MétaCan
Menu
Back to cohort
Record W3128273207 · doi:10.1007/s00371-020-02047-5

A deep learning computer vision iPad application for Sales Rep optimization in the field

2021· article· en· W3128273207 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueThe Visual Computer · 2021
Typearticle
Languageen
FieldComputer Science
TopicImage and Video Quality Assessment
Canadian institutionsSheridan College
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsUsabilityComputer scienceVariety (cybernetics)Field (mathematics)Identification (biology)Set (abstract data type)Product (mathematics)Human–computer interactionComputer graphicsMultimediaArtificial intelligence

Abstract

fetched live from OpenAlex

Abstract Computer vision is becoming an increasingly critical area of research, and its applications to real-world problems are gaining significance. In this paper, we describe the design, development and evaluation of our computer vision Faster R-CNN iPad App for Sales Representatives in grocery store environments. Our system aims to assist Sales Reps to be more productive, reduce errors, and provide increased efficiencies. We report on the creation of the iPad app, the data capturing guidelines we created for the creation of good classifiers and the results of professional Sales Reps evaluating our system. Our system was tested in a variety of conditions in grocery store environments and has an accuracy of 99%, a System Usability Score usability score of 85 (high). It supports up to 40 classifiers running concurrently to perform product identification in less than 3.8 s. We also created a set of data capturing guidelines that will enable other researchers to create their own classifiers for these types of products in complex environments (e.g., products with very similar packaging located on shelves).

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.

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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.647
Threshold uncertainty score0.371

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 science0.0010.000
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 head0.021
GPT teacher head0.360
Teacher spread0.339 · 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