Subjects and Their Objects: Localizing Interactees for a Person-Centric View of Importance

@article{Chen2016SubjectsAT,
  title={Subjects and Their Objects: Localizing Interactees for a Person-Centric View of Importance},
  author={Chao-Yeh Chen and K. Grauman},
  journal={International Journal of Computer Vision},
  year={2016},
  volume={126},
  pages={292-313}
}
  • Chao-Yeh Chen, K. Grauman
  • Published 2016
  • Computer Science
  • International Journal of Computer Vision
  • Understanding images with people often entails understanding their interactions with other objects or people. As such, given a novel image, a vision system ought to infer which other objects/people play an important role in a given person’s activity. However, existing methods are limited to learning action-specific interactions (e.g., how the pose of a tennis player relates to the position of his racquet when serving the ball) for improved recognition, making them unequipped to reason about… CONTINUE READING
    Following Gaze in Video
    • 29
    • PDF
    Grounded Human-Object Interaction Hotspots From Video
    • 12
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 88 REFERENCES
    Modeling mutual context of object and human pose in human-object interaction activities
    • 529
    • Highly Influential
    • PDF
    Predicting the Location of "interactees" in Novel Human-Object Interactions
    • 7
    • PDF
    Microsoft COCO: Common Objects in Context
    • 10,527
    • Highly Influential
    • PDF
    W4: Real-Time Surveillance of People and Their Activities
    • 2,732
    • PDF
    Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition
    • 455
    • Highly Influential
    • PDF
    What is an object?
    • 891
    • Highly Influential
    • PDF
    Weakly Supervised Learning of Interactions between Humans and Objects
    • 199
    • Highly Influential
    • PDF
    Scene Semantics from Long-Term Observation of People
    • 99
    • Highly Influential
    • PDF
    Understanding and predicting importance in images
    • 133
    • Highly Influential
    • PDF