AI Paper Atlas

Research map / Video / Action recognition

Action Tubelet Detector for Spatio-Temporal Action Localization

Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid

ICCV 2017 · Video › Action recognition · approach: Weakly supervised temporal action localization · 338 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 tubelet input of K=6 frames instead of K=1 per-frame detection (ablation)ACT-detector · UCF-Sports fast actorsframe-mAP: 68.1 -> 76.8Improved
add tubelets K=6 vs K=1 for fast actors (ablation)ACT-detector · J-HMDB fast actorsframe-mAP: 49.0 -> 58.0Improved
add tubelets K=6 vs K=1 for fast actors (ablation)ACT-detector · UCF-101 fast actorsframe-mAP: 67.3 -> 70.7Improved
use sequence length K=6 instead of K=1 (ablation)ACT-detector · UCF-Sports, J-HMDB, UCF-101MABO: MABO increases by 5% on UCF-Sports, 2% on J-HMDB and 5% on UCF-101Improved
increase tubelet length up to K=6 or 8 (ablation)ACT-detector · three datasetsframe-mAP: gain up to 10%Improved
increase tubelet length beyond K=8 (ablation)ACT-detector · J-HMDB, UCF-101frame-mAPHurt
late fusion of RGB and flow instead of union fusion (ablation)ACT-detector · three datasetsframe-mAP: gain between 1% and 4%Improved
add flow stream to RGB stream (ablation)ACT-detector · three datasetsframe-mAPImproved
stack 5 flow images instead of 1 as motion input (ablation)ACT-detector · three datasetsframe-mAP: +1% frame-mAPImproved
use tubelet linking instead of linking individual boxes (ablation)ACT-detector · three datasetsvideo-mAP: consistent gain of 1%Improved
use ACT-detector instead of prior SSD detector at high IoUJ-HMDB · J-HMDB video-mAP IoU 0.75video-mAP: 44.5 -> 52.1Improved
use ACT-detector instead of prior SSD detectorUCF-101 · UCF-101 video-mAP IoU 0.5video-mAP: 46.3 -> 51.4Improved

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