AI Paper Atlas

Research map / Video / Action recognition

MiniROAD: Minimal RNN Framework for Online Action Detection

Joungbin An, Hyolim Kang, Su Ho Han, Ming-Hsuan Yang, Seon Joo Kim

ICCV 2023 · Video › Action recognition · approach: Fully supervised temporal action detection · 46 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
use step-function loss weights (loss only at last clip step) instead of uniform weights (ablation)MiniROAD GRU · THUMOS'14mAP (%): 66.4 -> 71.8Improved
use step-function loss weights instead of learnable weights (ablation)MiniROAD GRU · THUMOS'14mAP (%): 70.8 -> 71.8Improved
linearly increasing instead of uniform loss weights (ablation)MiniROAD GRU · THUMOS'14mAP (%): 66.4 -> 68.6Improved
apply proposed last-step loss weights to the transformer encoder (ablation)OadTR encoder · THUMOS'14mAP (%): 63.0 -> 64.9Improved
increase training clip length beyond 32 seconds (ablation)MiniROAD · THUMOS'14mAP (%)No clear effect
GRU with step weights versus transformer SOTA on FineActionMiniROAD · FineActionmAP (%): 31.8 -> 37.1Improved
use faster NVIDIA optical flow instead of TV-L1MiniROAD · THUMOS'14Overall FPS / mAP: 23.8 -> 122 FPSMixed
apply last-step loss to action anticipationMiniROAD · THUMOS'14 anticipation (Kinetics)average mAP: 56.8 -> 59.7Improved

Later papers that compared with this method

3 later accepted papers report MiniROAD as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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