MétaCan
Menu
Back to cohort

A Lightweight Knowledge Distillation Framework for Multi-Target Action Recognition

2025· article· W7131116160 on OpenAlexaff
Z. Zhang, Z. Chen, Z. Xu, Z. Zhou

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicHuman Pose and Action Recognition
Canadian institutionsDalhousie University
FundersFujian Provincial Department of Science and TechnologyNational Natural Science Foundation of China
KeywordsInferenceTransformerSoftware deploymentAction recognitionKey (lock)Knowledge-based systemsDistillationAction (physics)

Abstract

fetched live from OpenAlex

Fast and accurate multi-target action recognition using Frequency Modulated Continuous Wave (FMCW) radar is a significant challenge for real-time applications. To address this, we propose a lightweight dual-input network named Quickly Identify Multi-Target Action Network (QIMTA). Built upon the MobileViT2 architecture, our model is trained via a knowledge distillation framework, utilizing a Swin Transformer as the teacher model. This design enables the parallel recognition of separated Range-Doppler maps, significantly enhancing computational efficiency. Experimental results demonstrate that QIMTA achieves 93.49% recognition accuracy with an inference speed of only 5.62 ms, demonstrating its high efficiency and effectiveness for deployment on edge devices.

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 categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.910
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0000.000
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0010.001

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 head0.102
GPT teacher head0.366
Teacher spread0.263 · 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.

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 topicHuman Pose and Action RecognitionFrench-language works237,207