AI Paper Atlas

Research map / Detection and segmentation / CNN features

CenterNet Heatmap Propagation for Real-time Video Object Detection

Zhujun Xu, Emir Hrustic, Damien Vivet

ECCV 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 42 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 heatmap propagation (HP)CenterNet ResNet-101 · ImageNet VID valmAP50 (%): 73.6 -> 76.7Improved
add heatmap propagation (HP) with Seq-NMS post-processingCenterNet ResNet-101 · ImageNet VID valmAP50 (%): 75.9 -> 78.4Improved
add heatmap propagation (HP)CenterNet DLA-34 · ImageNet VID valmAP50 (%): 69.1 -> 71.3Improved
add simple interpolation between consecutive-frame outputsCenterNet · ImageNet VID valmAP50 (%): 73.6 -> 73.6No clear effect
add HP (cost: extra runtime)CenterNet · ImageNet VID valFPS: 47 -> 37Hurt
add propagation dilation, P from 0 to 2 (ablation)CenterNet+HP · ImageNet VID valmAP50 (%): 75 -> 76.7Improved
increase dilation size P from 2 to 5 (ablation)CenterNet+HP · ImageNet VID valmAP50 (%): 76.7 -> 75.5Hurt
use larger P for fast-motion objects (P=5 vs P=2) (ablation)CenterNet+HP · ImageNet VID fast motionAP (%): 67.6 -> 68.6Improved
add balance with network heatmap (alpha 0.98 instead of 1) (ablation)CenterNet+HP · ImageNet VID valmAP50 (%): 75.3 -> 76.7Improved
increase alpha from 0.5 to 0.98 (ablation)CenterNet+HP · ImageNet VID valmAP50 (%): 74.6 -> 76.7Improved
add tracklet-length weighting with beta=2 instead of beta=1000 (no length weighting limit) (ablation)CenterNet+HP · ImageNet VID valmAP50 (%): 75 -> 76.7Improved
increase beta from 2 to 100 (ablation)CenterNet+HP · ImageNet VID valmAP50 (%): 76.7 -> 75.1Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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