Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Anurag Arnab"'
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::30e039bece66e713e603026e01e32180
https://pubmed.ncbi.nlm.nih.gov/36121952
https://pubmed.ncbi.nlm.nih.gov/36121952
Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning from noisy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e19dd1ca0c846279f69828eb772e5b8d
Autor:
Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, Neil Houlsby
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200793
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::097af93c692a87cf46cc4f2a732946e3
https://doi.org/10.1007/978-3-031-20080-9_42
https://doi.org/10.1007/978-3-031-20080-9_42
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly models these s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d59b1f80b1eebf5142002f3c4151293
http://arxiv.org/abs/2103.15662
http://arxiv.org/abs/2103.15662
We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of transform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80510156a30214c4033d6c4c1d3f8738
Scenic is an open-source JAX library with a focus on Transformer-based models for computer vision research and beyond. The goal of this toolkit is to facilitate rapid experimentation, prototyping, and research of new vision architectures and models.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::226ae423d8bfaf46bf91b23f8eefa372
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695248
ACCV (1)
ACCV (1)
Visual-based 3D detection is drawing a lot of attention recently. Despite the best efforts from the computer vision researchers visual-based 3D detection remains a largely unsolved problem. This is primarily due to the lack of accurate depth percepti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::271a7491088518af0ce78c223cedbeab
https://doi.org/10.1007/978-3-030-69525-5_21
https://doi.org/10.1007/978-3-030-69525-5_21
Publikováno v:
IROS
Personal robots and driverless cars need to be able to operate in novel environments and thus quickly and efficiently learn to recognise new object classes. We address this problem by considering the task of video object segmentation. Previous accura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c95a69334fe717588ed85c401a06bca8
https://doi.org/10.1109/iros45743.2020.9341737
https://doi.org/10.1109/iros45743.2020.9341737
Graphs are an invaluable modelling tool in many domains, but visualising large graphs in their entirety can be difficult. Hierarchical graph visualisation – recursively clustering a graph’s nodes to view it at a higher level of abstraction – ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1636372f70c6d066578c62c10d3da3ad
https://ora.ox.ac.uk/objects/uuid:e5a82113-71d3-454a-bdc5-dbee400bcfee
https://ora.ox.ac.uk/objects/uuid:e5a82113-71d3-454a-bdc5-dbee400bcfee
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586065
ECCV (10)
ECCV (10)
Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present a spatio-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bcc68131a79761ba9ca616e7ad24eab2
https://doi.org/10.1007/978-3-030-58607-2_44
https://doi.org/10.1007/978-3-030-58607-2_44