288 citations · 453 across the 42 of their papers we have counts for
53 papers
Semantic Slots for Video Object-Centric Learning
Khalil Sabri, Guillaume-Alexandre Bilodeau, Nicolas Saunier +1
Video Object-Centric Learning (OCL) has traditionally focused on refining the encoder architecture to ensure temporal consistency. In this paper, we argue that the primary bottlene…
Learning Data Association for Multi-Object Tracking using Only Coordinates
Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier
We propose a novel Transformer-based module to address the data association problem for multi-object tracking. From detections obtained by a pretrained detector, this module uses o…
Real-time instance segmentation with polygons using an Intersection-over-Union loss
Katia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau
Predicting a binary mask for an object is more accurate but also more computationally expensive than a bounding box. Polygonal masks as developed in CenterPoly can be a good compro…
VisiTherS: Visible-thermal infrared stereo disparity estimation of human silhouette
Noreen Anwar, Philippe Duplessis-Guindon, Guillaume-Alexandre Bilodeau +1
This paper presents a novel approach for visible-thermal infrared stereoscopy, focusing on the estimation of disparities of human silhouettes. Visible-thermal infrared stereo poses…
GUILGET: GUI Layout GEneration with Transformer
Andrey Sobolevsky, Guillaume-Alexandre Bilodeau, Jinghui Cheng +1
Sketching out Graphical User Interface (GUI) layout is part of the pipeline of designing a GUI and a crucial task for the success of a software application. Arranging all component…
TopTrack: Tracking Objects By Their Top
Jacob Meilleur, Guillaume-Alexandre Bilodeau
In recent years, the joint detection-and-tracking paradigm has been a very popular way of tackling the multi-object tracking (MOT) task. Many of the methods following this paradigm…
Video Prediction by Efficient Transformers
Xi Ye, Guillaume-Alexandre Bilodeau
Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction…
A unified model for continuous conditional video prediction
Xi Ye, Guillaume-Alexandre Bilodeau
Different conditional video prediction tasks, like video future frame prediction and video frame interpolation, are normally solved by task-related models even though they share ma…
Improving tracking with a tracklet associator
Rémi Nahon, Guillaume-Alexandre Bilodeau, Gilles Pesant
Multiple object tracking (MOT) is a task in computer vision that aims to detect the position of various objects in videos and to associate them to a unique identity. We propose an…
4D-MultispectralNet: Multispectral Stereoscopic Disparity Estimation using Human Masks
Philippe Duplessis-Guindon, Guillaume-Alexandre Bilodeau
Multispectral stereoscopy is an emerging field. A lot of work has been done in classical stereoscopy, but multispectral stereoscopy is not studied as frequently. This type of stere…
ActAR: Actor-Driven Pose Embeddings for Video Action Recognition
Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier
Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR…
Transformers for 1D Signals in Parkinson's Disease Detection from Gait
Duc Minh Dimitri Nguyen, Mehdi Miah, Guillaume-Alexandre Bilodeau +1
This paper focuses on the detection of Parkinson's disease based on the analysis of a patient's gait. The growing popularity and success of Transformer networks in natural language…
VPTR: Efficient Transformers for Video Prediction
Xi Ye, Guillaume-Alexandre Bilodeau
In this paper, we propose a new Transformer block for video future frames prediction based on an efficient local spatial-temporal separation attention mechanism. Based on this new…
Leveraging Sentiment Analysis Knowledge to Solve Emotion Detection Tasks
Maude Nguyen-The, Guillaume-Alexandre Bilodeau, Jan Rockemann
Identifying and understanding underlying sentiment or emotions in text is a key component of multiple natural language processing applications. While simple polarity sentiment anal…
PolyTrack: Tracking with Bounding Polygons
Gaspar Faure, Hughes Perreault, Guillaume-Alexandre Bilodeau +1
In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons. Polytrack detects objects by producing heatmaps o…
Multi-Object Tracking and Segmentation with a Space-Time Memory Network
Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier
We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets. The proposed tracker, MeNToS, addresses particularly…
Vehicle Detection and Tracking From Surveillance Cameras in Urban Scenes
Oumayma Messoussi, Felipe Gohring de Magalhaes, Francois Lamarre +4
Detecting and tracking vehicles in urban scenes is a crucial step in many traffic-related applications as it helps to improve road user safety among other benefits. Various challen…
FFAVOD: Feature Fusion Architecture for Video Object Detection
Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier +1
A significant amount of redundancy exists between consecutive frames of a video. Object detectors typically produce detections for one image at a time, without any capabilities for…
CenterPoly: real-time instance segmentation using bounding polygons
Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier +1
We present a novel method, called CenterPoly, for real-time instance segmentation using bounding polygons. We apply it to detect road users in dense urban environments, making it s…
MeNToS: Tracklets Association with a Space-Time Memory Network
Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier
We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection. The proposed method addresses par…
Predicting Next Local Appearance for Video Anomaly Detection
Pankaj Raj Roy, Guillaume-Alexandre Bilodeau, Lama Seoud
We present a local anomaly detection method in videos. As opposed to most existing methods that are computationally expensive and are not very generalizable across different video…
Multiple Convolutional Features in Siamese Networks for Object Tracking
Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir
Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are sp…
MFST: Multi-Features Siamese Tracker
Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir
Siamese trackers have recently achieved interesting results due to their balance between accuracy and speed. This success is mainly due to the fact that deep similarity networks we…
Local Anomaly Detection in Videos using Object-Centric Adversarial Learning
Pankaj Raj Roy, Guillaume-Alexandre Bilodeau, Lama Seoud
We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in video…