Strongsort: Make deepsort great again

Y Du, Z Zhao, Y Song, Y Zhao, F Su… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Recently, Multi-Object Tracking (MOT) has attracted rising attention, and accordingly,
remarkable progresses have been achieved. However, the existing methods tend to use …

BoT-SORT: Robust associations multi-pedestrian tracking

N Aharon, R Orfaig, BZ Bobrovsky - arXiv preprint arXiv:2206.14651, 2022 - arxiv.org
The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene,
while keeping a unique identifier for each object. In this paper, we present a new robust …

Bytetrack: Multi-object tracking by associating every detection box

Y Zhang, P Sun, Y Jiang, D Yu, F Weng, Z Yuan… - European conference on …, 2022 - Springer
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in
videos. Most methods obtain identities by associating detection boxes whose scores are …

Motiontrack: Learning robust short-term and long-term motions for multi-object tracking

Z Qin, S Zhou, L Wang, J Duan… - Proceedings of the …, 2023 - openaccess.thecvf.com
The main challenge of Multi-Object Tracking (MOT) lies in maintaining a continuous
trajectory for each target. Existing methods often learn reliable motion patterns to match the …

[HTML][HTML] A review of occluded objects detection in real complex scenarios for autonomous driving

J Ruan, H Cui, Y Huang, T Li, C Wu, K Zhang - Green energy and intelligent …, 2023 - Elsevier
Autonomous driving is a promising way to future safe, efficient, and low-carbon
transportation. Real-time accurate target detection is an essential precondition for the …

Glamr: Global occlusion-aware human mesh recovery with dynamic cameras

Y Yuan, U Iqbal, P Molchanov… - Proceedings of the …, 2022 - openaccess.thecvf.com
We present an approach for 3D global human mesh recovery from monocular videos
recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions …

Human pose estimation using deep learning: review, methodologies, progress and future research directions

P Kumar, S Chauhan, LK Awasthi - International Journal of Multimedia …, 2022 - Springer
Human pose estimation (HPE) has developed over the past decade into a vibrant field for
research with a variety of real-world applications like 3D reconstruction, virtual testing and re …

Quo vadis: Is trajectory forecasting the key towards long-term multi-object tracking?

P Dendorfer, V Yugay, A Osep… - Advances in Neural …, 2022 - proceedings.neurips.cc
Recent developments in monocular multi-object tracking have been very successful in
tracking visible objects and bridging short occlusion gaps, mainly relying on data-driven …

Tracking people by predicting 3d appearance, location and pose

J Rajasegaran, G Pavlakos… - Proceedings of the …, 2022 - openaccess.thecvf.com
We present an approach for tracking people in monocular videos by predicting their future
3D representations. To achieve this, we first lift people to 3D from a single frame in a robust …

Step: Segmenting and tracking every pixel

M Weber, J Xie, M Collins, Y Zhu… - arXiv preprint arXiv …, 2021 - arxiv.org
The task of assigning semantic classes and track identities to every pixel in a video is called
video panoptic segmentation. Our work is the first that targets this task in a real-world setting …