AI Paper Atlas

Research map / Video / Video segmentation and tracking

Complex Event Detection by Identifying Reliable Shots From Untrimmed Videos

Hehe Fan, Xiaojun Chang, De Cheng, Yi Yang, Dong Xu, Alexander G. Hauptmann

ICCV 2017 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 49 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
select reliable shots with MIL-SRI instead of treating all shots as instancesSVM · MEDTest-14 100ExmAP: 22.2 -> 38.6Improved
use MIL-SRI instead of SMIL-TopKMIL-SRI · MEDTest-14 100ExmAP: 36.9 -> 38.6Improved
use MIL-SRI instead of SMIL-TopKMIL-SRI · MEDTest-13 100ExmAP: 40.5 -> 43.1Improved
pool frame features with LSTM instead of sparse MILRNN-LSTM · MEDTest-14 100ExmAP: 19.8 -> 31.1Improved
add l2 diversity term (gamma > 0) (ablation)MIL-SRI · MEDTest-14 (rock climbing E027, 100Ex)AP: 30.76% -> 32.64%Improved
add IDT motion feature fusionMIL-SRI · MEDTest-14 10ExmAP: 28.4 -> 29.6Improved
add IDT motion feature fusionMIL-SRI · MEDTest-13 100ExmAP: 43.1 -> 49.7Improved
use MIL-SRI instead of NI-SVMMIL-SRI · CCVmAP: 78.3 -> 77.9Hurt
use MIL-SRI instead of CNN + VLADMIL-SRI · MEDTest-14 100ExmAP: 35.7 -> 38.6Improved

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