AI Paper Atlas

Research map / Point clouds / Point cloud classification

Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition

Yukun Su, Guosheng Lin, Jinhui Zhu, Qingyao Wu

ECCV 2020 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 85 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 SPIL interaction learning with Euclidean-distance position term (ablation)point-convolution baseline · RWF-2000accuracy: 84.3 -> 86.4Improved
add SPIL with distance spanning position term (ablation)point-convolution baseline · RWF-2000accuracy: 84.3 -> 88.0Improved
add SPIL with distance masking position term (ablation)point-convolution baseline · RWF-2000accuracy: 84.3 -> 88.7Improved
use masking instead of spanning position term (ablation)SPIL · RWF-2000accuracy: 88.0 -> 88.7Improved
use 8 heads instead of 1 head (ablation)SPIL-Mask · RWF-2000accuracy: 88.7 -> 89.2Improved
use 8 heads instead of 1 head (ablation)vanilla baseline · RWF-2000accuracy: 84.3 -> 84.7Improved
increase heads from 8 to 64 (ablation)SPIL-Mask · RWF-2000accuracy: 89.2 -> 89.0No clear effect
set mask threshold d=0.04 instead of 0.01 (ablation)SPIL-Mask · RWF-2000accuracy: 88.7 -> 89.3Improved
set mask threshold d=0.04 instead of 0.08 (ablation)SPIL-Mask · RWF-2000accuracy: 89.0 -> 89.3Improved
use SPIL instead of Flow Gated Network on RWF-2000 (ablation)SPIL-Mask · RWF-2000accuracy: 87.3 -> 89.3Improved
use SPIL instead of Flow Gated Network on Hockey-FightSPIL-Mask · Hockey-Fightaccuracy: 98.0 -> 96.8Hurt
use SPIL instead of Flow Gated Network on Crowd ViolenceSPIL-Mask · Crowd Violenceaccuracy: 88.8 -> 94.5Improved

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