Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Ben Packer"'
A common approach for testing fairness issues in text-based classifiers is through the use of counterfactuals: does the classifier output change if a sensitive attribute in the input is changed? Existing counterfactual generation methods typically re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcd56812ff9daddad4a69797b824ed14
Autor:
Allan Heydon, Benjamin Ricaud, Linjun Shou, Dmitry Ustalov, Yanick Schraner, George Yu, Daria Baidakova, Ly Dinh, Paul Groth, Mehrnoosh Sameki, Marinka Zitnik, Flavian Vasile, Krishnaram Kenthapadi, Benjamin Wollmer, Felix Gessert, Da-Cheng Juan, Hong Cheng, Javier Albert, David Rohde, Onur Celebi, Robert West, Xiang Wang, Dawei Yin, Amine Benhalloum, Junzhou Huang, Fuchun Sun, Michaël Defferrard, Ming Gong, Rezvaneh Rezapour, Levan Tsinadze, Shubhanshu Mishra, Stratis Ioannidis, Francisco M. Couto, Yicheng Fan, Xiangnan He, Christian Scheller, Yueqi Wang, Yu Rong, Pasquale Lisena, Sharada P. Mohanty, Nicolas Aspert, Irene Teinemaa, Chun-Ta Lu, Volodymyr Miz, Jiawei Chen, Johny Jose, Xiangyu Zhao, Philip Pham, Yatao Bian, Manuel K. Schneider, Jennifer G. Dy, Nashlie Sephus, Dmitri Goldenberg, Jiliang Tang, Fuli Feng, Wenbing Huang, Olivier Jeunen, Wenqi Fan, Nikita Popov, Mario Koenig, Shobeir Fakhraei, Olesia Altunina, Smriti Bhagat, Samin Aref, Chun-Sung Ferng, Wolfram Wingerath, Evann Courdier, Martin Müller, Xiubo Geng, Xingjie Zhou, Otmane Sakhi, Dragan Cvetinovic, Florian Laurent, Norbert Ritter, Cesar Ilharco Magalhaes, Stephan Succo, Jian Pei, Ben Packer, Tingyang Xu, Ilkay Yildiz, Rose Howell, Jana Diesner, Tudor Mihai Avram, Arjun Gopalan, Alexey Drutsa, Daxin Jiang, Albert Meroño-Peñuela, Christos Faloutsos
Publikováno v:
The Web Conference 2021: companion of the World Wide Web Conference WWW 2021: April 19-23, 2021, Ljubljana, Slovenia
The Web Conference 2021
30th World Wide Web (WWW) Conference (WebConf), APR 19-23, 2021, ELECTR NETWORK
WEB CONFERENCE 2021: COMPANION OF THE WORLD WIDE WEB CONFERENCE (WWW 2021)
The Web Conference 2021
30th World Wide Web (WWW) Conference (WebConf), APR 19-23, 2021, ELECTR NETWORK
WEB CONFERENCE 2021: COMPANION OF THE WORLD WIDE WEB CONFERENCE (WWW 2021)
This report summarizes the 23 tutorials hosted at The Web Conference 2021: nine lecture-style tutorials and 14 hands-on tutorials.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8db21f1ce6612200bda91f82be15d8cf
https://doi.org/10.1145/3442442.3453701
https://doi.org/10.1145/3442442.3453701
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28ba2802b1e1e0ccf9b8439e9ae15acb
https://doi.org/10.18653/v1/2021.emnlp-main.386
https://doi.org/10.18653/v1/2021.emnlp-main.386
Publikováno v:
EMNLP (1)
NLP models are shown to suffer from robustness issues, i.e., a model's prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled Adversarial Text Generation (CAT-Gen) model that, given an input tex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74d8cf24aa3297cb5bd20853479fc308
https://doi.org/10.18653/v1/2020.emnlp-main.417
https://doi.org/10.18653/v1/2020.emnlp-main.417
Autor:
S Bandla, Daphne Koller, Kristen Grauman, Ben Packer, Yong Jae Lee, Yangqing Jia, Chao-Yeh Chen, Kate Saenko, Juan Carlos Niebles, Trevor Darrell, Li Fei-Fei
We argue that mid-level representations can bridge the gap between existing low-level models, which are incapable of capturing the structure of interactive verbs, and contemporary high-level schemes, which rely on the output of potentially brittle in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3baeebfad2d003885767ec8611a92e3c
https://doi.org/10.21236/ada570728
https://doi.org/10.21236/ada570728
Publikováno v:
CVPR
Understanding natural human activity involves not only identifying the action being performed, but also locating the semantic elements of the scene and describing the person's interaction with them. We present a system that is able to recognize compl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cbaf571a01c1ada2662cf307faecf749
https://doi.org/10.1109/cvpr.2012.6247824
https://doi.org/10.1109/cvpr.2012.6247824
Publikováno v:
Computer Vision – ECCV 2010 ISBN: 9783642155543
ECCV (5)
ECCV (5)
The goal of this paper is to provide an accurate pixel-level segmentation of a deformable foreground object in an image. We combine state-of-the-art local image segmentation techniques with a global object-specific contour model to form a coherent en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7aad7a4ca9d90299ba3758e627de9fe1
https://doi.org/10.1007/978-3-642-15555-0_25
https://doi.org/10.1007/978-3-642-15555-0_25