Video-based Human-Object Interaction Detection from Tubelet Tokens Danyang Tu1, Wei Sun

Nov-15-2025, 12:24:06 GMT–Neural Information Processing Systems

HOIs from videos, a more challenging problem built on spatiotemporal semantic representations.

detection, machine learning, natural language, (16 more...)

Neural Information Processing Systems

Nov-15-2025, 12:24:06 GMT

Conferences PDF

Country:
- Asia
  - China > Shanghai
    - Shanghai (0.05)
  - India > Karnataka
    - Bengaluru (0.04)

Genre:
- Research Report (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks (0.94)
    - Statistical Learning (0.68)
  - Natural Language (1.00)
  - Representation & Reasoning (0.88)
  - Vision (1.00)