activity
20102022
most citedLow-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation

171 citations · 358 across the 21 of their papers we have counts for

collaborators
Showing 2021Show all

8 papers · 1 filter

cs.LG2021★ 3 cited

Trajectory Clustering Performance Evaluation: If we know the answer, it's not clustering

Mohsen Rezaie, Nicolas Saunier

Advancements in Intelligent Traffic Systems (ITS) have made huge amounts of traffic data available through automatic data collection. A big part of this data is stored as trajector…

cs.CV2021

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…

cs.CV2021★ 1 cited

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…

cs.CV2021

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…

cs.CV2021

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…

cs.CV2021

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…