Kernel association for classification and prediction: A survey
Y Motai - IEEE transactions on neural networks and learning …, 2014 - ieeexplore.ieee.org
Kernel association (KA) in statistical pattern recognition used for classification and prediction
have recently emerged in a machine learning and signal processing context. This survey …
have recently emerged in a machine learning and signal processing context. This survey …
Systematic analysis and review of video object retrieval techniques
Video object retrieval is a promising research direction, developing in the recent years, and
the current video object retrieval strategies are used for visualizing, digitizing, modeling, and …
the current video object retrieval strategies are used for visualizing, digitizing, modeling, and …
Weighed query-specific distance and hybrid NARX neural network for video object retrieval
CA Ghuge, V Chandra Prakash… - The Computer …, 2020 - academic.oup.com
The technical revolution in the field of video recording using the surveillance videos has
increased the amount of the video databases that caused the need for an efficient video …
increased the amount of the video databases that caused the need for an efficient video …
Detecting human action as the spatio-temporal tube of maximum mutual information
Human action detection in complex scenes is a challenging problem due to its high-
dimensional search space and dynamic backgrounds. To achieve efficient and accurate …
dimensional search space and dynamic backgrounds. To achieve efficient and accurate …
Object and motion cues based collaborative approach for human activity localization and recognition in unconstrained videos
J Ullah, MA Jaffar - Cluster Computing, 2018 - Springer
This paper addresses the problem of activity localization and recognition in large scale
video datasets by the collaborative use of holistic and motion based information (called …
video datasets by the collaborative use of holistic and motion based information (called …
A compressed sensing approach for query by example video retrieval
S Hou, S Zhou, MA Siddique - Multimedia tools and applications, 2014 - Springer
Recently, compressed Sensing (CS) has theoretically been proposed for more efficient
signal compression and recovery. In this paper, the CS based algorithms are investigated for …
signal compression and recovery. In this paper, the CS based algorithms are investigated for …
Tracking System with Re-identification Using a RGB String Kernel
People re-identification consists in identifying a person that comes back in a scene where it
has been previously detected. This key problem in visual surveillance applications may …
has been previously detected. This key problem in visual surveillance applications may …
Tracking system with re-identification using a graph kernels approach
This paper addresses people re-identification problem for visual surveillance applications.
Our approach is based on a rich description of each occurrence of a person thanks to a …
Our approach is based on a rich description of each occurrence of a person thanks to a …
Ré-identification de Personnes par Modèle de Noyaux de Graphe
Nous proposons dans cet article, des noyaux sur graphe définis entre le voisinage orienté
de chaque noeud à base de noyau Gaussien permettant la modélisation des individus et …
de chaque noeud à base de noyau Gaussien permettant la modélisation des individus et …