Research map / Detection and segmentation / Tracking
An HMM-Based Framework for Identity-Aware Long-Term Multi-Object Tracking From Sparse and Uncertain Identification: Use Case on Long-Term Tracking in Livestock
Anne Marthe Sophie Ngo Bibinbe, Chiron Bang, Patrick James Gagnon, Jamie Ahloy Dallaire, Éric R. Paquet
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add HMM identity framework (forward-backward plus Hungarian) to ByteTrack | ByteTrack · 10-min pig tracking (15 pigs, 21 feeder IDs) | Micro-F1: 0.48 -> 0.67 | Improved |
| add HMM framework instead of simple Re-ID correction | ByteTrack+Re-ID · 10-min pig tracking (15 pigs, 21 feeder IDs) | Micro-F1: 0.50 -> 0.67 | Improved |
| add HMM framework instead of simple Re-ID | ByteTrack+Re-ID · 10-min pig tracking (15 pigs, 21 feeder IDs) | Micro-Precision: 0.51 -> 0.75 | Improved |
| add HMM framework | ByteTrack · 10-min pig tracking (15 pigs, 21 feeder IDs) | I-FN: 291 -> 1642 | Hurt |
| add Re-ID correction to ByteTrack | ByteTrack · 10-min pig tracking (15 pigs, 21 feeder IDs) | Micro-F1: 0.48 -> 0.50 | No clear effect |
| increase number of identifications beyond about 8 | ByteTrack+HMM · 10-min pig tracking (artificial identifications) | F1 | Improved |
| add 25% random observations on MOT17/MOT20 with more identifications (ablation) | ByteTrack+Re-ID / FairMOT+Re-ID · MOT17 and MOT20 (artificial IDs) | F1 | Hurt |
| filter misleading identifications (IOU 0.7, probability above 0.5) (ablation) | ByteTrack+HMM / FairMOT+HMM · MOT17 and MOT20 (artificial IDs) | F1 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ByteTrack — ByteTrack: Multi-Object Tracking by Associating Every Detection Box (ECCV 2022) · better on 5 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild (IJCV 2022 · similarity 0.87)
- APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking (NeurIPS 2022 · similarity 0.85)
- Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding (NeurIPS 2024 · similarity 0.83)
- NetTrack: Tracking Highly Dynamic Objects with a Net (CVPR 2024 · similarity 0.83)
- BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes (NeurIPS 2024 · similarity 0.83)
- Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
