Zobrazeno 1 - 10
of 115
pro vyhledávání: '"Kuo-Hao Zeng"'
Publikováno v:
CVPR
We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption. Intelligent navigation may involve interacting with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1ba492fd72d2472eef430bb19ac23bd
http://arxiv.org/abs/2104.14040
http://arxiv.org/abs/2104.14040
Publikováno v:
CVPR
In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agent itself. Visual reaction entails predicting the future changes in a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8144be20eeb764b201a8d43c975b352b
https://doi.org/10.1109/cvpr42600.2020.01159
https://doi.org/10.1109/cvpr42600.2020.01159
Publikováno v:
ICRA
$ $Visual place recognition is challenging, especially when only a few place exemplars are given. To mitigate the challenge, we consider place recognition method using omnidirectional cameras and propose a novel Omnidirectional Convolutional Neural N
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::85f6161213d02f5173ff5942646149b2
https://doi.org/10.1109/icra.2018.8463173
https://doi.org/10.1109/icra.2018.8463173
Publikováno v:
ICCV
We introduce a general framework for visual forecasting, which directly imitates visual sequences without additional supervision. As a result, our model can be applied at several semantic levels and does not require any domain knowledge or handcrafte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c7718f25314d033c4ccfbe3fa56959a
http://arxiv.org/abs/1708.05827
http://arxiv.org/abs/1708.05827
Publikováno v:
CVPR
For survival, a living agent (e.g., human in Fig. 1(a)) must have the ability to assess risk (1) by temporally anticipating accidents before they occur (Fig. 1(b)), and (2) by spatially localizing risky regions (Fig. 1(c)) in the environment to move
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::068dff1bd3e69451b157afa26e107c03
https://doi.org/10.1109/cvpr.2017.146
https://doi.org/10.1109/cvpr.2017.146
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 26(7)
Due to the unprecedented growth of unedited videos, finding highlights relevant to a text query in a set of unedited videos has become increasingly important. We refer this task as semantic highlight retrieval and propose a query-dependent video repr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91784348f5de58502ec8bcb9ee82b8b8
https://pubmed.ncbi.nlm.nih.gov/28212082
https://pubmed.ncbi.nlm.nih.gov/28212082
Publikováno v:
Computer Vision – ACCV 2016 Workshops ISBN: 9783319544069
ACCV Workshops (1)
ACCV Workshops (1)
Generating video descriptions has many important applications such as human-robot interaction, video indexing, video summarization and assisting for the visually impaired. Many significant breakthroughs in deep learning and releases of large-scale op
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1bb6edeb7f0a1a88e1356bab476bb1a5
https://doi.org/10.1007/978-3-319-54407-6_18
https://doi.org/10.1007/978-3-319-54407-6_18
Autor:
Kuo-Hao Zeng, Tseng-Hung Chen, Ching-Yao Chuang, Yuan-Hong Liao, Juan Carlos Niebles, Min Sun
We propose a scalable approach to learn video-based question answering (QA): answer a "free-form natural language question" about a video content. Our approach automatically harvests a large number of videos and descriptions freely available online.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc2bd57445950172103a53439aa4f16f
http://arxiv.org/abs/1611.04021
http://arxiv.org/abs/1611.04021
Publikováno v:
ICIP
Finding highlights relevant to a text query in unedited videos has become increasingly important due to their unprecedented growth. We refer this task as semantic highlight retrieval and propose a query-dependent video representation for retrieving a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::394cf2ba8042cb8686876042d2fc2395
https://doi.org/10.1109/icip.2016.7532982
https://doi.org/10.1109/icip.2016.7532982
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464749
ECCV (2)
ECCV (2)
A great video title describes the most salient event compactly and captures the viewer’s attention. In contrast, video captioning tends to generate sentences that describe the video as a whole. Although generating a video title automatically is a v
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0c1d3a24c9031cf57c222fe81a804b4
https://doi.org/10.1007/978-3-319-46475-6_38
https://doi.org/10.1007/978-3-319-46475-6_38