Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Mahyar Najibi"'
Publikováno v:
AAAI
Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad class of im
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c28b4b72bc0a2cfe2d027a509335901
https://doi.org/10.1609/aaai.v34i04.6017
https://doi.org/10.1609/aaai.v34i04.6017
Autor:
Ser-Nam Lim, Xintong Han, Peng Zhou, Bor-Chun Chen, Larry S. Davis, Mahyar Najibi, Abhinav Shrivastava
Publikováno v:
AAAI
Detecting manipulated images has become a significant emerging challenge. The advent of image sharing platforms and the easy availability of advanced photo editing software have resulted in a large quantities of manipulated images being shared on the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cc13c23f4974ef7a7b6c64052b23e0d
https://doi.org/10.1609/aaai.v34i07.7007
https://doi.org/10.1609/aaai.v34i07.7007
Autor:
Mahyar Najibi, Jingwei Ji, Yin Zhou, Charles R. Qi, Xinchen Yan, Scott Ettinger, Dragomir Anguelov
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198380
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7f2ed72b6c20b6d872fb538a2d85b00
https://doi.org/10.1007/978-3-031-19839-7_25
https://doi.org/10.1007/978-3-031-19839-7_25
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200793
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2241aea3a82b4624e326e3c629830771
https://doi.org/10.1007/978-3-031-20080-9_10
https://doi.org/10.1007/978-3-031-20080-9_10
We present an efficient foveal framework to perform object detection. A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales. Such a restriction of objects'
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd228af1701e5c55e89d59bede3218ed
Publikováno v:
CVPR
While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality 3D labels.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef72d2871e65642e2d4ffb69bf477d59
Autor:
Caroline Pantofaru, Mahyar Najibi, Zhichao Lu, Abhijit Kundu, Larry S. Davis, Guangda Lai, David A. Ross, Thomas Funkhouser, Vivek Rathod, Alireza Fathi
Publikováno v:
CVPR
We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In contrast, we pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::976bc5668dc8465ad5dce9c668e00317
https://doi.org/10.1109/cvpr42600.2020.01193
https://doi.org/10.1109/cvpr42600.2020.01193
Publikováno v:
CVPR
We propose a novel approach for generating region proposals for performing face-detection. Instead of classifying anchor boxes using features from a pixel in the convolutional feature map, we adopt a pooling-based approach for generating region propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcd65db4f998b5c5117bb303348e0777
https://doi.org/10.1109/cvpr.2019.00791
https://doi.org/10.1109/cvpr.2019.00791
Publikováno v:
ICCV
This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are like
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::566f23e7d932fdfe61e7fdc7eda29032
Publikováno v:
WACV
In this paper, we introduce the Face Magnifier Network (Face-MageNet), a face detector based on the Faster-RCNN framework which enables the flow of discriminative information of small scale faces to the classifier without any skip or residual connect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a53a4a26029652b0909c18443724bae8