大学 × Computer Vision
東京科学大学
Computer Vision / 2022–2026 LIVE
掲載論文 46 本
論文一覧
46 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 46 本と一致しています。
2026年
- BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
掲載ID:
cvf:cvpr2026:66757f63fc9d0b8b30c4856a - COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
掲載ID:
cvf:cvpr2026:911e9ac1a05422fbdda961a3 - DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation
掲載ID:
cvf:cvpr2026:b846490dc03634f20a8877be - PowerCLIP: Powerset Alignment for Contrastive Pre-Training
掲載ID:
cvf:cvpr2026:dc6b3420d55a165aa08a1456 - Streaming Video Crime Anticipation with Spatio-Temporal Causal Reasoning
掲載ID:
cvf:cvpr2026:fbf1c3f893b3d303fb00b5fb - Teacher-Guided Routing for Sparse Vision Mixture-of-Experts
掲載ID:
cvf:cvpr2026:2c8c5f33e424bbe5241336c7 - Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
掲載ID:
cvf:cvpr2026:5a6d30b86611be20578dc5be - UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
掲載ID:
cvf:cvpr2026:7bcb9e020a6f7ab1b728d0f9 - BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming
掲載ID:
ecva:eccv2026:05202 - CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels
掲載ID:
ecva:eccv2026:04479 - Detect by Track: Making Detector-Free Matcher Trackable
掲載ID:
ecva:eccv2026:03971 - E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
掲載ID:
ecva:eccv2026:04639 - InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation
掲載ID:
ecva:eccv2026:05889 - LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension
掲載ID:
ecva:eccv2026:05385 - Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion
掲載ID:
ecva:eccv2026:05749 - Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
掲載ID:
ecva:eccv2026:04589 - Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
掲載ID:
ecva:eccv2026:05018
2025年
- Image Referenced Sketch Colorization Based on Animation Creation Workflow
掲載ID:
cvf:cvpr2025:2aa7e20daa4ec22eceec038e - LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model
掲載ID:
doi:10.1109/cvpr52734.2025.00277 - PolarFree: Polarization-based Reflection-Free Imaging
掲載ID:
doi:10.1109/cvpr52734.2025.01017 - AgroBench: Vision-Language Model Benchmark in Agriculture
掲載ID:
doi:10.1109/iccv51701.2025.00716 - AnimalClue: Recognizing Animals by their Traces
掲載ID:
doi:10.1109/iccv51701.2025.01371 - CityNav: A Large-Scale Dataset for Real-World Aerial Navigation
掲載ID:
doi:10.1109/iccv51701.2025.00559 - Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy
掲載ID:
doi:10.1109/iccv51701.2025.01644 - Embodied Navigation with Auxiliary Task of Action Description Prediction
掲載ID:
doi:10.1109/iccv51701.2025.00660 - GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields
掲載ID:
doi:10.1109/iccv51701.2025.00908 - Neural Inverse Rendering for High-Accuracy 3D Measurement of Moving Objects with Fewer Phase-Shifting Patterns
掲載ID:
doi:10.1109/iccv51701.2025.02571 - PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups
掲載ID:
doi:10.1109/iccv51701.2025.00994 - Referring Expression Comprehension for Small Objects
掲載ID:
doi:10.1109/iccv51701.2025.01972
2024年
- Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes
掲載ID:
doi:10.1109/cvpr52733.2024.01974 - VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection
掲載ID:
doi:10.1109/cvpr52733.2024.01643 - COM Kitchens: An Unedited Overhead-view Procedural Videos Dataset a Vision-Language Benchmark
掲載ID:
doi:10.1007/978-3-031-73650-6_8 - Formula-Supervised Visual-Geometric Pre-training
掲載ID:
doi:10.1007/978-3-031-72670-5_4 - OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation
掲載ID:
doi:10.1007/978-3-031-73226-3_5 - Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Composition
掲載ID:
doi:10.1007/978-3-031-72627-9_17 - Rethinking Directional Parameterization in Neural Implicit Surface Reconstruction
掲載ID:
doi:10.1007/978-3-031-72904-1_8 - Rethinking Image Super Resolution from Training Data Perspectives
掲載ID:
doi:10.1007/978-3-031-72643-9_2 - Scaling Backwards: Minimal Synthetic Pre-training?
掲載ID:
doi:10.1007/978-3-031-72633-0_9
2023年
- Few-Shot Learning With Visual Distribution Calibration and Cross-Modal Distribution Alignment
掲載ID:
doi:10.1109/cvpr52729.2023.02245 - Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves
掲載ID:
doi:10.1109/cvpr52729.2023.01782 - EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity
掲載ID:
doi:10.1109/iccv51070.2023.00013 - Pre-training Vision Transformers with Very Limited Synthesized Images
掲載ID:
doi:10.1109/iccv51070.2023.01862 - SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
掲載ID:
doi:10.1109/iccv51070.2023.01835
2022年
- Deep Hyperspectral-Depth Reconstruction Using Single Color-Dot Projection
掲載ID:
doi:10.1109/cvpr52688.2022.01915 - Replacing Labeled Real-Image Datasets With Auto-Generated Contours
掲載ID:
doi:10.1109/cvpr52688.2022.02055 - Implicit Neural Representations for Variable Length Human Motion Generation
掲載ID:
doi:10.1007/978-3-031-19790-1_22
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。