Modeling Spatio-Temporal Human Track Structure for Action Localization

Guilhem Chéron 1, 2 Anton Osokin 1, 3 Ivan Laptev 1 Cordelia Schmid 2
1 WILLOW - Models of visual object recognition and scene understanding
Inria de Paris, DI-ENS - Département d'informatique de l'École normale supérieure
2 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to model the temporal structure of actions on the level of person tracks. Our model is trained to simultaneously recognize and localize action classes in time and is based on two layer gated recurrent units (GRU) applied separately to two streams, i.e. appearance and optical flow streams. When used together with state-of-the-art person detection and tracking, our model is shown to improve substantially spatio-temporal action localization in videos. The gain is shown to be mainly due to improved temporal localization. We evaluate our method on two recent datasets for spatio-temporal action localization, UCF101-24 and DALY, demonstrating a significant improvement of the state of the art.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-01979583
Contributor : Guilhem Chéron <>
Submitted on : Sunday, January 13, 2019 - 2:36:01 PM
Last modification on : Wednesday, January 30, 2019 - 11:07:44 AM

Links full text

Identifiers

  • HAL Id : hal-01979583, version 1
  • ARXIV : 1806.11008

Collections

Citation

Guilhem Chéron, Anton Osokin, Ivan Laptev, Cordelia Schmid. Modeling Spatio-Temporal Human Track Structure for Action Localization. 2019. ⟨hal-01979583⟩

Share

Metrics

Record views

165