2023-06 | PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification | Kim, Minsu; Kim, Seungryong; Park, Jungin; Park, Seongheon; Sohn, Kwanghoon |
2023-06 | Probabilistic Prompt Learning for Dense Prediction | Kwon, Hyeongjun; Song, Taeyong; Jeong, Somi; Kim, Jin; Jang, Jinhyun; Sohn, Kwanghoon |
2023-06 | Unsupervised Deep Asymmetric Stereo Matching with Spatially-Adaptive Self-Similarity | Song, Taeyong; Kim, Sunok; Sohn, Kwanghoon |
2023-06 | Dual-path Adaptation from Image to Video Transformers | Park, Jungin; Lee, Jiyoung; Sohn, Kwanghoon |
2023-01 | Normality Guided Multiple Instance Learning for Weakly Supervised Video Anomaly Detection | Park, Seongheon; Kim, Hanjae; Kim, Minsu; Kim, Dahye; Sohn, Kwanghoon |
2023-01 | Language-free Training for Zero-shot Video Grounding | Kim, Dahye; Park, Jungin; Lee, Jiyoung; Park, Seongheon; Sohn, Kwanghoon |
2023-10 | Face Photo-Sketch Synthesis Via Domain-Invariant Feature Embedding | Choi, Yeji; Sohn, Kwanghoon; Kim, Ig-Jae |
2023-10 | Knowing Where to Focus: Event-aware Transformer for Video Grounding | Jang, Jinhyun; Park, Jungin; Kim, Jin; Kwon, Hyeongjun; Sohn, Kwanghoon |
2023-10 | Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning | Kim, Hanjae; Lee, Jiyoung; Park, Seongheon; Sohn, Kwanghoon |