MétaCan
Menu
Back to cohort

HSMR: A Head-Shoulder Mask Aided ResNet to Guide Focus of Re-Identification Implemented on Tour-Guide Robot

2022· article· en· W4317383319 on OpenAlexaff
Zheyuan Lin, Min Huang, Wen Wang, Mengjie Qin, Te Li, Minhong Wan, Jason Gu, Shiqiang Zhu

Bibliographic record

Venue2022 IEEE International Conference on Robotics and Biomimetics (ROBIO) · 2022
Typearticle
Languageen
FieldComputer Science
TopicVideo Surveillance and Tracking Methods
Canadian institutionsDalhousie University
Fundersnot available
KeywordsTask (project management)RobotComputer scienceIdentification (biology)Artificial intelligenceInferenceComputer visionEngineeringBiologySystems engineering

Abstract

fetched live from OpenAlex

For service robots, person re-identification (ReID) and multi-pedestrian tracking (MPT) are vital to get a person's location and link identities across frames. Though their accuracy keeps improving, most work lacks consideration of the application scenario, haunted by limited space, constrained power supply, and demands of the real-time response during human-robot interaction. Some ReID models learn trivial or unrelated features, inhibiting the downstream tasks. To solve these issues, the efficient and light-weighted Head-Shoulder Mask aided ResNet (HSMR) is proposed. This model applies multi-task learning to enhance the feature extraction performance in the training stage without extra computational load during inference. The auxiliary task fully uses head-shoulder information to guide the network and focuses on the head region, which contains the identity information. In experiments on the Tour-Guide Robot Data Base (TGRDB), HSMR earned results better than ResNet-18 on the ReID task and was superior to the recent two-stream method on the MPT task. On the mobile hardware, inference reaches an average of 15.2 FPS, three times faster than the two-stream method. The code is released at https://github.com/ZhYLin99/HSMR.

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)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.923
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
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 head0.092
GPT teacher head0.382
Teacher spread0.290 · 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 designSimulation or modeling
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
Published2022
Admission routes1
Has abstractyes

Explore more

Same venue2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)Same topicVideo Surveillance and Tracking MethodsFrench-language works237,207