English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The proliferation of camera-enabled devices and large video repositories hasled to a diverse set of video analytics applications. These applications relyon video pipelines, represented as DAGs of operations, to transform videos,process extracted metadata, and answer questions like, "Is this intersectioncongested?" The latency and resource efficiency of pipelines can be optimizedusing configurable knobs for each operation (e.g., sampling rate, batch size,or type of hardware used). However, determining efficient configurations ischallenging because (a) the configuration search space is exponentially large,and (b) the optimal configuration depends on users' desired latency and costtargets, (c) input video contents may exercise different paths in the DAG andproduce a variable amount intermediate results. Existing video analytics andprocessing systems leave it to the users to manually configure operations andselect hardware resources.  We present Llama: a heterogeneous and serverless framework for auto-tuningvideo pipelines. Given an end-to-end latency target, Llama optimizes for costefficiency by (a) calculating a latency target for each operation invocation,and (b) dynamically running a cost-based optimizer to assign configurationsacross heterogeneous hardware that best meet the calculated per-invocationlatency target. This makes the problem of auto-tuning large video pipelinestractable and allows us to handle input-dependent behavior, conditionalbranches in the DAG, and execution variability. We describe the algorithms inLlama and evaluate it on a cloud platform using serverless CPU and GPUresources. We show that compared to state-of-the-art cluster and serverlessvideo analytics and processing systems, Llama achieves 7.8x lower latency and16x cost reduction on average.

Llama: A Heterogeneous & Serverless Framework for Auto-Tuning Video Analytics Pipelines