Suhwan Cho
I am a Ph.D. student at Yonsei University, Seoul, Korea. I was a Research Scientist Intern at Adobe Research, San Jose, California, USA.
My research mainly focuses on video editing technologies such as video object segmentation and video inpainting.
I am always open to collaborations! Please feel free to contact me if you are interested :)
CV /
GitHub /
Linkedin /
Google Scholar
|
|
|
Dual Prototype Attention for Unsupervised Video Object Segmentation
Suhwan Cho*, Minhyeok Lee*, Seunghoon Lee, Dogyoon Lee, Sangyoun Lee
CVPR 2024
Paper / arXiv / Code
We propose two novel prototype-based attention mechanisms to incorporate different modalities and frames via dense propagation across them.
|
|
Guided Slot Attention for Unsupervised Video Object Segmentation
Minhyeok Lee, Suhwan Cho, Dogyoon Lee, Chaewon Park, Jungho Lee, Sangyoun Lee
CVPR 2024
Paper / arXiv / Code
We propose a guided slot attention network to reinforce spatial structural information and obtain better foreground–background separation.
|
|
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
Jungho Lee, Minhyeok Lee, Suhwan Cho, Sungmin Woo, Sangyoun Lee
ICCV 2023
Paper / arXiv / Code
We propose the inter-frame curve network to effectively leverage the spatio-temporal dependency of the human skeleton.
|
|
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
Suhwan Cho, Minhyeok Lee, Seunghoon Lee, Chaewon Park, Donghyeong Kim, Sangyoun Lee
WACV 2023
Paper / arXiv / Code
We propose a novel network architecture that operates regardless of motion availability, termed as a motion-as-option network. A collaborative network learning strategy is also introduced to fully exploit the property of the proposed network.
|
|
Unsupervised Video Object Segmentation via Prototype Memory Network
Minhyeok Lee, Suhwan Cho, Seunghoon Lee, Chaewon Park, Sangyoun Lee
WACV 2023
Paper / arXiv / Code
We propose a prototype memory network architecture to effectively extract and store appearance and motion information based on component prototypes from RGB images and optical flow maps.
|
|
Tackling Background Distraction in Video Object Segmentation
Suhwan Cho, Heansung Lee, Minhyeok Lee, Chaewon Park, Sungjun Jang, Minjung Kim, Sangyoun Lee
ECCV 2022
Paper / arXiv / Code
We propose three novel strategies to suppress the negative influence of background distractions in semi-supervised video object segmentation.
|
|
SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection
Minhyeok Lee*, Chaewon Park*, Suhwan Cho, Sangyoun Lee
ECCV 2022
Paper / arXiv / Code
We propose a prototype sampling network that only samples prototypes corresponding to obtain robustness to inconsistencies between RGB images and depth maps.
|
|
Pixel-Level Bijective Matching for Video Object Segmentation
Suhwan Cho, Heansung Lee, Minjung Kim, Sungjun Jang, Sangyoun Lee
WACV 2022
Paper / arXiv / Code
We introduce a bijective matching mechanism to find the best matches from the query frame to the reference frame and also vice versa. A mask embedding module is also proposed to consider multiple historic masks simultaneously.
|
|
Dual Prototype Attention for Unsupervised Video Object Segmentation
Suhwan Cho*, Minhyeok Lee*, Seunghoon Lee, Dogyoon Lee, Sangyoun Lee
CVPR 2024
Paper / arXiv / Code
We propose two novel prototype-based attention mechanisms to incorporate different modalities and frames via dense propagation across them.
|
|
Guided Slot Attention for Unsupervised Video Object Segmentation
Minhyeok Lee, Suhwan Cho, Dogyoon Lee, Chaewon Park, Jungho Lee, Sangyoun Lee
CVPR 2024
Paper / arXiv / Code
We propose a guided slot attention network to reinforce spatial structural information and obtain better foreground–background separation.
|
|
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
Jungho Lee, Minhyeok Lee, Suhwan Cho, Sungmin Woo, Sangyoun Lee
ICCV 2023
Paper / arXiv / Code
We propose the inter-frame curve network to effectively leverage the spatio-temporal dependency of the human skeleton.
|
|
Adaptive Graph Convolution Module for Salient Object Detection
Yongwoo Lee, Minhyeok Lee, Suhwan Cho, Sangyoun Lee
ICIP 2023
Paper / arXiv / Code
We propose an adaptive graph convolution module to capture the local structural information and long-range dependencies between distant pixels effectively.
|
|
TSANET: Temporal and Scale Alignment for Unsupervised Video Object Segmentation
Seunghoon Lee, Suhwan Cho, Dogyoon Lee, Minhyeok Lee, Sangyoun Lee
ICIP 2023
Paper / arXiv / Code
We propose a novel framework for unsupervised video object segmentation, which can utilize both contextual and motion information from adjacent frames.
|
|
Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection
Chaewon Park, Minhyeok Lee, Suhwan Cho, Donghyeong Kim, Sangyoun Lee
ICASSP 2023
Paper / arXiv / Code
We propose a two-stream decoder network, designed to learn both normal and abnormal features. A feature normality estimator is also proposed to eliminate abnormal features and prevent high-quality reconstruction of abnormal regions.
|
|
FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection
Donghyeong Kim, Chaewon Park, Suhwan Cho, Sangyoun Lee
ICASSP 2023
Paper / arXiv / Code
We propose fast adaptive patch memory consisting of patch-wise and layer-wise memory banks. A patch-wise adaptive coreset sampling is also proposed for fast and accurate detection.
|
|
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
Suhwan Cho, Minhyeok Lee, Seunghoon Lee, Chaewon Park, Donghyeong Kim, Sangyoun Lee
WACV 2023
Paper / arXiv / Code
We propose a novel network architecture that operates regardless of motion availability, termed as a motion-as-option network. A collaborative network learning strategy is also introduced to fully exploit the property of the proposed network.
|
|
Unsupervised Video Object Segmentation via Prototype Memory Network
Minhyeok Lee, Suhwan Cho, Seunghoon Lee, Chaewon Park, Sangyoun Lee
WACV 2023
Paper / arXiv / Code
We propose a prototype memory network architecture to effectively extract and store appearance and motion information based on component prototypes from RGB images and optical flow maps.
|
|
Tackling Background Distraction in Video Object Segmentation
Suhwan Cho, Heansung Lee, Minhyeok Lee, Chaewon Park, Sungjun Jang, Minjung Kim, Sangyoun Lee
ECCV 2022
Paper / arXiv / Code
We propose three novel strategies to suppress the negative influence of background distractions in semi-supervised video object segmentation.
|
|
SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection
Minhyeok Lee*, Chaewon Park*, Suhwan Cho, Sangyoun Lee
ECCV 2022
Paper / arXiv / Code
We propose a prototype sampling network that only samples prototypes corresponding to obtain robustness to inconsistencies between RGB images and depth maps.
|
|
Detection-Identification Balancing Margin Loss for One-Stage Multi-Object Tracking
Heansung Lee, Suhwan Cho, Sungjun Jang, Jungho Lee, Sungmin Woo, Sangyoun Lee
ICIP 2022
Paper / arXiv / Code
We propose a detection-identification balancing margin loss for minimizing the adverse effects caused by two different objectives in one-stage multi-object tracking.
|
|
Superpixel Group-Correlation Network for Co-Saliency Detection
Minhyeok Lee, Chaewon Park, Suhwan Cho, Sangyoun Lee
ICIP 2022
Paper / arXiv / Code
We propose a superpixel group-correlation network architecture that uses a superpixel algorithm to obtain various component features from a group of images and creates a group-correlation matrix to detect the common components of those images.
|
|
Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning
Minjung Kim, MyeongAh Cho, Heansung Lee, Suhwan Cho, Sangyoun Lee
ICASSP 2022
Paper / arXiv / Code
We propose a novel occlusion correction network that corrects features through relational weight learning and obtains diverse and representative features without using external networks.
|
|
Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Features
MyeongAh Cho, Taeoh Kim, Woo Jin Kim, Suhwan Cho, Sangyoun Lee
Pattern Recognition 2022
Paper / arXiv / Code
We propose an implicit two-path AE, a structure in which two encoders implicitly model appearance and motion features, along with a single decoder that combines them to learn normal video patterns.
|
|
Pixel-Level Bijective Matching for Video Object Segmentation
Suhwan Cho, Heansung Lee, Minjung Kim, Sungjun Jang, Sangyoun Lee
WACV 2022
Paper / arXiv / Code
We introduce a bijective matching mechanism to find the best matches from the query frame to the reference frame and also vice versa. A mask embedding module is also proposed to consider multiple historic masks simultaneously.
|
|
Ghost Graph Convolutional Network for Skeleton-based Action Recognition
Sungjun Jang, Heansung Lee, Suhwan Cho, Sungmin Woo, Sangyoun Lee
ICCE-Asia 2021
Paper / arXiv / Code
We propose a simple and effective lightweight graph convolutional network for skeleton-based action recognition.
|
|
CRVOS: Clue Refining Network for Video Object Segmentation
Suhwan Cho, MyeongAh Cho, Tae-Young Chung, Heansung Lee, Sangyoun Lee
ICIP 2020
Paper / arXiv / Code
We propose a real-time clue refining network for video object segmentation that does not have any intermediate network to efficiently deal with simple scenarios.
|
|
One-Shot Video Inpainting
Sangjin Lee*, Suhwan Cho*, Sangyoun Lee
Pending
Paper / arXiv / Code
We extend video inpainting to one-shot video inpainting, which refers to erasing a designated object in a video sequence only using a single frame annotation.
|
|
Boundary-aware Camouflaged Object Detection via Deformable Point Sampling
Minhyeok Lee, Suhwan Cho, Chaewon Park, Dogyoon Lee, Jungho Lee, Sangyoun Lee
Pending
Paper / arXiv / Code
We propose deformable point sampling method and global-local aggregation architecture to integrate object's global information, background, and boundary local information to improve the camouflaged object detection.
|
|
Pixel-Level Equalized Matching for Video Object Segmentation
Suhwan Cho, Woo Jin Kim, MyeongAh Cho, Seunghoon Lee, Minhyeok Lee, Chaewon Park, Sangyoun Lee
Pending
Paper / arXiv / Code
We propose an equalized matching mechanism to overcome the limitations of existing matching methods for video object segmentation.
|
|