AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection

Rui Dai, Srijan Das, Saurav Sharma, Luca Minciullo, Lorenzo Garattoni, François Brémond, Gianpiero Francesca

TPAMI 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 69 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 3D-pose attention module to SD-TCN on RGB (AGNet) (ablation)I3D+SD-TCN · TSU fine-grained (cross-subject)per-frame mAP: 29.2 -> 33.2Improved
add 3D-pose attention module to SD-TCN on RGB (AGNet) (ablation)I3D+SD-TCN · TSU fine-grained (cross-view)per-frame mAP: 18.3 -> 23.2Improved
use I3D instead of Inception RGB features (ablation)SD-TCN · TSU fine-grained (cross-subject)per-frame mAP: 22.3 -> 29.2Improved
use 3D pose (AGCN) instead of RGB (I3D) features (ablation)SD-TCN · TSU fine-grained (cross-view)per-frame mAP: 18.3 -> 22.4Improved
use 3D pose (AGCN) instead of RGB (I3D) features (ablation)SD-TCN · TSU fine-grained (cross-subject)per-frame mAP: 29.2 -> 26.2Hurt
add SD-TCN temporal modelling to I3D bottleneckI3D+Bottleneck · TSU fine-grained (cross-subject)per-frame mAP: 15.7 -> 29.2Improved
train I3D on trimmed clips instead of random untrimmed snippets (ablation)I3D+Bottleneck · TSU fine-grained (cross-subject)per-frame mAP: 15.7 -> 7.4Hurt
use balanced annotation instead of fine-grained annotationI3D+SD-TCN · Balanced TSU (cross-subject)per-frame mAP: 29.2 -> 35.8Improved
use balanced annotation instead of fine-grained annotationI3D+Bottleneck · Balanced TSU (cross-subject)per-frame mAP: 15.7 -> 17.1Improved
train with synchronized joint views (late fusion) instead of mixed viewSD-TCN · TSU joint-view (cross-subject)per-frame mAP: 35.5 -> 38.9Improved
train with synchronized joint views using AG-Net instead of mixed viewAG-Net · TSU joint-view (cross-subject)per-frame mAP: 35.5 -> 40.1Improved
use SSD human crops instead of center crops (ablation)I3D+AGNet · TSU-CSper-frame mAP: 26.9 -> 33.2Improved

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