S
Sergi Caelles
Researcher at ETH Zurich
Publications - 17
Citations - 2933
Sergi Caelles is an academic researcher from ETH Zurich. The author has contributed to research in topics: Segmentation & Image segmentation. The author has an hindex of 13, co-authored 16 publications receiving 2145 citations. Previous affiliations of Sergi Caelles include Bell Labs.
Papers
More filters
Posted Content
The 2017 DAVIS Challenge on Video Object Segmentation
Jordi Pont-Tuset,Federico Perazzi,Sergi Caelles,Pablo Arbeláez,Alexander Sorkine-Hornung,Luc Van Gool +5 more
TL;DR: The scope of the benchmark, the main characteristics of the dataset, the evaluation metrics of the competition, and a detailed analysis of the results of the participants to the challenge are described.
Proceedings ArticleDOI
One-Shot Video Object Segmentation
Sergi Caelles,Kevis-Kokitsi Maninis,Jordi Pont-Tuset,Laura Leal-Taixé,Daniel Cremers,L. Van Gool +5 more
TL;DR: One-shot video object segmentation (OSVOS) as mentioned in this paper is based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence.
Posted Content
One-Shot Video Object Segmentation
Sergi Caelles,Kevis-Kokitsi Maninis,Jordi Pont-Tuset,Laura Leal-Taixé,Daniel Cremers,Luc Van Gool +5 more
TL;DR: One-shot video object segmentation (OSVOS) as mentioned in this paper is based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence.
Proceedings ArticleDOI
Deep Extreme Cut: From Extreme Points to Object Segmentation
TL;DR: This paper explores the use of extreme points in an object as input to obtain precise object segmentation for images and videos by adding an extra channel to the image in the input of a convolutional neural network (CNN), which contains a Gaussian centered in each of the extreme points.
Journal ArticleDOI
Video Object Segmentation without Temporal Information
Kevis-Kokitsi Maninis,Sergi Caelles,Yuhua Chen,Jordi Pont-Tuset,Laura Leal-Taixé,Daniel Cremers,L. Van Gool +6 more
TL;DR: Semantic One-Shot Video Object Segmentation is presented, based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one shot).