서울대학교가 올해 10월 열리는 '국제컴퓨터비전학회(ICCV)'에서 총 21편의 논문이 채택되어 역대 가장 많은 논문을 발표한다. 

ICCV는 CVPR, ECCV와 함께 컴퓨터비전 분야(AI 시각지능)의 세계 3대 학회로, 국내에서 한 대학이 20편 이상의 논문을 발표하는 것은 처음이다. 

ICCV 2021에 채택된 서울대 논문은 다음과 같다. 

• Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation (H. Jung, E. Park, S. Yoo) # 유승주 교수팀 #Oral 
• ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models (Jooyoung Choi, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon, Sungroh Yoon) # 윤성로 교수팀 #Oral
• Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning (Sungyong Baik, Janghoon Choi, Heewon Kim, Dohee Cho, Jaesik Min, and Kyoung Mu Lee) # 이경무 교수팀 #Oral
• Normalization Matters in Weakly Supervised Object Localization (Jeesoo Kim, Junsuk Choe, Sangdoo Yun, Nojun Kwak) # 곽노준 교수팀
• Training Multi-Object Detector by Estimating Bounding Box Distribution for Input Image (Jaeyoung Yoo, Hojun Lee, Inseop Chung, Geonseok Seo, Nojun Kwak) # 곽노준 교수팀
• LFI-CAM: Learning Feature Importance for Better Visual Explanation (Kwang Hee Lee, Chaewon Park, Junghyun Oh, Nojun Kwak) # 곽노준 교수팀
• Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning (Sangho Lee, Jiwan Chung, Youngjae Yu (Allen Institute for AI), Gunhee Kim, Thomas Breuel (NVIDIA), Gal Chechik (NVIDIA), Yale Song (Microsoft)) # 김건희 교수팀
• Pano-AVQA: Grounded Audio-Visual Question Answering on 360° Videos (Heeseung Yun, Youngjae Yu (Allen Institute for AI), Wonsuk Yang (Oxford university), Kangil Lee (Hyundai Motors), Gunhee Kim) # 김건희 교수팀
• Viewpoint-Agnostic Change Captioning with Cycle Consistency (Hoeseong Kim, Jongseok Kim (Violet), Hyungseok Lee (Hyundai Motors), Hyunsung Park (Hyundai Motors), Gunhee Kim) # 김건희 교수팀
• Noisy Labeled Continual Learning via Self-Purified Replay (Chris Dongjoo Kim, Jinseo Jeong, Sangwoo Moon, Gunhee Kim) # 김건희 교수팀
• SS-IL: Separated Softmax for Incremental Learning (Hongjoon Ahn, Jihwan Kwak, Subin Lim, Hyeonsu Bang, Hyojun Kim, and Taesup Moon) # 문태섭 교수팀
• Visual Graph Memory with Unsupervised Representation for Visual Navigation (Obin Kwon, Nuri Kim, Yunho Choi, Hwiyeon Yoo, Jeongho Park, and Songhwai Oh) # 오성회 교수팀
• AdvRush: Searching for Adversarially Robust Neural Architectures (Jisoo Mok, Byunggook Na, Hyeokjun Choe, Sungroh Yoon) # 윤성로 교수팀
• Toward Spatially Unbiased Generative Models (Jooyoung Choi, Jungbeom Lee, Yonghyun Jeong, Sungroh Yoon) # 윤성로 교수팀
• Motion-Aware Dynamic Architecture for Efficient Frame Interpolation (Myungsub Choi, Suyoung Lee, Heewon Kim, and Kyoung Mu Lee) # 이경무 교수팀
  
• Searching for Controllable Image Restoration Networks (Heewon Kim, Sungyong Baik, Myungsub Choi, Janghoon Choi, and Kyoung Mu Lee) # 이경무 교수팀
• C2N: Practical Generative Noise Modeling for Real-World Denoising (Geonwoon Jang, Wooseok Lee, Sanghyun Son, and Kyoungmu Lee) # 이경무 교수팀
• 3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces (Mohsen Yavartanoo, Jaeyoung Chung, Reyhaneh Neshatavar, and Kyoung Mu Lee) # 이경무 교수팀
• Self-Supervised Product Quantization for Deep Unsupervised Image Retrieval (Young Kyun Jang, Nam Ik Cho) # 조남익 교수팀
  
• Influence-balanced Loss for Imbalanced Visual Classification (Seuki Park, Daewoong Jo, Jin Young Choi) # 최진영 교수팀
• Class-Incremental Continual Learning for Action Recognition in Videos (Jaeyoo Park, Minsoo Kang, and Bohyung Han) # 한보형 교수팀
• Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform (Myungseo Song, Jinyoung Choi, and Bohyung Han) # 한보형 교수팀

ICCV 2021은 10월 11부터 일주일간 온라인으로 열린다.