Search Results for author: Robert Bergevin

Found 10 papers, 2 papers with code

Future Video Prediction from a Single Frame for Video Anomaly Detection

no code implementations15 Aug 2023 Mohammad Baradaran, Robert Bergevin

Inspired by the abilities of the future frame prediction proxy-task, we introduce the task of future video prediction from a single frame, as a novel proxy-task for video anomaly detection.

Semantic Segmentation Semi-supervised Anomaly Detection +3

$β$-Multivariational Autoencoder for Entangled Representation Learning in Video Frames

1 code implementation22 Nov 2022 Fatemeh Nouri, Robert Bergevin

In this paper, we propose the $\beta$-Multivariational Autoencoder ($\beta$MVAE) to learn a Multivariate Gaussian prior from video frames for use as part of a single object-tracking in form of a decision-making process.

Decision Making Object +2

Multi-Task Learning based Video Anomaly Detection with Attention

no code implementations14 Oct 2022 Mohammad Baradaran, Robert Bergevin

Our qualitative results show that the proposed method considers the object class effectively and learns motion with attention to the aforementioned important factors which results in a precise motion modeling and a better motion anomaly detection.

Anomaly Detection Multi-Task Learning +3

Object Class Aware Video Anomaly Detection through Image Translation

no code implementations3 May 2022 Mohammad Baradaran, Robert Bergevin

Semi-supervised video anomaly detection (VAD) methods formulate the task of anomaly detection as detection of deviations from the learned normal patterns.

Anomaly Detection Object +4

A Critical Study on the Recent Deep Learning Based Semi-Supervised Video Anomaly Detection Methods

no code implementations2 Nov 2021 Mohammad Baradaran, Robert Bergevin

This paper introduces the researchers of the field to a new perspective and reviews the recent deep-learning based semi-supervised video anomaly detection approaches, based on a common strategy they use for anomaly detection.

Semi-supervised Anomaly Detection Supervised Anomaly Detection +1

Online Mutual Foreground Segmentation for Multispectral Stereo Videos

1 code implementation8 Sep 2018 Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau, Robert Bergevin

The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications.

Foreground Segmentation

From Superpixel to Human Shape Modelling for Carried Object Detection

no code implementations10 Jan 2018 Farnoosh Ghadiri, Robert Bergevin, Guillaume-Alexandre Bilodeau

We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales.

Object object-detection +2

An adaptive thresholding approach for automatic optic disk segmentation

no code implementations14 Oct 2017 Farnoosh Ghadiri, Robert Bergevin, Masoud Shafiee

The optic disk is correctly detected in 98% of the images with the mean overlap of 36. 32% in the KHATAM database.

Segmentation

SPiKeS: Superpixel-Keypoints Structure for Robust Visual Tracking

no code implementations23 Oct 2016 François-Xavier Derue, Guillaume-Alexandre Bilodeau, Robert Bergevin

In visual tracking, part-based trackers are attractive since they are robust against occlusion and deformation.

Superpixels Visual Tracking

Reproducible Evaluation of Pan-Tilt-Zoom Tracking

no code implementations18 May 2015 Gengjie Chen, Pierre-Luc St-Charles, Wassim Bouachir, Thomas Joeisseint, Guillaume-Alexandre Bilodeau, Robert Bergevin

Tracking with a Pan-Tilt-Zoom (PTZ) camera has been a research topic in computer vision for many years.

Cannot find the paper you are looking for? You can Submit a new open access paper.