and Correctness
Figure 3 for Challenges of Zero-Shot Recognition with Vision-Language Models: Granularity and Correctness
Figure 4 for Challenges of Zero-Shot Recognition with Vision-Language Models: Granularity and Correctness
Viaarxiv icon

ScaleDet: A Scalable Multi-Dataset Object Detector

Add code
Jun 08, 2023
Figure 1 for ScaleDet: A Scalable Multi-Dataset Object Detector
Figure 2 for ScaleDet: A Scalable Multi-Dataset Object Detector
Figure 3 for ScaleDet: A Scalable Multi-Dataset Object Detector
Figure 4 for ScaleDet: A Scalable Multi-Dataset Object Detector
Viaarxiv icon

Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment

Add code
Nov 23, 2022
Figure 1 for Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment
Figure 2 for Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment
Figure 3 for Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment
Figure 4 for Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment
Viaarxiv icon

Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval

Add code
Oct 19, 2022
Figure 1 for Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
Figure 2 for Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
Figure 3 for Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
Figure 4 for Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
Viaarxiv icon

Semi-Supervised and Unsupervised Deep Visual Learning: A Survey

Add code
Aug 24, 2022
Figure 1 for Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Figure 2 for Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Figure 3 for Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Figure 4 for Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Viaarxiv icon

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

Add code
Jul 14, 2022
Figure 1 for BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
Viaarxiv icon

Attention Consistency on Visual Corruptions for Single-Source Domain Generalization

Add code
Apr 27, 2022
Figure 1 for Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
Figure 2 for Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
Figure 3 for Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
Figure 4 for Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
Viaarxiv icon