Vehicle re-identification in still images: Application of semi-supervised learning and re-ranking
F Wu, S Yan, JS Smith, B Zhang - Signal Processing: Image …, 2019 - Elsevier
Vehicle re-identification (re-ID), namely, finding exactly the same vehicle from a large
number of vehicle images, remains a great challenge in computer vision. Most existing …
number of vehicle images, remains a great challenge in computer vision. Most existing …
A survey of automatic event detection in multi-camera third generation surveillance systems
T D'Orazio, C Guaragnella - International Journal of Pattern …, 2015 - World Scientific
Third generation surveillance systems are largely requested for intelligent surveillance of
different scenarios such as public areas, urban traffic control, smart homes and so on. They …
different scenarios such as public areas, urban traffic control, smart homes and so on. They …
Active learning for interactive satellite image change detection
We introduce in this paper a novel active learning algorithm for satellite image change
detection. The proposed solution is interactive and based on a question and answer model …
detection. The proposed solution is interactive and based on a question and answer model …
Misalignment resilient cca for interactive satellite image change detection
H Sahbi - 2016 23rd International Conference on Pattern …, 2016 - ieeexplore.ieee.org
Change detection, in multi-temporal satellite imagery, seeks to discover relevant changes
and to discard irrelevant ones. This task is usually achieved by modeling accurate decision …
and to discard irrelevant ones. This task is usually achieved by modeling accurate decision …
One-Shot Multi-Rate Pruning of Graph Convolutional Networks
H Sahbi - arXiv preprint arXiv:2312.17615, 2023 - arxiv.org
In this paper, we devise a novel lightweight Graph Convolutional Network (GCN) design
dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and …
dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and …
Frugal Satellite Image Change Detection with Deep-Net Inversion
H Sahbi, S Deschamps - arXiv preprint arXiv:2309.14781, 2023 - arxiv.org
Change detection in satellite imagery seeks to find occurrences of targeted changes in a
given scene taken at different instants. This task has several applications ranging from land …
given scene taken at different instants. This task has several applications ranging from land …
Skeleton-based hand-gesture recognition with lightweight graph convolutional networks
H Sahbi - arXiv preprint arXiv:2104.04255, 2021 - arxiv.org
Graph convolutional networks (GCNs) aim at extending deep learning to arbitrary irregular
domains, namely graphs. Their success is highly dependent on how the topology of input …
domains, namely graphs. Their success is highly dependent on how the topology of input …
Reinforcement-based Display-size Selection for Frugal Satellite Image Change Detection
H Sahbi - arXiv preprint arXiv:2312.16965, 2023 - arxiv.org
We introduce a novel interactive satellite image change detection algorithm based on active
learning. The proposed method is iterative and consists in frugally probing the user (oracle) …
learning. The proposed method is iterative and consists in frugally probing the user (oracle) …
Learning cca representations for misaligned data
H Sahbi - Proceedings of the European Conference on …, 2018 - openaccess.thecvf.com
Canonical correlation analysis (CCA) is a statistical learning method that seeks to build view-
independent latent representations from multi-view data. This method has been successfully …
independent latent representations from multi-view data. This method has been successfully …
Adaptive affinity for associations in multi-target multi-camera tracking
Data associations in multi-target multi-camera tracking (MTMCT) usually estimate affinity
directly from re-identification (re-ID) feature distances. However, we argue that it might not …
directly from re-identification (re-ID) feature distances. However, we argue that it might not …