MétaCan
Menu
Back to cohort
Record W3174843313 · doi:10.21467/proceedings.115.22

Instagram Image Filtration with Computer Vision

2021· article· en· W3174843313 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.

Bibliographic record

VenueAIJR Proceedings · 2021
Typearticle
Languageen
FieldComputer Science
TopicFace recognition and analysis
Canadian institutionsConcordia University of Edmonton
Fundersnot available
KeywordsComputer scienceUploadFace (sociological concept)Filter (signal processing)Information retrievalImage (mathematics)Social mediaComputer visionArtificial intelligenceWorld Wide Web

Abstract

fetched live from OpenAlex

Instagram is one of the famous and fast-growing media sharing platforms. Instagram allows users to share photos and videos with followers. There are plenty of ways to search for images on Instagram, but one of the most familiar ways is ’hashtag.’ Hashtag search enables the users to find the precise search result on Instagram. However, there are no rules for using the hashtag; that is why it often does not match the uploaded image, and for this reason, Users are unable to find the relevant search results. This research aims to filter any human face images on search results based on hashtags on Instagram. Our study extends the author’s [2] work by implementing image processing techniques that detect human faces and separate the identified images on search results based on hashtags using the face detection technique.

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)0.000
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: none
Teacher disagreement score0.702
Threshold uncertainty score0.492

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
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 head0.006
GPT teacher head0.221
Teacher spread0.215 · 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