Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Dídac Surís"'
Publikováno v:
CVPR
We introduce a framework for learning from unlabeled video what is predictable in the future. Instead of committing up front to features to predict, our approach learns from data which features are predictable. Based on the observation that hyperboli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a93cbf3ee07f38160cba86d453312c0
http://arxiv.org/abs/2101.01600
http://arxiv.org/abs/2101.01600
Autor:
Ying Lin, Jiawei Han, Yi Fung, Manling Li, Shih-Fu Chang, Qing Lyu, Ben Zhou, Xudong Lin, Haoyu Wang, Chris Callison-Burch, Martha Palmer, Alexander Dong, Xiaodong Yu, Piyush Mishra, Dídac Surís, Tuan Lai, Hongming Zhang, Zhenhailong Wang, Susan Brown, Dan Roth, Brian Chen, Carl Vondrick, Sha Li, Haoyang Wen, Heng Ji, Xiaoman Pan
Publikováno v:
NAACL-HLT (Demonstrations)
We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a91a564d13c60de74c9e20fa3758dba
https://doi.org/10.18653/v1/2021.naacl-demos.16
https://doi.org/10.18653/v1/2021.naacl-demos.16
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585259
ECCV (29)
ECCV (29)
Language acquisition is the process of learning words from the surrounding scene. We introduce a meta-learning framework that learns how to learn word representations from unconstrained scenes. We leverage the natural compositional structure of langu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::78e11c95363be519803f71ae3a50092d
https://doi.org/10.1007/978-3-030-58526-6_26
https://doi.org/10.1007/978-3-030-58526-6_26
Publikováno v:
CVPR
We propose a framework for learning through drawing. Our goal is to learn the correspondence between spoken words and abstract visual attributes, from a dataset of spoken descriptions of images. Building upon recent findings that GAN representations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d2db94ff352d9df672c67f4601516d5
https://doi.org/10.1109/cvpr.2019.00213
https://doi.org/10.1109/cvpr.2019.00213
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110178
ECCV Workshops (4)
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname
ECCV Workshops (4)
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname
The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in manageable way
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::284cfdd60a58f1b7de8c318e0db303ce
https://doi.org/10.1007/978-3-030-11018-5_62
https://doi.org/10.1007/978-3-030-11018-5_62
Publikováno v:
Springer US
In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91fab61af1739e23e87fb05619b07ba8
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012304
ECCV (6)
ECCV (6)
In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::203cb9520c47acd6dd99a1da8215411f
https://doi.org/10.1007/978-3-030-01231-1_40
https://doi.org/10.1007/978-3-030-01231-1_40
Publikováno v:
Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
ICC Workshops
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
ICC Workshops
©2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::617ab9670c5aad53f26a9f771ef7b9ce
http://hdl.handle.net/2117/110566
http://hdl.handle.net/2117/110566