Detecting and Recognizing Human-Object Interactions
Abstrak
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.
Topik & Kata Kunci
Penulis (4)
Georgia Gkioxari
Ross B. Girshick
Piotr Dollár
Kaiming He
Akses Cepat
- Tahun Terbit
- 2017
- Bahasa
- en
- Total Sitasi
- 639×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1109/CVPR.2018.00872
- Akses
- Open Access ✓