Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Hyounghun Kim"'
Natural language guided embodied task completion is a challenging problem since it requires understanding natural language instructions, aligning them with egocentric visual observations, and choosing appropriate actions to execute in the environment
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::922e36ddd218344d28b9f29117f586f7
http://arxiv.org/abs/2205.09249
http://arxiv.org/abs/2205.09249
Publikováno v:
AAAI
The Visual Dialog task requires a model to exploit both image and conversational context information to generate the next response to the dialogue. However, via manual analysis, we find that a large number of conversational questions can be answered
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1af3667e639900064666dd7eddac4ef0
https://doi.org/10.1609/aaai.v34i05.6320
https://doi.org/10.1609/aaai.v34i05.6320
Demand for image editing has been increasing as users' desire for expression is also increasing. However, for most users, image editing tools are not easy to use since the tools require certain expertise in photo effects and have complex interfaces.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1189fd9e6a60e2c0dfdea2b00547fb1
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1a64c8b2753adc24e5d392082f02ebdc
https://doi.org/10.18653/v1/2021.emnlp-main.518
https://doi.org/10.18653/v1/2021.emnlp-main.518
Publikováno v:
ACL/IJCNLP (1)
Recent years have witnessed various types of generative models for natural language generation (NLG), especially RNNs or transformer based sequence-to-sequence models, as well as variational autoencoder (VAE) and generative adversarial network (GAN)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d55b0afc44df5412bc97d7a9a25a7a7
https://doi.org/10.18653/v1/2021.acl-long.355
https://doi.org/10.18653/v1/2021.acl-long.355
Publikováno v:
EMNLP (Findings)
For embodied agents, navigation is an important ability but not an isolated goal. Agents are also expected to perform specific tasks after reaching the target location, such as picking up objects and assembling them into a particular arrangement. We
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f55f38b33f21b87b381a9bf38c5c55d
https://doi.org/10.18653/v1/2020.findings-emnlp.348
https://doi.org/10.18653/v1/2020.findings-emnlp.348
Publikováno v:
ACL
Videos convey rich information. Dynamic spatio-temporal relationships between people/objects, and diverse multimodal events are present in a video clip. Hence, it is important to develop automated models that can accurately extract such information f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11dd6f963941c22946571db2a28b7543
Publikováno v:
The Laryngoscope. 129
Objectives/hypothesis Augmented reality (AR) allows for the addition of transparent virtual images and video to one's view of a physical environment. Our objective was to develop a head-worn, AR system for accurate, intraoperative localization of pat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6e536820551aaa0589c3e4023e711e5
https://doi.org/10.1002/lary.28098
https://doi.org/10.1002/lary.28098
Autor:
Hyounghun Kim, Mohit Bansal
Publikováno v:
ACL (1)
Paragraph-style image captions describe diverse aspects of an image as opposed to the more common single-sentence captions that only provide an abstract description of the image. These paragraph captions can hence contain substantial information of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a73e3448b2632da1ca418d1b28e1acef
http://arxiv.org/abs/1906.06216
http://arxiv.org/abs/1906.06216
Autor:
Henry Fuchs, Zhaoqi Su, Jan-Michael Frahm, Xinran Lu, Rohan Chabra, Hyounghun Kim, Zihe Qin, Nicholas Rewkowski, True Price, Andrei State, Yebin Liu, Zhen Wei, Young-Woon Cha, Zhenlin Xu, Adrian Ilie
Publikováno v:
IEEE transactions on visualization and computer graphics. 24(11)
We propose a new approach for 3D reconstruction of dynamic indoor and outdoor scenes in everyday environments, leveraging only cameras worn by a user. This approach allows 3D reconstruction of experiences at any location and virtual tours from anywhe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::05129c1fc57d72d51f5f8bd9a8742564
https://pubmed.ncbi.nlm.nih.gov/30207957
https://pubmed.ncbi.nlm.nih.gov/30207957