MétaCan
Menu
Back to cohort
Record W4394597978 · doi:10.1109/csce60160.2023.00343

Techniques for Achieving High Performance in Deep Learning Based Systems for Selective Filtering of Live Video Streams

2023· article· en· W4394597978 on OpenAlexaff
Azhar Talha Syed, Shikharesh Majumdar

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicImage and Signal Denoising Methods
Canadian institutionsCarleton University
Fundersnot available
KeywordsSTREAMSComputer scienceDeep learningData stream miningReal-time computingArtificial intelligenceMachine learningComputer network

Abstract

fetched live from OpenAlex

The research focuses on applications of parallel and distributed processing techniques and deep learning for filtering frames from live video streaming data based on a set of criteria specified by the user. With various video streaming sources around the world, storing the entire video streams and searching the stored data is computationally expensive. A video stream filtering system keeps the frames of interest and discards the rest for fast search and retrieval as well as reduction of storage space. This research concerns the devising of filtering techniques for streaming video data. Parallel and distributed processing techniques including frameworks like Apache Kafka integrated with TensorFlow are used to devise the proposed scalable real-time filtering prototypes. Initial research results that include experiments with live video streams from webcams were conducted on Amazon EC2 cloud to gain insights into system performance including the reduction in processing time that accrues from applying the proposed techniques.

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)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.003
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0040.001

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 head0.022
GPT teacher head0.283
Teacher spread0.261 · 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 designBench or experimental
Domainnot available
GenreEmpirical

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
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicImage and Signal Denoising MethodsFrench-language works237,207