| ONLINE (8/9 Friday) | DAY1(8/12 Monday) | DAY2(8/13 Tuesday) | DAY3(8/14 Wednesday) | |
|---|---|---|---|---|
| 09:00 | Workshop 09:00 - 10:30 | Online Invited TalkAlbert Gu(CMU)09:00 - 10:00 | ||
| 09:40 | Opening09:40 - 10:00 | |||
| 10:00 | Oral 110:00 - 11:00 | Oral 3 10:00 - 11:00 |
Oral 510:00 - 11:00 | |
| 10:30 | Tutorial10:30 - 12:00 | |||
| 11:00 | Keynote 1 Yong Jae Lee(UW-Madison)11:00 ~ 12:00 |
Keynote 2 Stella X. Yu(Univ. of Michigan)11:00 ~ 12:00 |
Keynote 3Ivan Laptev(Inria/MBZUAI)11:00 - 12:00 | |
| 12:00 |
Lunch 12:00 ~ 13:30 | Lunch12:00 ~ 13:30 | Lunch12:00 ~ 13:30 | Lunch12:00 ~ 13:30 |
| 12:30 | ||||
| 13:30 | Tutorial 13:30 - 18:00 | Oral 213:30 - 14:50 | Oral 413:30 - 14:30 | Oral 613:30 - 14:30 |
| 14:30 | Industry 214:30 - 15:30 | Poster / Demo 314:30 - 15:50 | ||
| 14:50 | Industry 114:50 - 15:30 | |||
| 15:30 | Poster / Demo 1 15:30 - 17:10 | Poster / Demo 2 15:30 - 17:10 | ||
| 15:50 | Oral 715:50 - 16:50 | |||
| 16:50 |
Panel Discussion16:50 ~ 17:50 | |||
| 17:10 | Doctoral Colloquium17:10 ~ 18:10 | KCVS General Meeting17:10 ~ 18:10 | ||
| 17:50 | 폐회식17:50 ~ 18:10 |
| Worshop.1 | 9:00 ~ 9:30 | 성공적인 연구자가 되는 길 1 | Michael Ryoo (Stony Brook University) |
| Worshop.2 | 9:30 ~ 10:00 | 성공적인 연구자가 되는 길 2 | 노현우 |
| Worshop.3 | 10:00 ~ 10:30 | 성공적인 연구자가 되는 길 3 | 이문태 (University of Illinois Chicago) |
| Tutorial.1 | 10:30 ~ 12:00 | Prompt Learning via Meta-Regularization | 김현우 (고려대) |
| Tutorial.2 | 13:30 ~ 15:00 | Differentiable Point-based Inverse Rendering | 백승환 (POSTECH) |
| Tutorial.3 | 15:00 ~ 16:30 | CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation | 김승룡 (KAIST) |
| Tutorial.4 | 16:30 ~ 18:00 | Sound Source Localization is All about Cross-Modal Alignment | 정준선 (KAIST) |
| O1.1 | 10:00 ~ 10:20 | Sound Source Localization is All about Cross-Modal Alignment | 정준선 (KAIST) |
| O1.2 | 10:20 ~ 10:40 | Differentiable Display Photometric Stereo | 백승환 (POSTECH) |
| O1.3 | 10:40 ~ 11:00 | Unsupervised Object Localization with Representer Point Selection | 손진희 (GIST) |
| Keynote 1 | 11:00 ~ 12:00 | Learning to Understand Our Multimodal World | Yong Jae Lee (University of Wisconsin-Madison) |
| O2.1 | 13:30 ~ 13:50 | Generative Unlearning for Any Identity | 박경문 (경희대) |
| O2.2 | 13:50 ~ 14:10 | Exploiting Style Latent Flows for Generalizing Video Deepfake Detection | 최종원 (중앙대) |
| O2.3 | 14:10 ~ 14:30 | Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts | 윤상두 (NAVER) |
| O2.4 | 14:30 ~ 14:50 | Exploring Positional Characteristics of Dual-Pixel Data for Camera Autofocus | 최명섭 (SAIT) |
| I1.1 | 14:50 ~ 15:10 | Large-Scale Learning for Conquering Cancer | 유동근 (루닛) |
| I1.2 | 15:10 ~ 15:30 | Camera Sensors: The Eyes of the Fourth Industrial Revolution | 김수훈 (델타엑스) |
| Doctoral Colloquium | 17:10 ~ 18:10 | 김수필(DGIST), 배인환(GIST), 권혁준(KAIST), 김나영(POSTECH), 이민현(KAIST), 민철희(서울대) | |
| Invited Talk | 9:00 ~ 10:00 | Structured State Space Models for Deep Sequence Modeling | Albert Gu (CMU) |
| O2.1 | 10:00 ~ 10:20 | From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation | 윤국진 (KAIST) |
| O2.2 | 10:20 ~ 10:40 | Compositional Video Understanding with Spatiotemporal Structure-based Transformers | 김은솔 (한양대) |
| O2.3 | 10:40 ~ 11:00 | CAST: Cross-Attention in Space and Time for Video Action Recognition | 최진우 (경희대) |
| Keynote 2 | 11:00 ~ 12:00 | Unscripted and Grounded Visual Learning | Stella X. Yu (University of Michigan) |
| O4.1 | 13:30 ~ 13:50 | Compact 3D Gaussian Representation for Radiance Field | 박은병 (성균관대) |
| O4.2 | 13:50 ~ 14:10 | Fully Panoramic Localization | 김영민 (서울대) |
| O4.3 | 14:10 ~ 14:30 | CoPoNeRF: Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs | 김승룡 (KAIST) |
| I2.1 | 14:30 ~ 14:50 | Spatial Perception Technologies for Autonomous Manufacturing | 윤일용 (포스코 DX) |
| I2.2 | 14:50 ~ 15:10 | AI Research at Samsung | 지대현 (삼성전자 SAIT) |
| I2.3 | 15:10 ~ 15:30 | AI Implementation in Manufacturing: Challenges and Solutions | 조한상 (삼성전기) |
| O5.1 | 10:00 ~ 10:20 | On Exact Inversion of DPM-Solvers | 전세영 (서울대) |
| O5.2 | 10:20 ~ 10:40 | Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer | 허재필 (성균관대) |
| O5.3 | 10:40 ~ 11:00 | VMC:One-Shot Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models | 예종철 (KAIST) |
| Keynote 3 | 11:00 ~ 12:00 | From Video Understanding to Embodied Agents | Ivan Laptev (Inria / MBZUAI) |
| O6.1 | 13:30 ~ 13:50 | GALA: Generating Animatable Layered Assets from a Single Scan | 주한별 (서울대) |
| O6.2 | 13:50 ~ 14:10 | HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud | 고종환 (성균관대) |
| O6.3 | 14:10 ~ 14:30 | Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction | 김원준 (건국대) |
| O7.1 | 15:50 ~ 16:10 | Open-Vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models | 김현우 (고려대) |
| O7.2 | 16:10 ~ 16:30 | Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models | 김수현 (KIST) |
| O7.3 | 16:30 ~ 16:50 | RankMixup: Ranking-Based Mixup Training for Network Calibration | 함범섭 (연세대) |
| Panel Discussion | 16:50 ~ 17:50 | 컴퓨터비전 강국으로서 한국, 연구 커뮤니티의 역할과 방향 | |