Picture for Hailin Shi

Hailin Shi

C${^2}$RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval

Add code
Aug 19, 2024
Viaarxiv icon

I2Edit: Towards Multi-turn Interactive Image Editing via Dialogue

Add code
Mar 23, 2023
Viaarxiv icon

Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation

Add code
Sep 19, 2022
Figure 1 for Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation
Figure 2 for Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation
Figure 3 for Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation
Figure 4 for Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation
Viaarxiv icon

PetsGAN: Rethinking Priors for Single Image Generation

Add code
Mar 03, 2022
Figure 1 for PetsGAN: Rethinking Priors for Single Image Generation
Figure 2 for PetsGAN: Rethinking Priors for Single Image Generation
Figure 3 for PetsGAN: Rethinking Priors for Single Image Generation
Figure 4 for PetsGAN: Rethinking Priors for Single Image Generation
Viaarxiv icon

Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning

Add code
Dec 01, 2021
Figure 1 for Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning
Figure 2 for Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning
Figure 3 for Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning
Figure 4 for Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning
Viaarxiv icon

FasterPose: A Faster Simple Baseline for Human Pose Estimation

Add code
Jul 07, 2021
Figure 1 for FasterPose: A Faster Simple Baseline for Human Pose Estimation
Figure 2 for FasterPose: A Faster Simple Baseline for Human Pose Estimation
Figure 3 for FasterPose: A Faster Simple Baseline for Human Pose Estimation
Figure 4 for FasterPose: A Faster Simple Baseline for Human Pose Estimation
Viaarxiv icon

Boosting Semi-Supervised Face Recognition with Noise Robustness

Add code
May 10, 2021
Figure 1 for Boosting Semi-Supervised Face Recognition with Noise Robustness
Figure 2 for Boosting Semi-Supervised Face Recognition with Noise Robustness
Figure 3 for Boosting Semi-Supervised Face Recognition with Noise Robustness
Figure 4 for Boosting Semi-Supervised Face Recognition with Noise Robustness
Viaarxiv icon

Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning

Add code
May 10, 2021
Figure 1 for Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
Figure 2 for Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
Figure 3 for Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
Figure 4 for Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
Viaarxiv icon

Towards NIR-VIS Masked Face Recognition

Add code
Apr 14, 2021
Figure 1 for Towards NIR-VIS Masked Face Recognition
Figure 2 for Towards NIR-VIS Masked Face Recognition
Figure 3 for Towards NIR-VIS Masked Face Recognition
Figure 4 for Towards NIR-VIS Masked Face Recognition
Viaarxiv icon

Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition

Add code
Apr 01, 2021
Figure 1 for Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition
Figure 2 for Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition
Figure 3 for Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition
Figure 4 for Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition
Viaarxiv icon