Kwanghoon Sohn

Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations CVPR 2025 Faster Parameter-Efficient Tuning with Token Redundancy Reduction CVPR 2025 Mixture of Submodules for Domain Adaptive Person Search CVPR 2025 A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations NeurIPS 2024 Bridging Vision and Language Spaces with Assignment Prediction ICLR 2024 Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation CVPR 2024 EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models ECCV 2024 Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation ECCV 2024 Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping CVPR 2024 Layer-Wise Auto-Weighting for Non-Stationary Test-Time Adaptation WACV 2024 Dual-Path Adaptation From Image to Video Transformers CVPR 2023 Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning ICCV 2023 Knowing Where to Focus: Event-aware Transformer for Video Grounding ICCV 2023 Language-Free Training for Zero-Shot Video Grounding WACV 2023 Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning CVPR 2023 Normality Guided Multiple Instance Learning for Weakly Supervised Video Anomaly Detection WACV 2023 PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification CVPR 2023 Probabilistic Prompt Learning for Dense Prediction CVPR 2023 Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity CVPR 2023 CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning CLeaR 2022 KNN Local Attention for Image Restoration CVPR 2022 Pin the Memory: Learning To Generalize Semantic Segmentation CVPR 2022 PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation ECCV 2022 Probabilistic Representations for Video Contrastive Learning CVPR 2022 Adaptive Confidence Thresholding for Monocular Depth Estimation ICCV 2021 Bridge To Answer: Structure-Aware Graph Interaction Network for Video Question Answering CVPR 2021 CATs: Cost Aggregation Transformers for Visual Correspondence NeurIPS 2021 Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation AAAI 2021 Deep Low-Contrast Image Enhancement using Structure Tensor Representation AAAI 2021 Learning Canonical 3D Object Representation for Fine-Grained Recognition ICCV 2021 Looking Into Your Speech: Learning Cross-Modal Affinity for Audio-Visual Speech Separation CVPR 2021 Memory-Guided Unsupervised Image-to-Image Translation CVPR 2021 Mining Better Samples for Contrastive Learning of Temporal Correspondence CVPR 2021 Prototype-Guided Saliency Feature Learning for Person Search CVPR 2021 Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation CVPR 2020 Guided Semantic Flow ECCV 2020 Stereoscopic Image Super-Resolution with Stereo Consistent Feature AAAI 2020 SumGraph: Video Summarization via Recursive Graph Modeling ECCV 2020 Context-Aware Emotion Recognition Networks ICCV 2019 Joint Learning of Semantic Alignment and Object Landmark Detection ICCV 2019 LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation CVPR 2019 Semantic Attribute Matching Networks CVPR 2019 PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence ECCV 2018 Recurrent Transformer Networks for Semantic Correspondence NeurIPS 2018 DCTM: Discrete-Continuous Transformation Matching for Semantic Flow ICCV 2017 Deeply Aggregated Alternating Minimization for Image Restoration CVPR 2017 FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence CVPR 2017 DASC: Dense Adaptive Self-Correlation Descriptor for Multi-Modal and Multi-Spectral Correspondence CVPR 2015