MLGCN: Multi-Laplacian graph convolutional networks for human action recognition

A Mazari, H Sahbi - The British machine vision conference (BMVC), 2019 - hal.science
Convolutional neural networks are nowadays witnessing a major success in different pattern
recognition problems. These learning models were basically designed to handle vectorial …

Multi-label Classification using Deep Multi-order Context-aware Kernel Networks

M Jiu, H Zhu, H Sahbi - arxiv preprint arxiv:2412.19491, 2024 - arxiv.org
Multi-label classification is a challenging task in pattern recognition. Many deep learning
methods have been proposed and largely enhanced classification performance. However …

COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Learning

AM Das, G Bhatt, L Kumari, S Verma… - arxiv preprint arxiv …, 2024 - arxiv.org
Retrieval augmentation, the practice of retrieving additional data from large auxiliary pools,
has emerged as an effective technique for enhancing model performance in the low-data …

Exploiting visual saliency for increasing diversity of image retrieval results

G Boato, DT Dang-Nguyen, O Muratov… - Multimedia Tools and …, 2016 - Springer
Diversification of search results allows for better and faster search, gaining knowledge about
different perspectives and viewpoints on retrieved information sources. Recently various …

Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning

H Sahbi - arxiv preprint arxiv:2306.17590, 2023 - arxiv.org
Magnitude pruning is one of the mainstream methods in lightweight architecture design
whose goal is to extract subnetworks with the largest weight connections. This method is …

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 …

Diversity-based interactive learning meets multimodality

RT Calumby, MA Gonçalves, R da Silva Torres - Neurocomputing, 2017 - Elsevier
In interactive retrieval tasks, one of the main objectives is to maximize the user information
gain throughout search sessions. Retrieving many relevant items is quite important, but it …

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 …

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) …

Deep total variation support vector networks

H Sahbi - Proceedings of the IEEE/CVF International …, 2019 - openaccess.thecvf.com
Support vector machines (SVMs) have been successful in solving many computer vision
tasks including image and video category recognition especially for small and mid-scale …