LQTTrack: Multi-Object Tracking by Focusing on Low-Quality Targets Association
Source abstract
Abstract
Multi-object tracking (MOT) has seen rapid improvements in recent years. However, frequent occlusion remains a significant challenge in MOT, as it can cause targets to become smaller or disappear entirely, resulting in low-qu... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Advanced Computing and Algorithms · Fire Detection and Safety Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (47)
Show source-provided references
1. Deep learning in visual tracking: A review10.1109/TNNLS.2021.3136907 ↗
2. Multi-object tracking: A systematic literature review10.1007/s11042-023-17297-3 ↗
3. Simple online and realtime tracking
4. Simple online and realtime tracking with a deep association metric
5. ByteTrack: Multi object tracking by associating every detection box
6. StrongSORT: Make deepsort great again10.1109/TMM.2023.3240881 ↗
7. Chained-tracker: Chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking
8. FairMOT: On the fairness of detection and re-identification in multiple object tracking10.1007/s11263-021-01513-4 ↗
9. N. Aharon, R. Orfaig, and B. -Z. Bobrovsky, “BoT-SORT: Robust associations multi-pedestrian tracking,” 2022, arXiv:2206.14651.
10. Deep OC-SORT: Multi-pedestrian tracking by adaptive re-identification
11. Multiple hypothesis tracking revisited
12. Iterative multiple hypothesis tracking with tracklet-level association10.1109/TCSVT.2018.2881123 ↗
13. Feature pyramid networks for object detection
14. J. Wang, C. Xu, W. Yang, and L. Yu, “A normalized gaussian wasserstein distance for tiny object detection,” 2021, arXiv:2110.13389.
15. Y. Xu, Y. Ban, G. Delorme, C. Gan, D. Rus and X. Alameda-Pineda, “TransCenter: Transformers with dense queries for multiple-object tracking,” 2021, arXiv:2103.15145.
16. Observation-centric SORT: Rethinking sort for robust multi-object tracking
17. A. Milan, L. Leal-Taixé, I. Reid, S. Roth, and K. Schindler, “MOT16: A benchmark for multi-object tracking,” 2016, arXiv:1603.00831.
18. P. Dendorfer et al., “MOT20: A benchmark for multi object tracking in crowded scenes,” 2020, arXiv:2003.09003.
19. DanceTrack: Multi-object tracking in uniform appearance and diverse motion
20. A survey of detection-based video multi-object tracking10.1016/j.displa.2022.102317 ↗
21. SimpleTrack: Understanding and rethinking 3D multi-object tracking
22. Bag of tricks and a strong baseline for deep person re-identification
23. Omni-scale feature learning for person re-identification
24. Simple cues lead to a strong multi-object tracker
25. Modelling ambiguous assignments for multi-person tracking in crowds
26. UCMCTrack: Multi-object tracking with uniform camera motion compensation
27. Monocular quasi-dense 3D object tracking10.1109/TPAMI.2022.3168781 ↗
28. QDTrack: Quasi-dense similarity learning for appearance-only multiple object tracking10.1109/TPAMI.2023.3301975 ↗
29. Toward real-time UAV multi-target tracking using joint detection and tracking10.1109/ACCESS.2023.3283411 ↗
30. Transformer-based assignment decision network for multiple object tracking10.1016/j.cviu.2024.103957 ↗
31. Detection recovery in online multi-object tracking with sparse graph tracker
32. Labeled random finite sets and multi-object conjugate priors10.1109/TSP.2013.2259822 ↗
33. Resolvable cluster target tracking based on the DBSCAN clustering algorithm and labeled RFS10.1109/ACCESS.2021.3066629 ↗
34. Visual multi-object tracking with re-identification and occlusion handling using labeled random finite sets
35. Generalized intersection over union: A metric and a loss for bounding box regression
36. MOTFR: Multiple object tracking based on feature recoding10.1109/TCSVT.2022.3182709 ↗
37. Near-online multi-pedestrian tracking via combining multiple consistent appearance cues10.1109/TCSVT.2020.3005662 ↗
38. ResNeSt: Split-attention networks
39. Detecting tiny objects in aerial images: A normalized wasserstein distance and a new benchmark10.1016/j.isprsjprs.2022.06.002 ↗
40. RelationTrack: Relation-aware multiple object tracking with decoupled representation
41. Multiple object tracking with correlation learning
42. TransMOT: Spatial-temporal graph transformer for multiple object tracking
43. Evaluating multiple object tracking performance: The clear mot metrics10.1155/2008/246309 ↗
44. HOTA: A higher order metric for evaluating multi-object tracking10.1007/s11263-020-01375-2 ↗
45. Performance measures and a data set for multi-target, multi-camera tracking
46. L. He, X. Liao, W. Liu, X. Liu, P. Cheng and T. Mei, “FastReID: A pytorch toolbox for general instance re-identification,” 2020, arXiv:2006.02631.
47. Tracking objects as points