Alert button
Picture for Jun-Cheng Chen

Jun-Cheng Chen

Alert button

BlenDA: Domain Adaptive Object Detection through diffusion-based blending

Jan 18, 2024
Tzuhsuan Huang, Chen-Che Huang, Chung-Hao Ku, Jun-Cheng Chen

Viaarxiv icon

Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement

Sep 20, 2023
Shafique Ahmed, Chia-Wei Chen, Wenze Ren, Chin-Jou Li, Ernie Chu, Jun-Cheng Chen, Amir Hussain, Hsin-Min Wang, Yu Tsao, Jen-Cheng Hou

Figure 1 for Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement
Figure 2 for Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement
Figure 3 for Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement
Figure 4 for Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement
Viaarxiv icon

MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance

Sep 01, 2023
Ernie Chu, Tzuhsuan Huang, Shuo-Yen Lin, Jun-Cheng Chen

Figure 1 for MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance
Figure 2 for MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance
Figure 3 for MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance
Figure 4 for MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance
Viaarxiv icon

Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector

Jul 16, 2023
Shuo-Yen Lin, Ernie Chu, Che-Hsien Lin, Jun-Cheng Chen, Jia-Ching Wang

Figure 1 for Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector
Figure 2 for Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector
Figure 3 for Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector
Figure 4 for Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector
Viaarxiv icon

Video ControlNet: Towards Temporally Consistent Synthetic-to-Real Video Translation Using Conditional Image Diffusion Models

May 30, 2023
Ernie Chu, Shuo-Yen Lin, Jun-Cheng Chen

Figure 1 for Video ControlNet: Towards Temporally Consistent Synthetic-to-Real Video Translation Using Conditional Image Diffusion Models
Figure 2 for Video ControlNet: Towards Temporally Consistent Synthetic-to-Real Video Translation Using Conditional Image Diffusion Models
Figure 3 for Video ControlNet: Towards Temporally Consistent Synthetic-to-Real Video Translation Using Conditional Image Diffusion Models
Figure 4 for Video ControlNet: Towards Temporally Consistent Synthetic-to-Real Video Translation Using Conditional Image Diffusion Models
Viaarxiv icon

Continual Learning for Visual Search with Backward Consistent Feature Embedding

May 26, 2022
Timmy S. T. Wan, Jun-Cheng Chen, Tzer-Yi Wu, Chu-Song Chen

Figure 1 for Continual Learning for Visual Search with Backward Consistent Feature Embedding
Figure 2 for Continual Learning for Visual Search with Backward Consistent Feature Embedding
Figure 3 for Continual Learning for Visual Search with Backward Consistent Feature Embedding
Figure 4 for Continual Learning for Visual Search with Backward Consistent Feature Embedding
Viaarxiv icon

LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network

Sep 29, 2021
Nitin Balachandran, Jun-Cheng Chen, Rama Chellappa

Figure 1 for LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network
Figure 2 for LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network
Figure 3 for LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network
Figure 4 for LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network
Viaarxiv icon

Video-based Person Re-identification without Bells and Whistles

May 22, 2021
Chih-Ting Liu, Jun-Cheng Chen, Chu-Song Chen, Shao-Yi Chien

Figure 1 for Video-based Person Re-identification without Bells and Whistles
Figure 2 for Video-based Person Re-identification without Bells and Whistles
Figure 3 for Video-based Person Re-identification without Bells and Whistles
Figure 4 for Video-based Person Re-identification without Bells and Whistles
Viaarxiv icon

Class-Aware Robust Adversarial Training for Object Detection

Mar 31, 2021
Pin-Chun Chen, Bo-Han Kung, Jun-Cheng Chen

Figure 1 for Class-Aware Robust Adversarial Training for Object Detection
Figure 2 for Class-Aware Robust Adversarial Training for Object Detection
Figure 3 for Class-Aware Robust Adversarial Training for Object Detection
Figure 4 for Class-Aware Robust Adversarial Training for Object Detection
Viaarxiv icon