Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Zhongzheng Ren"'
We introduce an approach for selecting objects in neural volumetric 3D representations, such as multi-plane images (MPI) and neural radiance fields (NeRF). Our approach takes a set of foreground and background 2D user scribbles in one view and automa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba798f1d14bbc480bd2db06dfc105ebd
http://arxiv.org/abs/2205.14929
http://arxiv.org/abs/2205.14929
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c39f7397ac55417866fe690a8598c0e3
https://doi.org/10.2139/ssrn.4109911
https://doi.org/10.2139/ssrn.4109911
Solving complex real-world tasks, e.g., autonomous fleet control, often involves a coordinated team of multiple agents which learn strategies from visual inputs via reinforcement learning. Many existing multi-agent reinforcement learning (MARL) algor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66c2f4323f6f1b42a3ba982c94a3c6a3
http://arxiv.org/abs/2108.03319
http://arxiv.org/abs/2108.03319
Autor:
Zhongzheng Ren, Jan Kautz, Yong Jae Lee, Alexander G. Schwing, Ming-Yu Liu, Xiaodong Yang, Zhiding Yu
Publikováno v:
CVPR
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors te
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e17111edad3d00dbcac5c12f19854161
https://doi.org/10.1109/cvpr42600.2020.01061
https://doi.org/10.1109/cvpr42600.2020.01061
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585280
ECCV (19)
ECCV (19)
Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive image-level tags. However, real-world annotations are often diverse in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b5d0d2ba62680d665ebc09e04311d4b
https://doi.org/10.1007/978-3-030-58529-7_18
https://doi.org/10.1007/978-3-030-58529-7_18
Autor:
Zhongzheng Ren, Yong Jae Lee
Publikováno v:
CVPR
In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn generalizable high-le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f2ba4c962b516ab1a44d35e87c214cb
https://doi.org/10.1109/cvpr.2018.00086
https://doi.org/10.1109/cvpr.2018.00086
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012458
ECCV (1)
ECCV (1)
There is an increasing concern in computer vision devices invading users’ privacy by recording unwanted videos. On the one hand, we want the camera systems to recognize important events and assist human daily lives by understanding its videos, but
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33d42d621be0fa94c02c56c9068939ab
https://doi.org/10.1007/978-3-030-01246-5_38
https://doi.org/10.1007/978-3-030-01246-5_38
Publikováno v:
WACV
In neuroscience, understanding animal behaviors is key to studying their memory patterns. Meanwhile, this is also the most time-consuming and difficult process because it relies heavily on humans to manually annotate the videos recording the animals.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c98fad7ad12fcb713634334019822e31
https://doi.org/10.1109/wacv.2017.147
https://doi.org/10.1109/wacv.2017.147