大学 × Computer Vision
東京大学
Computer Vision / 2022–2026 LIVE
掲載論文 210 本
論文一覧
210 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 210 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 - Bridging Facial Understanding and Animation via Language Models
掲載ID:
cvf:cvpr2026:c0ef320e9cf5efcf7a01cd8d - CLIP-like Model as a Foundational Density Ratio Estimator
掲載ID:
cvf:cvpr2026:a73de3ce03b4bdfac4b64845 - CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
掲載ID:
cvf:cvpr2026:7cf9baf30614818691787f94 - ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Senisng
掲載ID:
cvf:cvpr2026:4e3cfcde8333248557400b7b - ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
掲載ID:
cvf:cvpr2026:a532c25128b7887c22bfb430 - Continual Distillation of Teachers from Different Domains
掲載ID:
cvf:cvpr2026:1ae02404b7a122a7fd6bf799 - DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification
掲載ID:
cvf:cvpr2026:f46db2d74f4c984368775834 - Direction-aware 3D Large Multimodal Models
掲載ID:
cvf:cvpr2026:b0b4b2aa2f35041374e8d582 - Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting
掲載ID:
cvf:cvpr2026:906de8a8d0b599ea0197efa1 - DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation
掲載ID:
cvf:cvpr2026:b846490dc03634f20a8877be - FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation
掲載ID:
cvf:cvpr2026:b2d55720c7a083a092db819b - Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3-D Constrained Terrains
掲載ID:
cvf:cvpr2026:a43409552a89a164ea160d73 - GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing
掲載ID:
cvf:cvpr2026:8610e290d50f8146b2d57e33 - Geometric-Photometric Event-based 3D Gaussian Ray Tracing
掲載ID:
cvf:cvpr2026:5824530f8ec9669d135ef567 - HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
掲載ID:
cvf:cvpr2026:8f05920bd7a9ad0ea3a8a23b - MD2E: Modeling Depth-to-Edge Cues for Monocular Metric Depth Estimation
掲載ID:
cvf:cvpr2026:ee178a6ec997a1f3a3d037e3 - MERIT: Multi-domain Efficient RAW Image Translation
掲載ID:
cvf:cvpr2026:7c2ad709685d89002b282018 - MM-OVSeg: Multimodal Optical-SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing
掲載ID:
cvf:cvpr2026:745ce721cc19d098f3e5c087 - Mirai: Autoregressive Visual Generation Needs Foresight
掲載ID:
cvf:cvpr2026:973a0abd1992f6a4cedf7993 - Motion-Aware Animatable Gaussian Avatars Deblurring
掲載ID:
cvf:cvpr2026:2cf69c54dadf7d847c3b0774 - Multi-speaker Attention Alignment for Multimodal Social Interaction
掲載ID:
cvf:cvpr2026:c2f72ab53556cca6033ab6cc - MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation
掲載ID:
cvf:cvpr2026:30095cdc734b98ce703d08f2 - Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction
掲載ID:
cvf:cvpr2026:ecc34a1bba1df45255bcabe5 - Occluded Human Body Capture with Frequency Domain Denoising Prior
掲載ID:
cvf:cvpr2026:8c136f66eba9ff420672ae14 - RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos
掲載ID:
cvf:cvpr2026:b60d35920c5d0f8512b9488f - RefTon: Reference person shot assist virtual Try-on
掲載ID:
cvf:cvpr2026:48dd2d00180c63f678bbd8d1 - Region-Wise Correspondence Prediction between Manga Line Art Images
掲載ID:
cvf:cvpr2026:78fd32da19042377e6921c93 - TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion
掲載ID:
cvf:cvpr2026:20c44e125b7f325b594d5f12 - Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
掲載ID:
cvf:cvpr2026:5a6d30b86611be20578dc5be - Towards High-resolution and Disentangled Reference-based Sketch Colorization
掲載ID:
cvf:cvpr2026:e511b00959638f1e92456fa1 - Towards Robust Sequential Decomposition for Complex Image Editing
掲載ID:
cvf:cvpr2026:881c2d0d503c39b3b0597c59 - Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities
掲載ID:
cvf:cvpr2026:3b5c8f5550b3a497de9c21a2 - UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
掲載ID:
cvf:cvpr2026:7bcb9e020a6f7ab1b728d0f9 - Unified Vector Floorplan Generation via Markup Representation
掲載ID:
cvf:cvpr2026:a4c7da6a22345df43f59a482 - 360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
掲載ID:
ecva:eccv2026:05213 - Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
掲載ID:
ecva:eccv2026:04223 - Benchmarking MLLMs on Mistake Recognition and Explanation in Single-Step Components of Cooking
掲載ID:
ecva:eccv2026:05187 - Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation
掲載ID:
ecva:eccv2026:05270 - Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation
掲載ID:
ecva:eccv2026:03714 - Constrained Rotation Optimization: Revisiting Crop-Based Gaze Estimation
掲載ID:
ecva:eccv2026:04912 - Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging
掲載ID:
ecva:eccv2026:03316 - E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
掲載ID:
ecva:eccv2026:04639 - FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
掲載ID:
ecva:eccv2026:03888 - FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement
掲載ID:
ecva:eccv2026:03622 - Gripper-aware Vision Language Action Models
掲載ID:
ecva:eccv2026:04272 - HERO: Heterogeneous Evidential Robust Object-Level Collaborative Perception
掲載ID:
ecva:eccv2026:05572 - Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation
掲載ID:
ecva:eccv2026:04928 - 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 - NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment
掲載ID:
ecva:eccv2026:03859 - Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users
掲載ID:
ecva:eccv2026:03649 - Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
掲載ID:
ecva:eccv2026:04589 - Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations
掲載ID:
ecva:eccv2026:03885 - StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
掲載ID:
ecva:eccv2026:03204 - Surprise Forcing: What to Remember, When to Skip in Long Video Generation
掲載ID:
ecva:eccv2026:03534 - Synesthesia via Direct Latent Augmentation: Bypassing the Decode-Encode Loop for Cross-Modal Distillation
掲載ID:
ecva:eccv2026:03566 - Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
掲載ID:
ecva:eccv2026:05696
2025年
- A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains
掲載ID:
doi:10.1109/cvpr52734.2025.00948 - Associative Transformer
掲載ID:
doi:10.1109/cvpr52734.2025.00426 - EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark
掲載ID:
doi:10.1109/cvpr52734.2025.01245 - EventPSR: Surface Normal and Reflectance Estimation from Photometric Stereo Using an Event Camera
掲載ID:
doi:10.1109/cvpr52734.2025.01067 - Frequency Dynamic Convolution for Dense Image Prediction
掲載ID:
doi:10.1109/cvpr52734.2025.02809 - Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities
掲載ID:
doi:10.1109/cvpr52734.2025.00778 - Image Referenced Sketch Colorization Based on Animation Creation Workflow
掲載ID:
cvf:cvpr2025:2aa7e20daa4ec22eceec038e - InsTaG: Learning Personalized 3D Talking Head from Few-Second Video
掲載ID:
doi:10.1109/cvpr52734.2025.00999 - Instruction-based Image Manipulation by Watching How Things Move
掲載ID:
doi:10.1109/cvpr52734.2025.00258 - LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table
掲載ID:
cvf:cvpr2025:dff7e71dbe01868b3ea0afa8 - Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment
掲載ID:
doi:10.1109/cvpr52734.2025.02465 - MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
掲載ID:
doi:10.1109/cvpr52734.2025.00072 - MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
掲載ID:
doi:10.1109/cvpr52734.2025.02129 - Neural Hierarchical Decomposition for Single Image Plant Modeling
掲載ID:
doi:10.1109/cvpr52734.2025.00077 - Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition
掲載ID:
doi:10.1109/iccv51701.2025.00970 - CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
掲載ID:
doi:10.1109/iccv51701.2025.00139 - CityNav: A Large-Scale Dataset for Real-World Aerial Navigation
掲載ID:
doi:10.1109/iccv51701.2025.00559 - Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance
掲載ID:
doi:10.1109/iccv51701.2025.02526 - Frequency-Dynamic Attention Modulation For Dense Prediction
掲載ID:
doi:10.1109/iccv51701.2025.02100 - GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting
掲載ID:
doi:10.1109/iccv51701.2025.02691 - Generative Modeling of Shape-Dependent Self-Contact Human Poses
掲載ID:
doi:10.1109/iccv51701.2025.00515 - GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields
掲載ID:
doi:10.1109/iccv51701.2025.00908 - GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling
掲載ID:
doi:10.1109/iccv51701.2025.01017 - MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration
掲載ID:
doi:10.1109/iccv51701.2025.01209 - MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
掲載ID:
doi:10.1109/iccv51701.2025.01305 - NeRF Is a Valuable Assistant for 3D Gaussian Splatting
掲載ID:
doi:10.1109/iccv51701.2025.02434 - Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution
掲載ID:
doi:10.1109/iccv51701.2025.01313 - PUMPS: Skeleton-Agnostic Point-based Universal Motion Pre-Training for Synthesis in Human Motion Tasks
掲載ID:
doi:10.1109/iccv51701.2025.01345 - Polarimetric Neural Field via Unified Complex-Valued Wave Representation
掲載ID:
doi:10.1109/iccv51701.2025.02380 - Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation
掲載ID:
doi:10.1109/iccv51701.2025.00403 - Sequential Gaussian Avatars with Hierarchical Motion Context
掲載ID:
doi:10.1109/iccv51701.2025.01262 - Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars
掲載ID:
doi:10.1109/iccv51701.2025.01323 - Tree-NeRV: Efficient Non-Uniform Sampling for Neural Video Representation via Tree-Structured Feature Grids
掲載ID:
cvf:iccv2025:727663173eda37a6c0fb648f - Video Motion Graphs
掲載ID:
doi:10.1109/iccv51701.2025.01274 - You Share Beliefs, I Adapt: Progressive Heterogeneous Collaborative Perception
掲載ID:
doi:10.1109/iccv51701.2025.02555
2024年
- DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
掲載ID:
doi:10.1109/cvpr52733.2024.01963 - EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
掲載ID:
doi:10.1109/cvpr52733.2024.00115 - EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension
掲載ID:
doi:10.1109/cvpr52733.2024.01303 - Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
掲載ID:
doi:10.1109/cvpr52733.2024.01834 - Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes
掲載ID:
doi:10.1109/cvpr52733.2024.01974 - EventPS: Real-Time Photometric Stereo Using an Event Camera
掲載ID:
doi:10.1109/cvpr52733.2024.00917 - Face2Diffusion for Fast and Editable Face Personalization
掲載ID:
doi:10.1109/cvpr52733.2024.00654 - Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection
掲載ID:
doi:10.1109/cvpr52733.2024.02333 - Frequency-Adaptive Dilated Convolution for Semantic Segmentation
掲載ID:
doi:10.1109/cvpr52733.2024.00328 - HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses
掲載ID:
doi:10.1109/cvpr52733.2024.00145 - IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation
掲載ID:
doi:10.1109/cvpr52733.2024.00613 - Improving Plasticity in Online Continual Learning via Collaborative Learning
掲載ID:
doi:10.1109/cvpr52733.2024.02214 - Motion Blur Decomposition with Cross-shutter Guidance
掲載ID:
cvf:cvpr2024:4af684ef5333b72825cd6171 - Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution
掲載ID:
doi:10.1109/cvpr52733.2024.02412 - PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
掲載ID:
doi:10.1109/cvpr52733.2024.00825 - Retrieval-Augmented Egocentric Video Captioning
掲載ID:
doi:10.1109/cvpr52733.2024.01284 - Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation
掲載ID:
doi:10.1109/cvpr52733.2024.00015 - Robust Synthetic-to-Real Transfer for Stereo Matching
掲載ID:
doi:10.1109/cvpr52733.2024.01914 - Rolling Shutter Correction with Intermediate Distortion Flow Estimation
掲載ID:
doi:10.1109/cvpr52733.2024.02394 - SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction
掲載ID:
doi:10.1109/cvpr52733.2024.00449 - Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion
掲載ID:
doi:10.1109/cvpr52733.2024.00682 - Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
掲載ID:
doi:10.1109/cvpr52733.2024.00071 - "NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation"
掲載ID:
doi:10.1007/978-3-031-72655-2_1 - "UniINR: Event-guided Unified Rolling Shutter Correction, Deblurring, and Interpolation"
掲載ID:
doi:10.1007/978-3-031-72673-6_1 - A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis
掲載ID:
doi:10.1007/978-3-031-73016-0_23 - ActionVOS: Actions as Prompts for Video Object Segmentation
掲載ID:
doi:10.1007/978-3-031-72684-2_13 - CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model
掲載ID:
doi:10.1007/978-3-031-73661-2_11奈良先端科学技術大学院大学 / 東京大学 / 早稲田大学
- CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization
掲載ID:
doi:10.1007/978-3-031-73232-4_19 - Direct Distillation between Different Domains
掲載ID:
doi:10.1007/978-3-031-72989-8_9 - Domain Generalization of 3D Object Detection by Density-Resampling
掲載ID:
doi:10.1007/978-3-031-73039-9_26 - Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning
掲載ID:
doi:10.1007/978-3-031-72943-0_25 - Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
掲載ID:
doi:10.1007/978-3-031-73661-2_8 - G2fR: Frequency Regularization in Grid-based Feature Encoding Neural Radiance Fields
掲載ID:
doi:10.1007/978-3-031-72670-5_11 - IRGen: Generative Modeling for Image Retrieval
掲載ID:
doi:10.1007/978-3-031-72633-0_2 - KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter
掲載ID:
doi:10.1007/978-3-031-72995-9_1 - LayoutFlow: Flow Matching for Layout Generation
掲載ID:
doi:10.1007/978-3-031-72764-1_4 - LoA-Trans: Enhancing Visual Grounding by Location-Aware Transformers
掲載ID:
doi:10.1007/978-3-031-72667-5_23 - MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model
掲載ID:
doi:10.1007/978-3-031-72655-2_7 - Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition
掲載ID:
doi:10.1007/978-3-031-72649-1_18 - Object-Aware NIR-to-Visible Translation
掲載ID:
doi:10.1007/978-3-031-73337-6_6 - Open-set Domain Adaptation via Joint Error based Multi-class Positive and Unlabeled Learning
掲載ID:
doi:10.1007/978-3-031-73464-9_7 - PairingNet: A Learning-based Pair-searching and -matching Network for Image Fragments
掲載ID:
doi:10.1007/978-3-031-73202-7_14 - PetFace: A Large-Scale Dataset and Benchmark for Animal Identification
掲載ID:
doi:10.1007/978-3-031-72649-1_2 - RAW-Adapter: Adapting Pretrained Visual Model to Camera RAW Images
掲載ID:
doi:10.1007/978-3-031-73235-5_3 - RPBG: Towards Robust Neural Point-based Graphics in the Wild
掲載ID:
doi:10.1007/978-3-031-72633-0_22 - RS-NeRF: Neural Radiance Fields from Rolling Shutter Images
掲載ID:
doi:10.1007/978-3-031-72952-2_10 - SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning
掲載ID:
doi:10.1007/978-3-031-72983-6_13 - SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
掲載ID:
doi:10.1007/978-3-031-72751-1_10 - TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting
掲載ID:
doi:10.1007/978-3-031-72684-2_8 - Taming Lookup Tables for Efficient Image Retouching
掲載ID:
doi:10.1007/978-3-031-73636-0_9 - The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization
掲載ID:
doi:10.1007/978-3-031-72904-1_6 - WHAC: World-grounded Humans and Cameras
掲載ID:
doi:10.1007/978-3-031-72754-2_2 - WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding
掲載ID:
doi:10.1007/978-3-031-73116-7_1 - Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence
掲載ID:
doi:10.1007/978-3-031-72967-6_27
2023年
- A-Cap: Anticipation Captioning With Commonsense Knowledge
掲載ID:
doi:10.1109/cvpr52729.2023.01042 - AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
掲載ID:
cvf:cvpr2023:8e9e68eabc0a39888dc34814 - Blur Interpolation Transformer for Real-World Motion From Blur
掲載ID:
doi:10.1109/cvpr52729.2023.00553 - DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive Ranking
掲載ID:
doi:10.1109/cvpr52729.2023.02215 - Evading DeepFake Detectors via Adversarial Statistical Consistency
掲載ID:
doi:10.1109/cvpr52729.2023.01181 - High-Fidelity Event-Radiance Recovery via Transient Event Frequency
掲載ID:
doi:10.1109/cvpr52729.2023.01975 - Learning Event Guided High Dynamic Range Video Reconstruction
掲載ID:
doi:10.1109/cvpr52729.2023.01338 - OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer
掲載ID:
doi:10.1109/cvpr52729.2023.01276 - PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations
掲載ID:
doi:10.1109/cvpr52729.2023.00573 - Polarized Color Image Denoising
掲載ID:
doi:10.1109/cvpr52729.2023.00952 - Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction
掲載ID:
doi:10.1109/cvpr52729.2023.01603 - Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark
掲載ID:
doi:10.1109/cvpr52729.2023.01343 - Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training
掲載ID:
doi:10.1109/cvpr52729.2023.01813 - Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color
掲載ID:
doi:10.1109/iccv51070.2023.00452 - BlendFace: Re-designing Identity Encoders for Face-Swapping
掲載ID:
doi:10.1109/iccv51070.2023.00702 - Distribution Shift Matters for Knowledge Distillation with Webly Collected Images
掲載ID:
doi:10.1109/iccv51070.2023.01602 - Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
掲載ID:
doi:10.1109/iccv51070.2023.00696 - MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
掲載ID:
doi:10.1109/iccv51070.2023.02062 - Multi-Label Knowledge Distillation
掲載ID:
doi:10.1109/iccv51070.2023.01584 - NIR-assisted Video Enhancement via Unpaired 24-hour Data
掲載ID:
doi:10.1109/iccv51070.2023.00989 - Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer
掲載ID:
doi:10.1109/iccv51070.2023.01104 - NeRFrac: Neural Radiance Fields through Refractive Surface
掲載ID:
doi:10.1109/iccv51070.2023.01687 - Partition-And-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts
掲載ID:
doi:10.1109/iccv51070.2023.00454 - Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation
掲載ID:
cvf:iccv2023:845b4d40ea36525ac412c1cd - Semantic Information in Contrastive Learning
掲載ID:
doi:10.1109/iccv51070.2023.00523 - SimMatchV2: Semi-Supervised Learning with Graph Consistency
掲載ID:
doi:10.1109/iccv51070.2023.01506 - Single Image Deblurring with Row-dependent Blur Magnitude
掲載ID:
doi:10.1109/iccv51070.2023.01127 - Towards Robust Model Watermark via Reducing Parametric Vulnerability
掲載ID:
doi:10.1109/iccv51070.2023.00438
2022年
- Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding
掲載ID:
doi:10.1109/cvpr52688.2022.01835 - Detecting Deepfakes With Self-Blended Images
掲載ID:
doi:10.1109/cvpr52688.2022.01816 - ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework
掲載ID:
doi:10.1109/cvpr52688.2022.00660 - Ego4D: Around the World in 3,000 Hours of Egocentric Video
掲載ID:
doi:10.1109/cvpr52688.2022.01842 - GazeOnce: Real-Time Multi-Person Gaze Estimation
掲載ID:
doi:10.1109/cvpr52688.2022.00416 - Instance-Dependent Label-Noise Learning With Manifold-Regularized Transition Matrix Estimation
掲載ID:
cvf:cvpr2022:f8af14293f6113134a99b639 - Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition
掲載ID:
doi:10.1109/cvpr52688.2022.01431 - Learnable Lookup Table for Neural Network Quantization
掲載ID:
doi:10.1109/cvpr52688.2022.01210 - Learning Adaptive Warping for Real-World Rolling Shutter Correction
掲載ID:
doi:10.1109/cvpr52688.2022.01726 - Learning Where To Learn in Cross-View Self-Supervised Learning
掲載ID:
doi:10.1109/cvpr52688.2022.01405 - Lepard: Learning Partial Point Cloud Matching in Rigid and Deformable Scenes
掲載ID:
doi:10.1109/cvpr52688.2022.00547 - NOC-REK: Novel Object Captioning With Retrieved Vocabulary From External Knowledge
掲載ID:
doi:10.1109/cvpr52688.2022.01747 - Neural Global Shutter: Learn To Restore Video From a Rolling Shutter Camera With Global Reset Feature
掲載ID:
doi:10.1109/cvpr52688.2022.01727 - OSSGAN: Open-Set Semi-Supervised Image Generation
掲載ID:
doi:10.1109/cvpr52688.2022.01090 - Optimal LED Spectral Multiplexing for NIR2RGB Translation
掲載ID:
doi:10.1109/cvpr52688.2022.01232 - Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective
掲載ID:
doi:10.1109/cvpr52688.2022.01266 - SimMatch: Semi-Supervised Learning With Similarity Matching
掲載ID:
doi:10.1109/cvpr52688.2022.01407 - Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis
掲載ID:
doi:10.1109/cvpr52688.2022.01542 - Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects
掲載ID:
doi:10.1109/cvpr52688.2022.00366 - Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
掲載ID:
doi:10.1007/978-3-031-19800-7_35 - 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
- Bringing Rolling Shutter Images Alive with Dual Reversed Distortion
掲載ID:
doi:10.1007/978-3-031-20071-7_14 - COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
掲載ID:
doi:10.1007/978-3-031-19815-1_16 - CompNVS: Novel View Synthesis with Scene Completion
掲載ID:
doi:10.1007/978-3-031-19769-7_26 - Compound Prototype Matching for Few-Shot Action Recognition
掲載ID:
doi:10.1007/978-3-031-19772-7_21 - Deforming Radiance Fields with Cages
掲載ID:
doi:10.1007/978-3-031-19827-4_10 - Domain Adaptive Hand Keypoint and Pixel Localization in the Wild
掲載ID:
doi:10.1007/978-3-031-20077-9_5 - Efficient Video Deblurring Guided by Motion Magnitude
掲載ID:
doi:10.1007/978-3-031-19800-7_24 - Exploring Resolution and Degradation Clues As Self-Supervised Signal for Low Quality Object Detection
掲載ID:
doi:10.1007/978-3-031-20077-9_28 - Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution
掲載ID:
doi:10.1007/978-3-031-19800-7_1 - Learning Self-Prior for Mesh Denoising Using Dual Graph Convolutional Networks
掲載ID:
doi:10.1007/978-3-031-20062-5_21 - Spectrum-Aware and Transferable Architecture Search for Hyperspectral Image Restoration
掲載ID:
doi:10.1007/978-3-031-19800-7_2 - Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations
掲載ID:
doi:10.1007/978-3-031-19790-1_36 - Unsupervised Pose-Aware Part Decomposition for Man-Made Articulated Objects
掲載ID:
doi:10.1007/978-3-031-20062-5_32 - Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification
掲載ID:
doi:10.1007/978-3-031-20053-3_4
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。