AI Paper Atlas

Research map / Detection and segmentation / CNN features

A Delay Metric for Video Object Detection: What Average Precision Fails to Tell

Huizi Mao, Xiaodong Yang, William J. Dally

ICCV 2019 · Detection and segmentation › CNN features · approach: Box regression and loss design · 54 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add flow-guided feature aggregation (FGFA)R-FCN ResNet-101 · VIDTmAP: 0.642 -> 0.675Improved
add flow-guided feature aggregation (FGFA)R-FCN ResNet-101 · VIDTaverage delay (AD): 9.0 -> 10.2Hurt
aggregate more frames in FGFAFGFA · VIDTmAP and ADMixed
use sparse key frames (DFF, 1 in 10) instead of per-frame R-FCN half modelR-FCN · VIDTaverage delay (AD): 11.2 -> 11.6Hurt
add tracker-driven cascade (CaTDet)Faster R-CNN ResNet-50 · VIDTaverage delay (AD): 8.2 -> 9.2Hurt
add tracker-driven cascade (CaTDet)Faster R-CNN ResNet-50 · VIDTmAP: 0.561 -> 0.555No clear effect
increase anchor scales from 2 to 3 (ablation)Faster R-CNN ResNet-50 · VIDTaverage delay (AD), overall: 9.9 -> 8.8Improved
increase anchor scales from 3 to 4 (add small scale) (ablation)Faster R-CNN ResNet-50 · VIDTaverage delay (AD), overall: 8.8 -> 8.2Improved
increase anchor scales from 3 to 4 (ablation)Faster R-CNN ResNet-50 · VIDTmAP: 0.563 -> 0.562No clear effect
increase anchor scales from 4 to 5 (ablation)Faster R-CNN ResNet-50 · VIDTaverage delay (AD), overall: 8.2 -> 8.4No clear effect
retard first 5 detections of every instance (all detections)R-FCN ResNet-101 · VIDT toy caseaverage delay (AD): 9.0 -> 13.8Hurt
tail boost: elevate confidence of late detectionsR-FCN ResNet-101 · VIDT toy caseaverage delay (AD): 9.0 -> 8.9No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy