大学 × Computer Vision
慶應義塾大学
Computer Vision / 2022–2026 LIVE
掲載論文 27 本
論文一覧
27 本
このEditionのランキングに掲載している論文です。同じ大学の複数著者による共著は1本にまとめています。
ランキングの対象論文 27 本と一致しています。
2026年
- Geometric-Photometric Event-based 3D Gaussian Ray Tracing
掲載ID:
cvf:cvpr2026:5824530f8ec9669d135ef567 - Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal
掲載ID:
cvf:cvpr2026:287f2a6d2e7301d128757f4e - Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors
掲載ID:
cvf:cvpr2026:f78e2ff6e7b6e50ac4aaa23b - Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
掲載ID:
cvf:cvpr2026:1b6631e19dcefb2b13349a10 - Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
掲載ID:
cvf:cvpr2026:f7052ec4d5dd2781f7d2c111 - ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
掲載ID:
cvf:cvpr2026:3ef18dc86a87544459af2ea5 - ZINA: Multimodal Fine-grained Hallucination Detection and Editing
掲載ID:
cvf:cvpr2026:b58ee75c8089284613e97426 - AiSCREAM: Absolute Target Localization with Language-Conditioned Cross-View Alignment for Autonomous Vehicles
掲載ID:
ecva:eccv2026:04382 - Reference-Free Quality Assessment for Virtual Try-On via Human Feedback
掲載ID:
ecva:eccv2026:05449 - Sound-based Multi-Person 3D Pose Estimation
掲載ID:
ecva:eccv2026:03961
2025年
- AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model
掲載ID:
cvf:iccv2025:68114bd9364042eabd58451c - Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Images
掲載ID:
doi:10.1109/iccv51701.2025.00877 - Simultaneous Motion And Noise Estimation with Event Cameras
掲載ID:
doi:10.1109/iccv51701.2025.00654 - VideoSetDiff: Identifying and Reasoning Similarities and Differences in Similar Videos
掲載ID:
doi:10.1109/iccv51701.2025.01138
2024年
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments
掲載ID:
doi:10.1109/cvpr52733.2024.01947 - EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
掲載ID:
doi:10.1109/cvpr52733.2024.00115 - Polos: Multimodal Metric Learning from Human Feedback for Image Captioning
掲載ID:
doi:10.1109/cvpr52733.2024.01287 - The STVchrono Dataset: Towards Continuous Change Recognition in Time
掲載ID:
doi:10.1109/cvpr52733.2024.01338 - Data Collection-free Masked Video Modeling
掲載ID:
doi:10.1007/978-3-031-73247-8_3 - Layer-Wise Relevance Propagation with Conservation Property for ResNet
掲載ID:
doi:10.1007/978-3-031-72775-7_20 - Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition
掲載ID:
doi:10.1007/978-3-031-73414-4_11 - Rethinking Image Super Resolution from Training Data Perspectives
掲載ID:
doi:10.1007/978-3-031-72643-9_2
2023年
- Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals
掲載ID:
doi:10.1109/cvpr52729.2023.01280
2022年
- Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation
掲載ID:
doi:10.1109/cvpr52688.2022.01115 - BEAT: A Large-Scale Semantic and Emotional Multi-modal Dataset for Conversational Gestures Synthesis
掲載ID:
doi:10.1007/978-3-031-20071-7_36北陸先端科学技術大学院大学 / 慶應義塾大学 / 東京大学
- Secrets of Event-Based Optical Flow
掲載ID:
doi:10.1007/978-3-031-19797-0_36 - UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture
掲載ID:
doi:10.1007/978-3-031-20068-7_1
掲載対象外の論文や未反映の論文は、この一覧には含まれません。