Pith. sign in

REVIEW 25 cited by

MOT20: A benchmark for multi object tracking in crowded scenes

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 2003.09003 v1 pith:LU2AQ2EX submitted 2020-03-19 cs.CV

Patrick Dendorfer , Hamid Rezatofighi , Anton Milan , Javen Shi , Daniel Cremers , Ian Reid , Stefan Roth , Konrad Schindler
show 1 more author
Laura Leal-Taixé
This is my paper · ORCID
classification cs.CV
keywords trackingbenchmarkmultipleobjectcrowdedbenchmarkschallengecommunity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods. The challenge focuses on multiple people tracking, since pedestrians are well studied in the tracking community, and precise tracking and detection has high practical relevance. Since the first release, MOT15, MOT16, and MOT17 have tremendously contributed to the community by introducing a clean dataset and precise framework to benchmark multi-object trackers. In this paper, we present our MOT20benchmark, consisting of 8 new sequences depicting very crowded challenging scenes. The benchmark was presented first at the 4thBMTT MOT Challenge Workshop at the Computer Vision and Pattern Recognition Conference (CVPR) 2019, and gives to chance to evaluate state-of-the-art methods for multiple object tracking when handling extremely crowded scenarios.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 25 Pith papers

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

  1. Higher-Order Cell Tracking Transformer

    cs.CV 2026-07 accept novelty 6.0 of 10

    An edge-centric Transformer with line-to-line geometric attention achieves SOTA cell lineage tracking without pretrained image encoders and fine-tunes far more efficiently than node-embedding baselines.

  2. WaspMOT: A Benchmark for Long-Term Multi-Object Tracking of Trichogramma Wasps

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A new insect-tracking benchmark reveals that five standard MOT methods suffer severe identity fragmentation on 8-minute sequences even with oracle detections, with simple spatial stitching recovering significant gains.

  3. Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Polycepta recursively estimates per-object appearance states so visual cues improve over time, reducing identity switches and lifting tracking-by-detection performance at real-time speed.

  4. COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm

    cs.CV 2026-03 conditional novelty 6.0 of 10

    Continuous TAO annotations plus multi-cue fusion, hierarchical aggregation, and temporal confidence propagation raise novel TETA to 35.4%/30.5% on TAO val/test.

  5. Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods

    cs.CV 2026-01 conditional novelty 6.0 of 10

    GD3A and DVTrack, driven by optimal-transport descriptor matching with an adaptive dustbin score, set state-of-the-art results on a new moving-drone dense-crowd counting and tracking benchmark.

  6. Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework

    cs.CV 2026-01 reject novelty 6.0 of 10

    A new LLM-generated dataset and an MLLM-based tracker claim state-of-the-art semantic multi-object tracking, but the evaluation protocol masks missed objects and ID switches.

  7. MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost

    cs.CV 2025-09 conditional novelty 6.0 of 10

    An end-to-end multi-view pedestrian tracker that aggregates motion and appearance costs over K past timestamps, outperforming prior methods on GMVD, Wildtrack, and MultiviewX, though with a validation-protocol concern...

  8. To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A taxonomy that classifies unified perception methods in autonomous driving into Early, Late, and Full Unified Perception based on task integration, tracking formulation, and representation flow.

  9. GRASPTrack: Geometry-Reasoned Association via Segmentation and Projection for Multi-Object Tracking

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A depth-aware MOT tracker using mask-guided 3D point clouds, voxelized 3D IoU association, adaptive Kalman noise, and 3D motion consistency surpasses prior TBD methods on MOT17, MOT20, and DanceTrack.

  10. RoundaboutHD: High-Resolution Real-World Urban Environment Benchmark for Multi-Camera Vehicle Tracking

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A high-resolution, real-world roundabout dataset for multi-camera vehicle tracking, with 512 identities, four non-overlapping 4K cameras, and baselines across four tasks.

  11. USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A new USV dataset combining 4D radar, camera, GPS, and IMU data for tracking boats, ships, and vessels on inland waterways, together with a radar-camera matching method that consistently improves two-stage trackers.

  12. Progressive Scaling Visual Object Tracking

    cs.CV 2025-05 reject novelty 6.0 of 10

    A progressive scaling training strategy with small-teacher distillation and masked-input alignment improves tracking accuracy and powers a new 12-dataset benchmark.

  13. Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A BEVFusion-based offboard tracker with density-aware loss weighting, nearest-neighbor relationship targets, and high-resolution sparse features doubles MOTA on a new crowded-pedestrian benchmark (PCP-MV) from 0.172 to 0.353.

  14. Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding

    cs.CV 2025-09 conditional novelty 5.0 of 10

    SIKNet, a learned Kalman filter with a semantic-independent encoder, improves bounding-box motion prediction in multi-object tracking over the classic Kalman filter and prior KalmanNet variants.

  15. MeMoSORT: Memory-Assisted Filtering and Motion-Adaptive Association Metric for Multi-Person Tracking

    cs.CV 2025-08 conditional novelty 5.0 of 10

    MeMoSORT reports state-of-the-art multi-person tracking HOTA of 67.9% on DanceTrack and 82.1% on SportsMOT by combining a memory-compensated Kalman filter with a motion-adaptive IoU association metric.

  16. Head Anchor Enhanced Detection and Association for Crowded Pedestrian Tracking

    cs.CV 2025-08 reject novelty 5.0 of 10

    FocusTrack, a YOLOX-based tracker using head keypoints and detector features, matches but does not beat simple baselines on MOT17 and MOT20, and its 3D trajectory completion underperforms 2D interpolation.

  17. CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios

    cs.CV 2025-07 conditional novelty 5.0 of 10

    CrowdTrack is a dense, first-person-view pedestrian tracking benchmark that exposes large performance drops in existing multi-object trackers.

  18. Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Multi-frame early fusion with single-frame supervision improves YOLOv7-tiny detection on MOT20Det and a new BOAT360 fisheye dataset.

  19. 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.

  20. Glance-MCMT: A General MCMT Framework with Glance Initialization and Progressive Association

    cs.CV 2025-07 conditional novelty 4.0 of 10

    Glance-MCMT combines BoT-SORT single-camera tracks, a short glance phase to seed global IDs, and progressive cross-view association, reaching 51.34 HOTA on AI City 2025 validation data.

  21. LazyVLM: Neuro-Symbolic Approach to Video Analytics

    cs.DB 2025-05 reject novelty 4.0 of 10

    LazyVLM decomposes multi-frame video queries into vector-search entity matching, SQL-style relationship lookup, and lightweight VLM refinement, but provides no experimental evaluation of its claims.

  22. Incremental Optimal Assignment for Real-Time Crowd Tracking

    cs.CV 2026-07 conditional novelty 3.0 of 10

    An incremental assignment solver with warm-started dual potentials claims 1.1–6.5× speedups over Hungarian on synthetic block-sparse crowd matrices, with the headline 3.7–6.5× range not matching its own data.

  23. A Framework for Multi-View Multiple Object Tracking using Single-View Multi-Object Trackers on Fish Data

    cs.CV 2025-05 reject novelty 3.0 of 10

    A YOLOv8-ByteTrack pipeline plus stereo triangulation can produce 3D fish tracks for some underwater video pairs, but the claimed multi-view accuracy improvement is not demonstrated.

  24. A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects

    cs.CV 2025-06 conditional novelty 2.0 of 10

    A comprehensive survey of video scene parsing that organizes methods, datasets, metrics, and benchmark results across VSS, VIS, VPS, VTS, and OVVS.

  25. Trajectory Prediction in Dynamic Object Tracking: A Critical Study

    cs.CV 2025-06 conditional novelty 1.0 of 10

    A survey of dynamic object tracking and trajectory prediction that identifies gaps and proposes a conceptual feedback-loop integration, but presents no formal model or experimental validation.

Pith tools