A Caltech Library Service

Detecting and Recognizing Human-Object Interactions

Gkioxari, Georgia and Girshick, Ross and Dollár, Piotr and He, Kaiming (2018) Detecting and Recognizing Human-Object Interactions. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE , Piscataway, NJ, pp. 8359-8367. ISBN 978-1-5386-6420-9.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


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.

Item Type:Book Section
Related URLs:
URLURL TypeDescription ItemDiscussion Paper
Record Number:CaltechAUTHORS:20221215-789762000.15
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118375
Deposited By: George Porter
Deposited On:19 Dec 2022 21:43
Last Modified:19 Dec 2022 21:43

Repository Staff Only: item control page