MétaCan
Menu
Back to cohort
Record W30174891 · doi:10.21037/jtd.2018.06.23

Modeling Video Data for Content Based Queries: Extending the DISIMA Image Data Model

2003· article· en· W30174891 on OpenAlexaff
Lei Chen, M. TAMER ÖZSU, Vincent Oria

Bibliographic record

VenueConference on Multimedia Modeling · 2003
Typearticle
Languageen
FieldComputer Science
TopicVideo Analysis and Summarization
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsComputer scienceVideo trackingVideo compression picture typesVideo post-processingSemantics (computer science)Key (lock)SalientData model (GIS)Data modelingData setComputer visionSmacker videoSet (abstract data type)Artificial intelligenceInformation retrievalVideo processingDatabase

Abstract

fetched live from OpenAlex

We present an efficient video data model that extends the DISIMA image data model by adding the video components and setting up links between image and video data. Many video data models have been proposed, most of which describe video data independently of image data and therefore fail to consider the relationship between videos and images. Our proposed model expresses the semantics of video data content by means of salient objects and relationships among them. Connections between video data and DISIMA images are made through key frames, which are extracted from each shot. Based on these connections, techniques used to query image data may be used to query video data. In addition, a set of new predicates has been defined to describe the spatio-temporal characteristics of salient objects in the video data. MOQL is used as a query language, with which we present example queries that can be posed on the proposed video data model.. 1

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.012
Version: metacan-v3-hybrid-931329e0061cValidation 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: Methods
Teacher disagreement score0.019
Threshold uncertainty score0.038

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.012
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0000.000
Scholarly communication0.0020.003
Open science0.0020.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

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 head0.344
GPT teacher head0.353
Teacher spread0.009 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
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

Citations17
Published2003
Admission routes1
Has abstractyes

Explore more

Same venueConference on Multimedia ModelingSame topicVideo Analysis and SummarizationFrench-language works237,207