Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Vignesh Ramanathan"'
Publikováno v:
2021 Innovations in Power and Advanced Computing Technologies (i-PACT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::552419ccb53d3398fa5813754cc4aa31
https://doi.org/10.1109/i-pact52855.2021.9696615
https://doi.org/10.1109/i-pact52855.2021.9696615
Publikováno v:
2021 2nd International Conference on Smart Electronics and Communication (ICOSEC).
Recently, there has been an increase in the introduction of renewable energy sources in the grid, and with that, an increased focus on power quality issues. Flexible Alternating Current Transmission Systems (FACTS) solve a number of such objectives,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db4f569fdd3f751213f46d74e0b98d3a
https://doi.org/10.1109/icosec51865.2021.9591906
https://doi.org/10.1109/icosec51865.2021.9591906
Publikováno v:
CVPR
Weakly supervised instance segmentation reduces the cost of annotations required to train models. However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of objects and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e0a47d5980e6ed2a4f511bb0971e628
https://doi.org/10.1109/cvpr46437.2021.01375
https://doi.org/10.1109/cvpr46437.2021.01375
Publikováno v:
CVPR
Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate whether it is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f222adb5a00d9c23c49e72c388e43dc5
https://doi.org/10.1109/cvpr46437.2021.01411
https://doi.org/10.1109/cvpr46437.2021.01411
Event cameras are activity-driven bio-inspired vision sensors, thereby resulting in advantages such as sparsity,high temporal resolution, low latency, and power consumption. Given the different sensing modality of event camera and high quality of con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::98a0e82965d5e15cff1e030e6aa150d2
http://arxiv.org/abs/2105.04216
http://arxiv.org/abs/2105.04216
Publikováno v:
CVPR
Large detection datasets have a long tail of lowshot classes with very few bounding box annotations. We wish to improve detection for lowshot classes with weakly labelled web-scale datasets only having image-level labels. This requires a detection fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b84dde8f5b231661d9a9cd16addb8b93
https://doi.org/10.1109/cvpr42600.2020.00936
https://doi.org/10.1109/cvpr42600.2020.00936
Autor:
Anirban Chakraborty, Vignesh Ramanathan, Pritesh Dwivedi, Chetan Singh Thakur, Bharath Katabathuni
Publikováno v:
WACV
Visual saliency is an important problem in the field of cognitive science and computer vision with applications such as surveillance, adaptive compressing, detecting unknown objects and scene understanding. In this paper, we propose a small and spars
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87fe8f5841115a483771f4cbb2e535de
https://doi.org/10.1109/wacv45572.2020.9093354
https://doi.org/10.1109/wacv45572.2020.9093354
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030660956
ECCV Workshops (2)
ECCV Workshops (2)
Object proposal generation is often the first step in many detection models. It is lucrative to train a good proposal model, that generalizes to unseen classes. Motivated by this, we study how a detection model trained on a small set of source classe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d79afb4765e9a9a164037eca83f2b05b
https://doi.org/10.1007/978-3-030-66096-3_32
https://doi.org/10.1007/978-3-030-66096-3_32
Publikováno v:
CVPR
Weakly supervised object detection aims at reducing the amount of supervision required to train detection models. Such models are traditionally learned from images/videos labelled only with the object class and not the object bounding box. In our wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ce379ded8cd135752d41dc42041d8c5
https://doi.org/10.1109/cvpr.2019.00303
https://doi.org/10.1109/cvpr.2019.00303
Autor:
Dhruv Mahajan, De-An Huang, Juan Carlos Niebles, Vignesh Ramanathan, Manohar Paluri, Li Fei-Fei, Lorenzo Torresani
Publikováno v:
CVPR
The ability to capture temporal information has been critical to the development of video understanding models. While there have been numerous attempts at modeling motion in videos, an explicit analysis of the effect of temporal information for video
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d745de8b3cdf5677e44a9449fdc9680
https://doi.org/10.1109/cvpr.2018.00769
https://doi.org/10.1109/cvpr.2018.00769