Joint learning of object and action detectors

Vicky Kalogeiton 1, 2 Philippe Weinzaepfel 3 Vittorio Ferrari 2 Cordelia Schmid 1
1 Thoth - Apprentissage de modèles à partir de données massives
LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
2 CALVIN research group [Edinburgh]
IPAB - Institute of Perception, Action and Behaviour
Abstract : While most existing approaches for detection in videos focus on objects or human actions separately, we aim at jointly detecting objects performing actions, such as cat eating or dog jumping. We introduce an end-to-end multitask objective that jointly learns object-action relationships. We compare it with different training objectives, validate its effectiveness for detecting objects-actions in videos, and show that both tasks of object and action detection benefit from this joint learning. Moreover, the proposed architecture can be used for zero-shot learning of actions: our multitask objective leverages the commonalities of an action performed by different objects, e.g. dog and cat jumping , enabling to detect actions of an object without training with these object-actions pairs. In experiments on the A2D dataset [50], we obtain state-of-the-art results on segmentation of object-action pairs. We finally apply our multitask architecture to detect visual relationships between objects in images of the VRD dataset [24].
Document type :
Conference papers
Complete list of metadatas

Cited literature [50 references]  Display  Hide  Download


https://hal.inria.fr/hal-01575804
Contributor : Thoth Team <>
Submitted on : Monday, August 21, 2017 - 4:56:10 PM
Last modification on : Friday, July 27, 2018 - 11:35:37 AM

Files

main.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid. Joint learning of object and action detectors. ICCV - IEEE International Conference on Computer Vision, Oct 2017, Venice, Italy. pp.2001-2010, ⟨10.1109/ICCV.2017.219⟩. ⟨hal-01575804⟩

Share

Metrics

Record views

1034

Files downloads

2612