論文表記の著者名
Nakamasa Inoue
東京科学大学Computer Vision2022–2026 LIVE
対象論文 15 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
- BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
- PowerCLIP: Powerset Alignment for Contrastive Pre-Training
- Detect by Track: Making Detector-Free Matcher Trackable
- LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension
- AgroBench: Vision-Language Model Benchmark in AgricultureDOI
- AnimalClue: Recognizing Animals by their TracesDOI
- CityNav: A Large-Scale Dataset for Real-World Aerial NavigationDOI
- GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language FieldsDOI
- Referring Expression Comprehension for Small ObjectsDOI
- Formula-Supervised Visual-Geometric Pre-trainingDOI
- Rethinking Image Super Resolution from Training Data PerspectivesDOI
- Visual Atoms: Pre-Training Vision Transformers With Sinusoidal WavesDOI
- Pre-training Vision Transformers with Very Limited Synthesized ImagesDOI
- SegRCDB: Semantic Segmentation via Formula-Driven Supervised LearningDOI
- Replacing Labeled Real-Image Datasets With Auto-Generated ContoursDOI