AI Paper Atlas

Research map / Video / Action recognition

E2E-LOAD: End-to-End Long-form Online Action Detection

Shuqiang Cao, Weixin Luo, Bairui Wang, Wei Zhang, Lin Ma

ICCV 2023 · Video › Action recognition · approach: Fully supervised temporal action detection · 20 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 long-term compression and long-short-term fusion (ablation)E2E-LOAD baseline · THUMOS'14mAP: 71.2 -> 72.2Improved
add efficient inference token re-usage (ablation)E2E-LOAD baseline · THUMOS'14FPS: 9.1 -> 19.5Improved
add efficient inference token re-usage (ablation)E2E-LOAD baseline · THUMOS'14mAP: 71.2 -> 71.5Improved
use progressive long-term compression x2,x2,x1,x1 instead of x4,x2,x1 (ablation)LC module · THUMOS'14mAP: 70.8 -> 72.4Improved
fuse long-term into short-term at middle layer 5 instead of early layer 1 (ablation)LSF · THUMOS'14mAP: 70.5 -> 72.4Improved
fuse at layer 5 instead of late layer 11 (ablation)LSF · THUMOS'14mAP: 71.5 -> 72.4Improved
cross-attention fusion instead of self-attention fusion (ablation)LSF · THUMOS'14mAP: 70.3 -> 72.4Improved
use MViT pooling attention instead of Video Swin shifted window (ablation)Short-term modeling · THUMOS'14mAP: 64.7 -> 71.5Improved
use MViT pooling attention instead of MeMViT (ablation)Short-term modeling · THUMOS'14mAP: 70.9 -> 71.5Improved
switch LSTR backbone from TSN to MViT featuresLSTR RGB-only · THUMOS'14mAP: 56.8 -> 60.7Improved
end-to-end training of LSTR instead of frozen featuresLSTR RGB-only · THUMOS'14mAP: 56.8 -> 59.2Improved
add optical flow input to feature-based LSTR with MViTLSTR · THUMOS'14mAP: 60.7 -> 71.2Improved

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