Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Rodrigo Benenson"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 40:973-986
Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the "perfect single frame detector". We enable our analysis by creating a human baseline for pedestrian detection (over the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0fe7a02534161573aa1a5219c43ca01c
https://doi.org/10.1109/tpami.2017.2700460
https://doi.org/10.1109/tpami.2017.2700460
Publikováno v:
CVPR
Manually annotating object segmentation masks is very time consuming. Interactive object segmentation methods offer a more efficient alternative where a human annotator and a machine segmentation model collaborate. In this paper we make several contr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e27e883822101bed8109af8ba8ab2f5
Publikováno v:
IEEE Transactions on Medical Imaging
IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers, 2015, 34 (12), pp.2603--2617. ⟨10.1109/TMI.2015.2450831⟩
IEEE Transactions on Medical Imaging, 2015, 34 (12), pp.2603--2617. ⟨10.1109/TMI.2015.2450831⟩
IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers, 2015, 34 (12), pp.2603--2617. ⟨10.1109/TMI.2015.2450831⟩
IEEE Transactions on Medical Imaging, 2015, 34 (12), pp.2603--2617. ⟨10.1109/TMI.2015.2450831⟩
International audience; Detecting tools in surgical videos is an important ingredient for context-aware computer-assisted surgical systems. To this end, we present a new surgical tool detection dataset and a method for joint tool detection and pose e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::760cf03db5f2cdb72c779b17dc2d34c5
https://doi.org/10.1109/tmi.2015.2450831
https://doi.org/10.1109/tmi.2015.2450831
Publikováno v:
ICCV
People nowadays share large parts of their personal lives through social media. Being able to automatically recognise people in personal photos may greatly enhance user convenience by easing photo album organisation. For human identification task, ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a71981e9da1ff55631285ad21bc466bb
http://arxiv.org/abs/1710.03224
http://arxiv.org/abs/1710.03224
Publikováno v:
CVPR
Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation. Our model proceeds on a per-frame basis, guided by the output of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d03d4adf72e0c850830621700ee0cf0b
https://doi.org/10.1109/cvpr.2017.372
https://doi.org/10.1109/cvpr.2017.372
Publikováno v:
CVPR
Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data. We revisit CNN design and point out key adaptations, enabling plain FasterRCNN to obta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33f34b31925b48ca008a0d6d8234cfdc
https://doi.org/10.1109/cvpr.2017.474
https://doi.org/10.1109/cvpr.2017.474
Publikováno v:
CVPR
Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, features, and the classifier becoming one neural network improved results two-fold on general object detection. One indispensable component is non-m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71fdfec7675b8e96e87601619ae488ed
http://arxiv.org/abs/1705.02950
http://arxiv.org/abs/1705.02950
Publikováno v:
International Journal of Computer Vision
Convolutional networks reach top quality in pixel-level video object segmentation but require a large amount of training data (1k~100k) to deliver such results. We propose a new training strategy which achieves state-of-the-art results across three e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f64c5879168c3bd89c5f76ed68d14d6
http://arxiv.org/abs/1703.09554
http://arxiv.org/abs/1703.09554