AI Paper Atlas

Research map / Video / Action recognition

AMTnet: Action-Micro-Tube Regression by End-To-End Trainable Deep Architecture

Suman Saha, Gurkirt Singh, Fabio Cuzzolin

ICCV 2017 · Video › Action recognition · approach: Fully supervised temporal action detection · 60 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
lower positive IoU threshold for 3D proposal sampling (0.5 instead of 0.7) (ablation)AMTnet · UCF-101video-mAP @0.2: 54.83 -> 60.06Improved
add scheme-32 pairs to scheme-11 training data (ablation)AMTnet · J-HMDB-21 frame-mAPframe-mAP: 43.6 -> 45.0Improved
add scheme-32 pairs to scheme-11 training data (ablation)AMTnet · J-HMDB-21video-mAP @0.5: 54.27 -> 55.31Improved
add scheme-32 pairs to scheme-11 training data (ablation)AMTnet · J-HMDB-21video-mAP @0.4: 56.81 -> 56.79No clear effect
use sum fusion instead of mean fusion of feature maps (ablation)AMTnet · J-HMDB-21video-mAP @0.5: 54.51 -> 55.31Improved
use top 300 instead of 1000 proposals at test time (ablation)AMTnet · J-HMDB-21video-mAP @0.5: 55.31 -> 55.26No clear effect
train with consecutive-frame pairs instead of identical-frame pairs (ablation)AMTnet · J-HMDB-21 split 1video-mAP @0.5: 48.9 -> 52.7Improved
train with mixed consecutive and gapped pairs instead of consecutive only (ablation)AMTnet · J-HMDB-21 split 1video-mAP @0.5: 52.7 -> 57.1Improved
lower mid-layer loss weights to 0.5/0.5 instead of 1.0/1.0 (ablation)AMTnet · J-HMDB-21 split 1video-mAP @0.5: 52.78 -> 53.81Improved
very low mid-layer loss weights 0.1/0.05 instead of 1.0/1.0 (ablation)AMTnet · J-HMDB-21 split 1video-mAP @0.5: 52.78 -> 50.33Hurt
use 2PDP tube generation instead of micro-tube linkingAMTnet · UCF-101video-mAP @0.2: 61.36 -> 63.06Improved
use cross-validated alphasAMTnet ML · UCF-101video-mAP @0.2: 60.06 -> 61.36Improved

Later papers that compared with this method

1 later accepted paper reports AMTNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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