skip to main content
Idioma:

Detecting and Recognizing Human-Object Interactions

Gkioxari, Georgia ; Girshick, Ross ; Dollar, Piotr ; He, Kaiming

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, p.8359-8367

IEEE

Texto completo disponível

Citações Citado por
  • Título:
    Detecting and Recognizing Human-Object Interactions
  • Autor: Gkioxari, Georgia ; Girshick, Ross ; Dollar, Piotr ; He, Kaiming
  • Assuntos: Feature extraction ; Image recognition ; Object detection ; Predictive models ; Target recognition ; Task analysis ; Visualization
  • É parte de: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, p.8359-8367
  • Descrição: To understand the visual world, a machine must not only recognize individual object instances but also how they interact. Humans are often at the center of such interactions and detecting human-object interactions is an important practical and scientific problem. In this paper, we address the task of detecting (human, verb, object) triplets in challenging everyday photos. We propose a novel model that is driven by a human-centric approach. Our hypothesis is that the appearance of a person - their pose, clothing, action - is a powerful cue for localizing the objects they are interacting with. To exploit this cue, our model learns to predict an action-specific density over target object locations based on the appearance of a detected person. Our model also jointly learns to detect people and objects, and by fusing these predictions it efficiently infers interaction triplets in a clean, jointly trained end-to-end system we call InteractNet. We validate our approach on the recently introduced Verbs in COCO (V-COCO) and HICO-DET datasets, where we show quantitatively compelling results.
  • Editor: IEEE
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.