AI Paper Atlas

Research map / Detection and segmentation / CNN features

Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation

Tao Song, Leiyu Sun, Di Xie, Haiming Sun, Shiliang Pu

ECCV 2018 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 234 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 MRF-based matching post-processing (ablation)TLL · Caltech Farmiss rate (%): 68.03 -> 67.69Improved
add MRF-based matching post-processing (ablation)TLL · Caltech Middlemiss rate (%): 26.25 -> 25.55Improved
add MRF-based matching post-processing (ablation)TLL · Caltech Allmiss rate (%): 39.99 -> 39.12Improved
add MRF-based matching post-processing (ablation)TLL · Caltech Reasonablemiss rate (%): 8.45 -> 8.01Improved
add MRF-based matching post-processing (ablation)TLL · CityPersons Heavymiss rate (%): 53.6 -> 52.0Improved
add MRF-based matching post-processing (ablation)TLL · CityPersons Reasonablemiss rate (%): 15.5 -> 14.4Improved
add MRF-based matching post-processing (ablation)TLL · CityPersons Baremiss rate (%): 10.0 -> 9.2Improved
add Conv-LSTM temporal feature aggregation (ablation)TLL(MRF) · Caltech Farmiss rate (%): 67.69 -> 60.79Improved
add Conv-LSTM temporal feature aggregation (ablation)TLL(MRF) · Caltech Allmiss rate (%): 39.12 -> 37.62Improved
add Conv-LSTM temporal feature aggregation (ablation)TLL(MRF) · Caltech Nearmiss rate (%): 0.67 -> 0.72Hurt
use Conv-LSTM instead of FGFA for temporal aggregation (ablation)TLL(MRF) · Caltech Farmiss rate (%): 63.28 -> 60.79Improved
stack two or more Conv-LSTM layers (ablation)TLL+Conv-LSTM · Caltechmiss rate (%)No 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