Does color influence eye movements while exploring videos?

Autor: Shahrbanoo Hamel, Dominique Houzet, Denis Pellerin, Nathalie Guyader

Publikováno v: Journal of Eye Movement Research, Vol 8, Iss 1 (2015)

Although visual attention studies consider color as one of the most important features in guiding visual attention, few studies have investigated how color influences eye movements while viewing natural scenes without any particular task. To better u

Externí odkaz: https://doaj.org/article/5928e142654149b6ae9f781fe82eb8f5

Influence of number, location and size of faces on gaze in video

Autor: Anis Rahman, Denis Pellerin, Dominique Houzet

Publikováno v: Journal of Eye Movement Research, Vol 7, Iss 2 (2014)

Many studies have reported the preference for faces and influence of faces on gaze, most of them in static images and a few in videos. In this paper, we study the influence of faces in complex free-viewing videos, with respect to the effects of numbe

Externí odkaz: https://doaj.org/article/3e44730d3e0f432394d2b80730bacc0b

Human Shape-Motion Analysis In Athletics Videos for Coarse To Fine Action/Activity Recognition Using Transferable Belief Model

Autor: Emmanuel Ramasso, Costas Panagiotakis, Michèle Rombaut, Denis Pellerin, Georgios Tziritas

Publikováno v: ELCVIA Electronic Letters on Computer Vision and Image Analysis, Vol 7, Iss 4 (2009)

We present an automatic human shape-motion analysis method based on a fusion architecture for human action and activity recognition in athletic videos. Robust shape and motion features are extracted from human detection and tracking. The features are

Externí odkaz: https://doaj.org/article/2525847ef66348cb8f89b4c7d923a3c7

Coupled Ensembles of Neural Networks

Autor: Georges Quénot, Anuvabh Dutt, Denis Pellerin

Publikováno v: Neurocomputing
Neurocomputing, Elsevier, 2020, 396, pp.346-357. ⟨10.1016/j.neucom.2018.10.092⟩
HAL
ICLR (Workshop)
ICLR 2018-6th International Conference on Learning Representations-Workshop Track
ICLR 2018-6th International Conference on Learning Representations-Workshop Track, Apr 2018, Vancouver, Canada
CBMI 2018-International Conference on Content-Based Multimedia Indexing
CBMI 2018-International Conference on Content-Based Multimedia Indexing, Sep 2018, La Rochelle, France

We investigate in this paper the architecture of deep convolutional networks. Building on existing state of the art models, we propose a reconfiguration of the model parameters into several parallel branches at the global network level, with each bra

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6e8e0143a9ff32a53f712beb2f4643d
https://hal.archives-ouvertes.fr/hal-02088253

Learned features versus engineered features for multimedia indexing

Autor: Georges Quénot, Efrain-Leonardo Gutierrez-Gomez, Bahjat Safadi, Mateusz Budnik, Denis Pellerin

Publikováno v: Multimedia Tools and Applications
Multimedia Tools and Applications, Springer Verlag, 2016, 76 (9), pp.11941-11958. ⟨10.1007/s11042-016-4240-2⟩

published online; International audience; In this paper, we compare " traditional " engineered (hand-crafted) features (or descriptors) and learned features for content-based indexing of image or video documents. Learned (or semantic) features are ob

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40c1e8ce1d45389daaf907af19a7c66e
https://doi.org/10.1007/s11042-016-4240-2