Pith. sign in

REVIEW 10 cited by

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.06864 v3 pith:KARUZCMO submitted 2021-10-13 cs.CV

Yifu Zhang , Peize Sun , Yi Jiang , Dongdong Yu , Fucheng Weng , Zehuan Yuan , Ping Luo , Wenyu Liu
show 1 more author
Xinggang Wang
This is my paper
classification cs.CV
keywords detectionbytetrackobjectstrackingassociatingboxesscorestate-of-the-art
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 higher than a threshold. The objects with low detection scores, e.g. occluded objects, are simply thrown away, which brings non-negligible true object missing and fragmented trajectories. To solve this problem, we present a simple, effective and generic association method, tracking by associating almost every detection box instead of only the high score ones. For the low score detection boxes, we utilize their similarities with tracklets to recover true objects and filter out the background detections. When applied to 9 different state-of-the-art trackers, our method achieves consistent improvement on IDF1 score ranging from 1 to 10 points. To put forwards the state-of-the-art performance of MOT, we design a simple and strong tracker, named ByteTrack. For the first time, we achieve 80.3 MOTA, 77.3 IDF1 and 63.1 HOTA on the test set of MOT17 with 30 FPS running speed on a single V100 GPU. ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks. The source code, pre-trained models with deploy versions and tutorials of applying to other trackers are released at https://github.com/ifzhang/ByteTrack.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    Formalizes suicide risk assessment (SRA) from metro videos and benchmarks an interpretable pipeline with 83.2% ROC-AUC using tracking, activity recognition, segmentation, and risk heatmaps.

  2. Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Introduces the first interpretable framework for suicide risk assessment (SRA) from metro station surveillance videos, achieving 83.2% ROC-AUC via person tracking, activity recognition, semantic segmentation, and traj...

  3. Efficient Perception in Automotive Detection and Tracking Using Neuromorphic Computing

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Transfer-learned SpikeYOLO achieves mAP 0.937/0.771 and HOTA 0.701/0.445 on KITTI and BDD100K for two-class automotive detection and tracking, competitive with conventional deep networks.

  4. Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    Kairos is a native world model stack using cross-embodiment pretraining, hybrid linear temporal attention with theoretical error bounds, and deployment-aware co-design, reporting top performance on embodied benchmarks.

  5. Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI

    cs.AI 2026-06 conditional novelty 5.0 of 10

    Kairos learns and maintains control-sufficient world states via a cross-embodiment curriculum, hybrid linear temporal attention, and deployment-aware co-design for Physical AI.

  6. Time-series Meets Complex Motion Modeling: Robust and Computational-effective Motion Predictor for Multi-object Tracking

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    TCMP achieves SOTA MOT metrics (HOTA 63.4%, IDF1 65.0%, AssA 49.1%) with 0.014x parameters and 0.05x FLOPs of the previous best method by using a simple dilated TCN regressor.

  7. Occlusion-Aware Multi-Object Tracking via Expected Probability of Detection

    eess.SY 2025-11 unverdicted novelty 5.0 of 10

    The paper derives an occlusion-aware multi-object tracking method that assigns each object an expected detection probability over the reduced Palm density within a multi-Bernoulli mixture filter.

  8. Design Insights and Comparative Evaluation of a Hardware-Based Cooperative Perception Architecture for Lane Change Prediction

    cs.AI 2025-09 conditional novelty 5.0 of 10

    A hardware cooperative lane-change prediction system is demonstrated with component benchmarks, but the end-to-end 4-second prediction benefit lacks direct output traces and repeated trials.

  9. YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A YOLOv8 detector trained on overlapping slices plus an OC-SORT tracker with EMA motion direction and expanded IoU distance penalty achieves 55.205 SO-HOTA on the SMOT4SB public test set.

  10. CD-TWINSAFE: A ROS-enabled Digital Twin for Scene Understanding and Safety Emerging V2I Technology

    cs.CV 2026-01 unverdicted novelty 3.0 of 10

    A ROS-enabled V2I digital twin architecture integrates on-board stereo perception with an Unreal Engine 5 replica to deliver real-time safety monitoring for autonomous vehicles.

Pith tools