日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

HOI検出arXiv:2104.02867

アフォーダンス転移学習による人-物体インタラクション検出

Affordance Transfer Learning for Human-Object Interaction Detection

シェア:XThreadsFacebookLINEはてブBluesky

人-物体インタラクション表現をアフォーダンスと物体表現に分解し、未知物体へアフォーダンスを転移することで新規物体とのインタラクション検出とアフォーダンス認識を同時に改善する手法を提案した。

著者: Zhi Hou, Baosheng Yu, Yu Qiao, Xiaojiang Peng, Dacheng Tao

分類: cs.CV, cs.AI, cs.RO

原文アブストラクト

Reasoning the human-object interactions (HOI) is essential for deeper scene understanding, while object affordances (or functionalities) are of great importance for human to discover unseen HOIs with novel objects. Inspired by this, we introduce an affordance transfer learning approach to jointly detect HOIs with novel objects and recognize affordances. Specifically, HOI representations can be decoupled into a combination of affordance and object representations, making it possible to compose novel interactions by combining affordance representations and novel object representations from additional images, i.e. transferring the affordance to novel objects. With the proposed affordance transfer learning, the model is also capable of inferring the affordances of novel objects from known affordance representations. The proposed method can thus be used to 1) improve the performance of HOI detection, especially for the HOIs with unseen objects; and 2) infer the affordances of novel objects. Experimental results on two datasets, HICO-DET and HOI-COCO (from V-COCO), demonstrate significant improvements over recent state-of-the-art methods for HOI detection and object affordance detection. Code is available at https://github.com/zhihou7/HOI-CL

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI