ENHANCING TEMPORAL SEGMENTATION BY NONLOCAL SELF-SIMILARITY

Abstract : Temporal segmentation of untrimmed videos and photo-streams is currently an active area of research in computer vision and image processing. This paper proposes a new approach to improve the temporal segmentation of photo-streams. The method consists in enhancing image representations by encoding long-range temporal dependencies. Our key contribution is to take advantage of the temporal station-arity assumption of photostreams for modeling each frame by its nonlocal self-similarity function. The proposed approach is put to test on the EDUB-Seg dataset, a standard benchmark for egocentric photostream temporal segmentation. Starting from seven different (CNN based) image features, the method yields consistent improvements in event segmentation quality , leading to an average increase of F-measure of 3.71% with respect to the state of the art.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02346583
Contributor : Herwig Wendt <>
Submitted on : Thursday, November 7, 2019 - 3:30:09 PM
Last modification on : Wednesday, November 13, 2019 - 2:59:54 PM

Identifiers

  • HAL Id : hal-02346583, version 1

Citation

Mariella Dimiccoli, Herwig Wendt. ENHANCING TEMPORAL SEGMENTATION BY NONLOCAL SELF-SIMILARITY. IEEE International Conference on Image Processing (ICIP), Sep 2019, Taipei, Taiwan. ⟨hal-02346583⟩

Share

Metrics

Record views

20

Files downloads

13