Corpus ID: 235899137

MeNToS: Tracklets Association with a Space-Time Memory Network

  title={MeNToS: Tracklets Association with a Space-Time Memory Network},
  author={Mehdi Miah and Guillaume-Alexandre Bilodeau and 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 particularly the data association problem. Indeed, the recently introduced HOTA metric, that has a better alignment with the human visual assessment by evenly balancing detections and associations quality, has shown that improvements are still needed for data association. After creating tracklets using instance… Expand

Figures and Tables from this paper


Video Object Segmentation Using Space-Time Memory Networks
This work proposes a novel solution for semi-supervised video object segmentation by leveraging memory networks and learning to read relevant information from all available sources to better handle the challenges such as appearance changes and occlussions. Expand
MOTS: Multi-Object Tracking and Segmentation
This paper creates dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure, and proposes a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network. Expand
Mask Selection and Propagation for Unsupervised Video Object Segmentation
This work introduces a novel idea of assessing mask quality using a neural network called Selector Net, trained is such way that it is generalizes across various datasets and is able to limit the noise accumulated along the video. Expand
LIFTS: Lidar and Monocular Image Fusion for Multi-Object Tracking and Segmentation
In recent years, the computer vision society has made significant progress in multi-object tracking (MOT) and video object segmentation (VOS) respectively. Further progress can be achieved byExpand
A Greedy Data Association Technique for Multiple Object Tracking
This paper proposes a fast data association technique for tracking multiple objects by using Tracking-by-Detection paradigm with a focus on high-speed performance and proposes a threshold-based greedy algorithm that iteratively finds a locally optimum solution with significantly low computational overhead. Expand
Track to Reconstruct and Reconstruct to Track
This work exploits the 3D motion extracted from dynamic object reconstructions to track objects through long periods of complete occlusion and to recover missing detections, and outperforms all previous approaches for both bounding box and segmentation tracking. Expand
Two-Frame Motion Estimation Based on Polynomial Expansion
A method to estimate displacement fields from the polynomial expansion coefficients is derived and after a series of refinements leads to a robust algorithm that shows good results on the Yosemite sequence. Expand
ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation
A self-supervised refining MOTS (i.e., ReMOTS) framework to improve the performance of Multiple Object Tracking and Segmentation by refinement utilizing adopted appearance features and thresholds that are automatically obtained from statistical information. Expand
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
This work presents a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. Expand
RobMOTS : A Benchmark and Simple Baselines for Robust Multi-Object Tracking and Segmentation
  • In CVPR RVSU Workshop,
  • 2021