大学 × Computer Vision
東北大学
Computer Vision / 2022–2026 LIVE
掲載論文 23 本
論文一覧
23 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 23 本と一致しています。
2026年
- COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
掲載ID:
cvf:cvpr2026:911e9ac1a05422fbdda961a3 - Fourier Angle Alignment for Oriented Object Detection in Remote Sensing
掲載ID:
cvf:cvpr2026:2d845d0edd17d2e7402dbfdd - NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks
掲載ID:
cvf:cvpr2026:44bfd61cd2bafeafd4b04fb4 - POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation
掲載ID:
cvf:cvpr2026:2d946dc90276928e8adb2f08 - SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation
掲載ID:
cvf:cvpr2026:5308409aaf881abee9e6cc04 - SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation
掲載ID:
cvf:cvpr2026:5847980b103592a75d48c5c9 - SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition
掲載ID:
cvf:cvpr2026:fe5c8203fc5ce10f3c8963a6 - Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
掲載ID:
cvf:cvpr2026:5a6d30b86611be20578dc5be - 360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method
掲載ID:
ecva:eccv2026:04124 - Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation
掲載ID:
ecva:eccv2026:05270 - CaPCL: Caption-Preserved Continual Learning for Text-to-Image Retrieval
掲載ID:
ecva:eccv2026:05212 - Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging
掲載ID:
ecva:eccv2026:03316 - Improving Adversarial Robustness via Activation Amplification and Attenuation
掲載ID:
ecva:eccv2026:03522 - Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
掲載ID:
ecva:eccv2026:04589
2025年
- VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
掲載ID:
doi:10.1109/cvpr52734.2025.02312 - LayerD: Decomposing Raster Graphic Designs into Layers
掲載ID:
cvf:iccv2025:a2e9d5482a16577a85c853e8 - StreamDiffusion: A Pipeline-level Solution for Real-Time Interactive Generation
掲載ID:
doi:10.1109/iccv51701.2025.01150
2024年
- Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Model
掲載ID:
doi:10.1007/978-3-031-72754-2_6 - Learning Equilibrium Transformation for Gamut Expansion and Color Restoration
掲載ID:
doi:10.1007/978-3-031-73209-6_24 - Scaling Backwards: Minimal Synthetic Pre-training?
掲載ID:
doi:10.1007/978-3-031-72633-0_9
2023年
- Hyperbolic Chamfer Distance for Point Cloud Completion
掲載ID:
doi:10.1109/iccv51070.2023.01342
2022年
- Symmetry-Aware Neural Architecture for Embodied Visual Exploration
掲載ID:
doi:10.1109/cvpr52688.2022.01673 - GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features
掲載ID:
doi:10.1007/978-3-031-20059-5_10
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。