MétaCan
Menu
Back to cohort
Record W4405179107 · doi:10.1109/tmc.2024.3514214

Joint Encoding and Enhancement for Low-Light Video Analytics in Mobile Edge Networks

2024· article· en· W4405179107 on OpenAlexaff
Yuanyi He, Peng Yang, Ning Zhang

Bibliographic record

VenueIEEE Transactions on Mobile Computing · 2024
Typearticle
Languageen
FieldComputer Science
TopicImage and Video Quality Assessment
Canadian institutionsUniversity of Windsor
FundersNational Natural Science Foundation of China
KeywordsComputer scienceJoint (building)AnalyticsEncoding (memory)Enhanced Data Rates for GSM EvolutionMobile telephonyComputer networkTelecommunicationsArtificial intelligenceMobile radioData science

Abstract

fetched live from OpenAlex

In this paper, we present our design and analysis of a Joint Encoding and Enhancement (JEE) system for low-light video analytics in mobile edge networks. First, it is observed that, relying solely on a single pipeline for encoding and enhancement of mobile videos proves insufficient, because of the fluctuations in end-edge bandwidth and computing resources. Therefore, two distinct pipelines are introduced in the JEE system, namely, the encode-decode-enhance pipeline and the enhance-encode-decode pipeline. We then characterize the relationship of accuracy, transmission overhead, and computing overhead of these two pipelines through extensive experiments. Considering the significant demands of transmission and computing for low-light videos, we formulate an optimization problem to strike a balance between accuracy and delay, where the available end-edge bandwidth and computing resources are unknown in advance. To solve this mixed-integer nonlinear programming problem, we propose an algorithm based on online gradient descent, enabling adaptive pipeline selection and joint encoding and enhancement configuration. Theoretical analysis indicates that the proposed algorithm achieves sub-linear dynamic regret, highlighting its capability to the accuracy improvement and delay reduction in online environments. Experimental comparison against baselines demonstrates that, JEE can achieve up to a 27.32% increase in accuracy and a 26.18% reduction in delay.

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)0.001
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: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.967
Threshold uncertainty score0.907

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
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 head0.027
GPT teacher head0.308
Teacher spread0.280 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
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

Citations6
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Mobile ComputingSame topicImage and Video Quality AssessmentFrench-language works237,207