Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Mani Ranjbar"'
Publikováno v:
ICCV
Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly, in surveil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ad4ac167abd8aad05469cbb04a3a8e38
http://arxiv.org/abs/1904.02361
http://arxiv.org/abs/1904.02361
Publikováno v:
CVPR
Building a large image dataset with high-quality object masks for semantic segmentation is costly and time consuming. In this paper, we introduce a principled semi-supervised framework that only uses a small set of fully supervised images (having sem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3641cc8a5825778813084815c009a265
Ramsey theory is an active research area in combinatorics whose central theme is the emergence of order in large disordered structures, with Ramsey numbers marking the threshold at which this order first appears. For generalized Ramsey numbers $r(G,H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::19aefcf6120feec1db2eb08f4e3d3802
Autor:
Ze-Nian Li, Bahman Yari Saeed Khanloo, Ferdinand Stefanus, Tarek Sayed, Greg Mori, Mani Ranjbar, Nicolas Saunier
Publikováno v:
Computer Vision and Image Understanding. 116:676-689
We introduce MMTrack (max-margin tracker), a single-target tracker that linearly combines constant and adaptive appearance features. We frame offline single-camera tracking as a structured output prediction task where the goal is to find a sequence o
Autor:
Mani Ranjbar, Shohreh Kasaei
Publikováno v:
Computers & Electrical Engineering. 35:536-548
In this paper, the problem of spatial error concealment for real-time applications is addressed. The proposed method can be categorized in exemplar-based error concealment approaches. In this category, a patch of corrupted pixels are replaced by anot
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 35(4)
We develop an algorithm for structured prediction with nondecomposable performance measures. The algorithm learns parameters of Markov Random Fields (MRFs) and can be applied to multivariate performance measures. Examples include performance measures
Publikováno v:
ICCV Workshops
In this paper we develop a model for recognizing human interactions - activity recognition with multiple actors. An activity is modeled with a sequence of key poses, important atomic-level actions performed by the actors. Spatial arrangements between
Autor:
Ferdinand Stefanus, Greg Mori, Ze-Nian Li, Tarek Sayed, Mani Ranjbar, Nicolas Saunier, Bahman Yari Saeed Khanloo
Publikováno v:
CRV
In this paper, we introduce MMTrack, a hybrid single pedestrian tracking algorithm that puts together the advantages of descriptive and discriminative approaches for tracking. Specifically, we combine the idea of cluster-based appearance modeling and
Publikováno v:
Computer Vision – ECCV 2010 ISBN: 9783642155512
ECCV (2)
ECCV (2)
In this paper we develop an algorithm for structured prediction that optimizes against complex performance measures, those which are a function of false positive and false negative counts. The approach can be directly applied to performance measures
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2792d3c7524f4f452b3661123545f287
https://doi.org/10.1007/978-3-642-15552-9_42
https://doi.org/10.1007/978-3-642-15552-9_42
Publikováno v:
CVPR
In this paper we present a method for learning class-specific features for recognition. Recently a greedy layer-wise procedure was proposed to initialize weights of deep belief networks, by viewing each layer as a separate restricted Boltzmann machin