Detecting Parts for Action Localization

Nicolas Chesneau 1 Grégory Rogez 1 Karteek Alahari 1 Cordelia Schmid 1
1 Thoth - Apprentissage de modèles à partir de données massives
LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
Abstract : In this paper, we propose a new framework for action localization that tracks people in videos and extracts full-body human tubes, i.e., spatio-temporal regions localizing actions, even in the case of occlusions or truncations. This is achieved by training a novel human part detector that scores visible parts while regressing full-body bounding boxes. The core of our method is a convolutional neural network which learns part proposals specific to certain body parts. These are then combined to detect people robustly in each frame. Our tracking algorithm connects the image detections temporally to extract full-body human tubes. We apply our new tube extraction method on the problem of human action localization, on the popular JHMDB dataset, and a very recent challenging dataset DALY (Daily Action Localization in YouTube), showing state-of-the-art results.
Document type :
Conference papers
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01573629
Contributor : Thoth Team <>
Submitted on : Thursday, August 10, 2017 - 10:52:48 AM
Last modification on : Sunday, March 10, 2019 - 3:53:21 PM

File

0159.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01573629, version 1
  • ARXIV : 1707.06005

Collections

Citation

Nicolas Chesneau, Grégory Rogez, Karteek Alahari, Cordelia Schmid. Detecting Parts for Action Localization. BMVC - British Machine Vision Conference, Sep 2017, London, United Kingdom. ⟨hal-01573629⟩

Share

Metrics

Record views

323

Files downloads

231