Action Tubelet Detector for Spatio-Temporal Action Localization

Vicky Kalogeiton 1, 2 Philippe Weinzaepfel 3 Vittorio Ferrari 2 Cordelia Schmid 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
2 CALVIN research group [Edinburgh]
IPAB - Institute of Perception, Action and Behaviour
Abstract : Current state-of-the-art approaches for spatio-temporal action detection rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating at the frame level. We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, ie., sequences of bounding boxes with associated scores. The same way state-of-the-art object detectors rely on anchor boxes, our ACT-detector is based on anchor cuboids. We build upon the state-of-the-art SSD framework. Convolutional features are extracted for each frame, while scores and regressions are based on the temporal stacking of these features, thus exploiting information from a sequence. Our experimental results show that leveraging sequences of frames significantly improves detection performance over using individual frames. The gain of our tubelet detector can be explained by both more relevant scores and more precise localization. Our ACT-detector outperforms the state of the art methods for frame-mAP and video-mAP on the J-HMDB and UCF-101 datasets, in particular at high overlap thresholds.
Type de document :
Communication dans un congrès
ICCV - IEEE International Conference on Computer Vision, Oct 2017, Venice, Italy
Liste complète des métadonnées

Littérature citée [37 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-01519812
Contributeur : Thoth Team <>
Soumis le : lundi 21 août 2017 - 16:46:08
Dernière modification le : jeudi 26 octobre 2017 - 16:34:02

Fichiers

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01519812, version 2
  • ARXIV : 1705.01861

Collections

Citation

Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid. Action Tubelet Detector for Spatio-Temporal Action Localization. ICCV - IEEE International Conference on Computer Vision, Oct 2017, Venice, Italy. 〈hal-01519812v2〉

Partager

Métriques

Consultations de
la notice

253

Téléchargements du document

290