Skip to Main content Skip to Navigation

Dynamic visual saliency in image sequences

Abstract : Our thesis research is concerned with the estimation of motion saliency in image sequences. First, we have defined an original method to detect frames in which a salient motion is present. For this, we propose a framework relying on a deep neural network, and on the compensation of the dominant camera motion. Second, we have designed a method for estimating motion saliency maps. This method requires no learning. The motion saliency cue is obtained by an optical flow inpainting step, followed by a comparison with the initial flow. Third, we consider the problem of trajectory saliency estimation to handle progressive saliency over time. We have built a weakly supervised framework based on a recurrent auto-encoder that represents trajectories with latent codes. Performance of the three methods was experimentally assessed on real video datasets.
Complete list of metadata
Contributor : Léo Maczyta <>
Submitted on : Wednesday, December 23, 2020 - 4:14:04 PM
Last modification on : Thursday, March 11, 2021 - 3:38:05 AM


Files produced by the author(s)


  • HAL Id : tel-03087274, version 1


Léo Maczyta. Dynamic visual saliency in image sequences. Computer Vision and Pattern Recognition [cs.CV]. UNIVERSITÉ DE RENNES 1, 2020. English. ⟨tel-03087274v1⟩



Record views


Files downloads