Naoki Kato

[輪講] Vision Transformer Adapterfor Dense Predictions

[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

[輪講] Transformer Layers as Painters

[論文解説] Domain Aligned CLIP for Few-shot Classification

Leveraging Temporal Joint Depths for Improving 3D Human Pose Estimation in Video

第四回 全日本コンピュータビジョン勉強会 / Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation

ラベルなしデータを用いた Dense Tracking の研究事例 / Learning Dense Tracking from Unlabeled Videos