Semi-supervised understanding of complex activities from temporal concepts

Abstract : Methods for action recognition have evolved considerably over the past years and can now automatically learn and recognize short term actions with satisfactory accuracy. Nonetheless, the recognition of complex activities-compositions of actions and scene objects-is still an open problem due to the complex temporal and composite structure of this category of events. Existing methods focus either on simple activities or oversimplify the modeling of complex activities by targeting only whole-part relations between its sub-parts (e.g., actions). In this paper, we propose a semi-supervised approach that learns complex activities from the temporal patterns of concept compositions (e.g., " slicing-tomato " before " pouring into-pan "). We demonstrate that our method outperforms prior work in the task of automatic modeling and recognition of complex activities learned out of the interaction of 218 distinct concepts.
Document type :
Conference papers
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-01398958
Contributor : Carlos Fernando Crispim-Junior <>
Submitted on : Tuesday, November 29, 2016 - 2:29:35 PM
Last modification on : Thursday, February 7, 2019 - 3:05:02 PM
Long-term archiving on : Tuesday, March 21, 2017 - 1:58:12 AM

File

crispim_et_al_AVSS16_v2.4_cr_h...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01398958, version 1

Collections

Citation

Carlos Fernando Crispim-Junior, Michal Koperski, Serhan Cosar, Francois Bremond. Semi-supervised understanding of complex activities from temporal concepts. 13th International Conference on Advanced Video and Signal-Based Surveillance, Aug 2016, Colorado Springs, United States. ⟨hal-01398958⟩

Share

Metrics

Record views

321

Files downloads

262