MétaCan
Menu
Back to cohort
Record W4410907419 · doi:10.21428/d82e957c.322c472b

Attention-Mamba for Multi-Object Tracking

2025· article· en· W4410907419 on OpenAlexaff
Dheeraj Khanna, John Zelek

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicVideo Surveillance and Tracking Methods
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsObject (grammar)Tracking (education)Computer scienceComputer visionArtificial intelligencePsychology

Abstract

fetched live from OpenAlex

Multi-Object Tracking (MOT) is fundamental to applications such as autonomous driving, video surveillance, and sports analytics. However, challenges persist in maintaining long-term identity associations, handling dynamic object counts, managing irregular motion patterns, and mitigating occlusions in complex environments. Inspired by advancements in state-space models (SSMs), particularly Mamba [1], we propose a novel learning-based motion prediction architecture that integrates Mamba’s input-dependent sequence modeling with self-attention layers to effectively capture non-linear motion patterns within the Tracking-By-Detection (TBD) framework. Mamba’s ability to model long-range dependencies enhances motion prediction. We further refine spatial association by improving the cost matrix traditionally based on Intersection over Union (IoU). We incorporate Height-based IoU and extend bounding boxes using adjusted buffers to account for fast motion and partial overlaps, increasing robustness in object association. Achieving accurate MOT requires a balance between precise motion modeling and effective spatial and appearance matching, leveraging both strong and weak cues in data association. Our method is evaluated on challenging benchmarks, such as DanceTrack [2] and SportsMOT [3], achieving HOTA scores of 63.16% and 77.26%, respectively. These results surpass multiple state-of-the-art methods with a 3-7% improvement over other learning-based motion models, demonstrating the effectiveness of our approach in real-world tracking scenarios.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.739
Threshold uncertainty score0.317

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.061
GPT teacher head0.371
Teacher spread0.311 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicVideo Surveillance and Tracking MethodsFrench-language works237,207