Picture for Hajin Shim

Hajin Shim

SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization

Add code
Jun 21, 2023
Figure 1 for SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization
Figure 2 for SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization
Figure 3 for SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization
Figure 4 for SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization
Viaarxiv icon

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding

Add code
Dec 06, 2022
Figure 1 for Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
Figure 2 for Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
Figure 3 for Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
Figure 4 for Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
Viaarxiv icon

Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation

Add code
Dec 02, 2021
Figure 1 for Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
Figure 2 for Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
Figure 3 for Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
Figure 4 for Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
Viaarxiv icon

Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation

Nov 10, 2021
Figure 1 for Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation
Figure 2 for Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation
Figure 3 for Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation
Figure 4 for Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation
Viaarxiv icon

Mutually-Constrained Monotonic Multihead Attention for Online ASR

Add code
Mar 26, 2021
Figure 1 for Mutually-Constrained Monotonic Multihead Attention for Online ASR
Figure 2 for Mutually-Constrained Monotonic Multihead Attention for Online ASR
Figure 3 for Mutually-Constrained Monotonic Multihead Attention for Online ASR
Viaarxiv icon

Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification

Sep 18, 2017
Figure 1 for Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification
Figure 2 for Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification
Figure 3 for Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification
Figure 4 for Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification
Viaarxiv icon