Profiles2019-2026
Kwanghoon Sohn
Yonsei University
29Papers
27Last author
26Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers29
- Saliency-Aware Model MergingAuthor 3 of 3ICML 2026
- V-LynX: Token Interface Alignment for Video+X LLMsAuthor 3 of 3ICML 2026
- Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video RepresentationsAuthor 3 of 3CVPR 2025
- Mixture of Submodules for Domain Adaptive Person SearchAuthor 3 of 3CVPR 2025
- Bridging Vision and Language Spaces with Assignment PredictionAuthor 3 of 3ICLR 2024 · 15 citations
- A Simple Framework for Generalization in Visual RL under Dynamic Scene PerturbationsAuthor 3 of 4NeurIPS 2024 · 6 citations
- Diffusion-Driven GAN Inversion for Multi-Modal Face Image GenerationAuthor 5 of 5CVPR 2024
- Improving Visual Recognition with Hyperbolical Visual Hierarchy MappingAuthor 5 of 5CVPR 2024
- Knowing Where to Focus: Event-aware Transformer for Video GroundingAuthor 5 of 5ICCV 2023 · 103 citations
- Hierarchical Visual Primitive Experts for Compositional Zero-Shot LearningAuthor 4 of 4ICCV 2023 · 27 citations
- Dual-Path Adaptation from Image to Video TransformersAuthor 3 of 3CVPR 2023
- PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-IdentificationAuthor 5 of 5CVPR 2023
- Probabilistic Prompt Learning for Dense PredictionAuthor 6 of 6CVPR 2023
- Unsupervised Deep Asymmetric Stereo Matching with Spatially-Adaptive Self-SimilarityAuthor 3 of 3CVPR 2023
- Pin the Memory: Learning to Generalize Semantic SegmentationAuthor 5 of 5CVPR 2022 · 69 citations
- KNN Local Attention for Image RestorationAuthor 3 of 4CVPR 2022 · 62 citations
- Probabilistic Representations for Video Contrastive LearningAuthor 4 of 4CVPR 2022 · 42 citations
- Cross-Domain Grouping and Alignment for Domain Adaptive Semantic SegmentationAuthor 6 of 6AAAI 2021 · 17 citations
- Learning Canonical 3D Object Representation for Fine-Grained RecognitionAuthor 5 of 5ICCV 2021 · 14 citations
- Deep Low-Contrast Image Enhancement using Structure Tensor RepresentationAuthor 4 of 4AAAI 2021 · 3 citations
- Bridge To Answer: Structure-Aware Graph Interaction Network for Video Question AnsweringAuthor 3 of 3CVPR 2021
- Looking Into Your Speech: Learning Cross-Modal Affinity for Audio-Visual Speech SeparationAuthor 5 of 5CVPR 2021
- Memory-Guided Unsupervised Image-to-Image TranslationAuthor 4 of 4CVPR 2021
- Mining Better Samples for Contrastive Learning of Temporal CorrespondenceAuthor 4 of 4CVPR 2021
- Prototype-Guided Saliency Feature Learning for Person SearchAuthor 4 of 4CVPR 2021
- Stereoscopic Image Super-Resolution with Stereo Consistent FeatureAuthor 4 of 4AAAI 2020 · 61 citations
- Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint EstimationAuthor 7 of 7CVPR 2020
- Context-Aware Emotion Recognition NetworksAuthor 5 of 5ICCV 2019 · 285 citations
- Joint Learning of Semantic Alignment and Object Landmark DetectionAuthor 4 of 4ICCV 2019 · 18 citations
