Zobrazeno 1 - 10
of 80
pro vyhledávání: '"Tsu-Jui Fu"'
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf479849a5e72f589898c7f209f64e95
https://doi.org/10.1109/cvpr52688.2022.01026
https://doi.org/10.1109/cvpr52688.2022.01026
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200588
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8eecd95a560e00fb75e452279a3971a7
https://doi.org/10.1007/978-3-031-20059-5_41
https://doi.org/10.1007/978-3-031-20059-5_41
Autor:
Tsu-Jui Fu, William Yang Wang
Publikováno v:
NAACL-HLT
Using natural language as a hint can supply an additional reward for playing sparse-reward games. Achieving a goal should involve several different hints, while the given hints are usually incomplete. Those unmentioned latent hints still rely on the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b0b5339493da0db82cc65a499a3bdae4
https://doi.org/10.18653/v1/2021.naacl-main.249
https://doi.org/10.18653/v1/2021.naacl-main.249
Publikováno v:
Proceedings of the Second Workshop on Advances in Language and Vision Research.
Video editing tools are widely used nowadays for digital design. Although the demand for these tools is high, the prior knowledge required makes it difficult for novices to get started. Systems that could follow natural language instructions to perfo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9ab430a0f0fac49ecb3ab2a9315a8dc2
https://doi.org/10.18653/v1/2021.alvr-1.8
https://doi.org/10.18653/v1/2021.alvr-1.8
Creating presentation materials requires complex multimodal reasoning skills to summarize key concepts and arrange them in a logical and visually pleasing manner. Can machines learn to emulate this laborious process? We present a novel task and appro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c83c5871f0f9da4f11739e03e80ae9a7
Autor:
Wanrong Zhu, Kazoo Sone, Xin Wang, An Yan, Sugato Basu, William Yang Wang, Tsu-Jui Fu, Pradyumna Narayana
Publikováno v:
EACL
Scopus-Elsevier
Scopus-Elsevier
One of the most challenging topics in Natural Language Processing (NLP) is visually-grounded language understanding and reasoning. Outdoor vision-and-language navigation (VLN) is such a task where an agent follows natural language instructions and na
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34afb2748327ab99c343fc322083fa7e
https://doi.org/10.18653/v1/2021.eacl-main.103
https://doi.org/10.18653/v1/2021.eacl-main.103
Publikováno v:
EACL
Recent advances in language and vision push forward the research of captioning a single image to describing visual differences between image pairs. Suppose there are two images, I_1 and I_2, and the task is to generate a description W_{1,2} comparing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0271229e73c5015acef2372e102ed2a
Publikováno v:
EMNLP (1)
Iterative Language-Based Image Editing (IL-BIE) tasks follow iterative instructions to edit images step by step. Data scarcity is a significant issue for ILBIE as it is challenging to collect large-scale examples of images before and after instructio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::194f26c4ea2d5c0a47e9943ef22c8797
http://arxiv.org/abs/2009.09566
http://arxiv.org/abs/2009.09566
Publikováno v:
ACL/IJCNLP (Findings)
Although distant supervision automatically generates training data for relation extraction, it also introduces false-positive (FP) and false-negative (FN) training instances to the generated datasets. Whereas both types of errors degrade the final mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::783afd22dd444e8a1b9f43d15407e1d2
Autor:
Tsu-Jui Fu, Miguel P. Eckstein, Matthew F. Peterson, Scott T. Grafton, William Yang Wang, Xin Eric Wang
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585389
ECCV (6)
ECCV (6)
Vision-and-Language Navigation (VLN) is a task where agents must decide how to move through a 3D environment to reach a goal by grounding natural language instructions to the visual surroundings. One of the problems of the VLN task is data scarcity s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::34ce956b968e4c20d2a92cfc563d6f89
https://doi.org/10.1007/978-3-030-58539-6_5
https://doi.org/10.1007/978-3-030-58539-6_5