Semantic Scholar Open Access 2017 639 sitasi

Detecting and Recognizing Human-Object Interactions

Georgia Gkioxari Ross B. Girshick Piotr Dollár Kaiming He

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)

G

Georgia Gkioxari

R

Ross B. Girshick

P

Piotr Dollár

K

Kaiming He

Format Sitasi

Gkioxari, G., Girshick, R.B., Dollár, P., He, K. (2017). Detecting and Recognizing Human-Object Interactions. https://doi.org/10.1109/CVPR.2018.00872

Akses Cepat

Lihat di Sumber doi.org/10.1109/CVPR.2018.00872
Informasi Jurnal
Tahun Terbit
2017
Bahasa
en
Total Sitasi
639×
Sumber Database
Semantic Scholar
DOI
10.1109/CVPR.2018.00872
Akses
Open Access ✓