A survey on graph neural networks and graph transformers in computer vision: A task-oriented perspective

C Chen, Y Wu, Q Dai, HY Zhou, M Xu… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Graph Neural Networks (GNNs) have gained momentum in graph representation learning
and boosted the state of the art in a variety of areas, such as data mining (eg, social network …

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 …

Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection

J Liu, X Fan, Z Huang, G Wu, R Liu… - Proceedings of the …, 2022 - openaccess.thecvf.com
This study addresses the issue of fusing infrared and visible images that appear differently
for object detection. Aiming at generating an image of high visual quality, previous …

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 …

Trackformer: Multi-object tracking with transformers

T Meinhardt, A Kirillov, L Leal-Taixe… - Proceedings of the …, 2022 - openaccess.thecvf.com
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about
track initialization, identity, and spatio-temporal trajectories. We formulate this task as a …

Hota: A higher order metric for evaluating multi-object tracking

J Luiten, A Osep, P Dendorfer, P Torr, A Geiger… - International journal of …, 2021 - Springer
Multi-object tracking (MOT) has been notoriously difficult to evaluate. Previous metrics
overemphasize the importance of either detection or association. To address this, we …

Fairmot: On the fairness of detection and re-identification in multiple object tracking

Y Zhang, C Wang, X Wang, W Zeng, W Liu - International journal of …, 2021 - Springer
Multi-object tracking (MOT) is an important problem in computer vision which has a wide
range of applications. Formulating MOT as multi-task learning of object detection and re-ID …

Observation-centric sort: Rethinking sort for robust multi-object tracking

J Cao, J Pang, X Weng… - Proceedings of the …, 2023 - openaccess.thecvf.com
Kalman filter (KF) based methods for multi-object tracking (MOT) make an assumption that
objects move linearly. While this assumption is acceptable for very short periods of …

Towards real-time multi-object tracking

Z Wang, L Zheng, Y Liu, Y Li, S Wang - European conference on computer …, 2020 - Springer
Modern multiple object tracking (MOT) systems usually follow the tracking-by-detection
paradigm. It has 1) a detection model for target localization and 2) an appearance …

Track to detect and segment: An online multi-object tracker

J Wu, J Cao, L Song, Y Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Most online multi-object trackers perform object detection stand-alone in a neural net without
any input from tracking. In this paper, we present a new online joint detection and tracking …