Computer Vision

Papers published at the venues related to computer vision such as CVPR, ECCV, ICCV, WACV, etc.

2022

Beomyoung Kim, Janghyeon Lee (KAIST), Sihaeng Lee (KAIST), Doyeon Kim (KAIST), Junmo Kim (KAIST). TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection. WACV 2022.

2021

Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang. ViDT: An Efficient and Effective Fully Transformer-based Object Detector. arXiv 2021.

Junsuk Choe, Seong Joon Oh, Sanghyuk Chun, Zeynep Akata, Hyunjung Shim. Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets. IEEE Trans on PAMI. 2021.

Byungsoo Ko, Geonmo Gu, Han-Gyu Kim. Learning with Memory-based Virtual Classes for Deep Metric Learning. ICCV 2021.

Daehee Kim (Kookmin U.), Seunghyun Park, Jinkyu Kim (Korea U.), Jaekoo Lee (Kookmin U.). SelfReg: Self-supervised Contrastive Regularization for Domain Generalization. ICCV 2021.

Jeesoo Kim (SNU), Junsuk Choe, Sangdoo Yun, Nojun Kwak (SNU). Normalization Matters in Weakly Supervised Object Localization. ICCV 2021.

Minsong Ki (Yonsei U.), Youngjung Uh (Yonsei U.), Junsuk Choe, Hyeran Byun (Yonsei U.). Contrastive Attention Maps for Self-supervised Co-localization. ICCV 2021.

Kyungjune Baek, Yunjey Choi, Youngjung Uh (Yonsei U.), Jaejun Yoo (EPFL), Hyunjung Shim (Yonsei U.). Rethinking the Truly Unsupervised Image-to-Image Translation. ICCV 2021.

Song Park, Sanghyuk Chun, Junbum Cha, Bado Lee, Hyunjung Shim (Yonsei U.). Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts. ICCV 2021. Github

Jae Myung Kim, Junsuk Choe, Zeynep Akata (U of Tuebingen), Seong Joon Oh. Keep CALM and Improve Visual Feature Attribution. ICCV 2021. Github

Byeongho Heo, Sangdoo Yun, Dongyoon Han , Sanghyuk Chun , Junsuk Choe, Seong Joon Oh. Rethinking Spatial Dimensions of Vision Transformers. ICCV 2021. Github

Dongyoon Han, Sangdoo Yun, Byeongho Heo, YoungJoon Yoo. Rethinking Channel Dimensions for Efficient Model Design. CVPR 2021. Github

Hyunsu Kim, Yunjey Choi, Junho Kim, Sungjoo Yoo (Seoul National University), Youngjung Uh (Yonsei University). Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing. CVPR 2021. Github

Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende, Yannis Kalantidis, Diane Larlus. Probabilistic Embeddings for Cross-Modal Retrieval. CVPR 2021.

Sangdoo Yun, Seong Joon Oh, Byeongho Heo, Dongyoon Han, Junsuk Choe, Sanghyuk Chun. Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels. CVPR 2021. Github

Jiyoung Lee (Yonsei), Soo-Whan Chung, Sunok Kim(Yonsei, Korea Aerospace), Hong-Goo Kang(Yonsei), Kwanghoon Sohn(Yonsei). Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation. CVPR 2021.

Jihwan Bang, Heesu Kim, Youngjoon Yoo, Jung-Woo Ha, Jonghyun Choi (GIST). Rainbow Memory: Continual Learning with a Memory of Diverse Samples. CVPR 2021. Github

2020

Sangdoo Yun, Seong Joon Oh, Byeongho Heo, Dongyoon Han, Jinhyung Kim. VideoMix: Rethinking Data Augmentation for Video Classification. ArXiv. 2020

Junsuk Choe, Seong Joon Oh, Sanghyuk Chun, Zeynep Akata, Hyunjung Shim. Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets. ArXiv. 2020

Kyungjune Baek, Yunjey Choi, Youngjung Uh, Jaejun Yoo, Hyunjung Shim. Rethinking the Truly Unsupervised Image-to-Image Translation. ArXiv. 2020

Jungkyu Lee, Taeryun Won, Kiho Hong. Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network. arXiv. 2020

Samuel Albanie, Gul Varol, Liliane Momeni, Triantafyllos Afouras, Joon Son Chung, Neil Fox, Andrew Zisserman. BSL-1K: Scaling up co-articulated sign recognition using mouthing cues. ECCV 2020.

Triantafyllos Afouras, Andrew Owens, Joon Son Chung, Andrew Zisserman. Self-supervised learning of audio-visual objects from video. ECCV 2020.

Junbum Cha, Sanghyuk Chun, Gayoung Lee, Bado Lee, Seonghyeon Kim, Hwalsuk Lee. Few-shot Compositional Font Generation with Dual Memory. ECCV 2020.

Youngmin Baek, Seung Shin, Jeonghun Baek, Sungrae Park, JunyeopLee, Daehyun Nam, Hwalsuk Lee. Character Region Attention For Text Spotting. ECCV 2020.

Minho Shim, Hsuan-I Ho, Jinhyung Kim, Dongyoon Wee. ReAD: Reciprocal Attention Discriminator for Image-to-Video Re-Identification. ECCV 2020.

Junsuk Choe, Seong Joon Oh, Sanghyuk Chun, Zeynep Akata (Univ. of Tuebingen), Hyunjung Shim (Yonsei Univ.), Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets. arXiv. 2020.

Byungsoo Ko*, Geonmo Gu*. Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning. CVPR 2020.

Jinhyung Kim, Dongyoon Wee, Soonmin Bae, Junmo Kim. Regularization on Spatio-Temporally Smoothed Feature for Action Recognition. CVPR 2020. 2020

Jaejun Yoo*, Namhyuk Ahn, Kyung-Ah Sohn. Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy. CVPR 2020. 2020

Junsuk Choe*, Seong Joon Oh*, Seungho Lee (Yonsei Univ.), Sanghyuk Chun, Zeynep Akata (Univ. of Tubingen), Hyunjung Shim (Yonsei Univ.). Evaluating Weakly Supervised Object Localization Methods Right. CVPR 2020.

Yunjey Choi*, Youngjung Uh*, Jaejun Yoo*, Jung-Woo Ha. StarGAN v2: Diverse Image Synthesis for Multiple Domains. CVPR 2020.

Dong-Hyun Hwang, Suntae Kim, Nicolas Monet, Hideki Koike, Soonmin Bae. Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning. WACV 2020.

Hyojin Park, Lars Lowe Sjösund, YoungJoon Yoo, Nicolas Monet (NAVER LABS Europe), Jihwan Bang, Nojun Kwak (Seoul National Univ.). SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder. WACV 2020.

2019

Gayoung Lee, Dohyun Kim (NAVER Webtoon), Youngjoon Yoo, Dongyoon Han, Jung-Woo Ha, Jaehyuk Chang (NAVER Webtoon). Unpaired Sketch-to-Line Translation via Synthesis of Sketches. SIGGRAPH-Asia. 2019

Chae Young Lee, Youngmin Baek, Hwalsuk Lee. TedEval: A Fair Evaluation Metric for Scene Text Detectors. Workshop on Industrial Applications of Document Analysis and Recognition 2019.

Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, Youngjoon Yoo. CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features Classification Robustness and Uncertainty. ICCV 2019 (Oral).

Jeonghun Baek, Geewook Kim, Junyeop Lee, Sungrae Park, Dongyoon Han, Sangdoo Yun, Seong Joon Oh, Hwalsuk Lee. What is Wrong with Scene Text Recognition Model Comparisons? Dataset and Model Analysis. ICCV 2019 (Oral).

Jaejun Yoo, Youngjung Uh, Sanghyuk Chun, Byungkyu Kang, Jung-Woo Ha. Photorealistic Style Transfer via Wavelet Transforms. ICCV 2019.

Byeongho Heo, Jeesoo Kim, Sangdoo Yun, Hyojin Park, Nojun Kwak, Jin Young Choi. A Comprehensive Overhaul of Feature Distillation. ICCV 2019.

Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee. Character Region Awareness for Text Detection. CVPR 2019.

2018

Kyung-Min Kim, Seong-Ho Choi (SNU), Jin-Hwa Kim (SKT), Byoung-Tak Zhang (SNU). Multimodal Dual Attention Memory for Video Story Question Answering. ECCV 2018.

Donghoon Lee (SNU), Sangdoo Yun, Sungjoon Choi (SNU), Hwiyeon Yoo (SNU), Ming-Hsuan Yang (Univ. of Merced), Songhwai Oh (SNU). Unsupervised Holistic Image Generation from Key Local Patches. ECCV 2018.

Yunjey Choi, Minje Choi (Korea Univ.), Munyoung Kim, Jung-Woo Ha, Sunghun Kim, Jaegul Choo (Korea Univ.). StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. CVPR 2018 (Oral). 2018

Jongwon Choi (SNU), Hyung Jin Chang (Univ. of Birmingham), Tobias Fischer (QUT), Sangdoo Yun, Kyuewang Lee, Jiyeoup Jeong (SNU), Yiannis Demiris (Imperial College London), Jin Young Choi (SNU). Context-aware deep feature compression for high-speed visual tracking. CVPR 2018.

2017

Hyeonseob Nam, Jung-Woo Ha, Jeonghee Kim. Dual attention networks for multimodal reasoning and matching. CVPR 2017 (Spot).