Signals 4 · free daily AI digest

Input Resolution Matters: Real-Time Object Detection Latency

Paper recorded by Signals 4 on 2026-09-11 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14

Category: cs.CV · 计算机视觉 · first seen 2026-09-14

Abstract

We model total latency as the convolution of preprocessing, inference, and postprocessing distributions under a simplifying independence approximation, with selected stage parameters expressed as functions of source-image resolution. Under this assumption, the probability density of the total latency is the convolution of the stage-wise densities, and its cumulative distribution function (CDF) pro

Read on arXiv →

#69 most recent of 237 cs.CV papers we have recorded · ↑ newer: DementiaCare-Bench: A Modality-Validated Video Benchmark · ↓ older: PA-CDM: Position-Aware Character Detection Matching for Evaluating Han
Cite this page: Input Resolution Matters: Real-Time Object Detection Latency: the #69 most recent of 237 cs.CV papers we have recorded (as of 2026-09-11). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/input-resolution-matters-real-time-object-detection-latency.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions