論文表記の著者名
Yoichi Sato
東京大学Computer Vision2022–2026 LIVE
対象論文 19 本
著者名は論文に記載された表記をそのまま使用しており、同一人物の名寄せは行っていません。
印刷日： 全論文
論文上の著者表記・公開時所属による集計です。人物の名寄せ・現在所属・全業績を表すものではありません。
対象論文
論文一覧
- CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
- HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
- Multi-speaker Attention Alignment for Multimodal Social Interaction
- Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
- Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
- Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human ActivitiesDOI
- Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language GuidanceDOI
- Generative Modeling of Shape-Dependent Self-Contact Human PosesDOI
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person PerspectivesDOI
- Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose EstimationDOI
- Masked Video and Body-worn IMU Autoencoder for Egocentric Action RecognitionDOI
- WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal UnderstandingDOI
- DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive RankingDOI
- Structural Multiplane Image: Bridging Neural View Synthesis and 3D ReconstructionDOI
- Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-TrainingDOI
- Ego4D: Around the World in 3,000 Hours of Egocentric VideoDOI
- Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action RecognitionDOI
- CompNVS: Novel View Synthesis with Scene CompletionDOI
- Domain Adaptive Hand Keypoint and Pixel Localization in the WildDOI