AI Paper Atlas

Research map / Video / Action recognition

AViD Dataset: Anonymized Videos from Diverse Countries

AJ Piergiovanni, Michael Ryoo

NeurIPS 2020 · Video › Action recognition · approach: Disentangled action recognition · 19 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
Train the 3D ResNet-50 on geographically diverse AViD videos rather than Kinetics-4003D ResNet-50 · AViD shared classes, Rest of Worldaccuracy: 64.5% -> 73.5%Improved
Train on AViD rather than Kinetics-6003D ResNet-50 · AViD shared classes, Rest of Worldaccuracy: 65.5% -> 73.5%Improved
Train on AViD rather than Kinetics-4003D ResNet-50 · AViD shared classes, North Americaaccuracy: 72.8% -> 75.2%Improved
Train on AViD rather than Kinetics-4003D ResNet-50 · AViD shared classes, Africaaccuracy: 58.4% -> 71.4%Improved
Pretrain on AViD rather than Kinetics-400I3D · HMDB-51accuracy: 72.5 -> 75.2Improved
Pretrain on AViD rather than Kinetics-6003D ResNet-50 · HMDB-51accuracy: 76.2 -> 77.3Improved
Add the AViD no-action examples to pretraining (ablation)I3D · Charades localizationmAP: 17.3 -> 19.7Improved
Add the AViD no-action examples to pretraining (ablation)3D ResNet-50 · Charades localizationmAP: 18.7 -> 23.2Improved
Use weak agglomerative-clustering tags instead of full action labels for pretraining (ablation)3D ResNet-50 · HMDB-51accuracy: 77.3 -> 76.4Hurt
Use weak affinity-propagation tags instead of full action labels for pretraining (ablation)3D ResNet-50 · HMDB-51accuracy: 77.3 -> 75.3Hurt
Blur faces in the AViD training videos (ablation)3D ResNet-50 · AViDaccuracy: 48.2 -> 47.9Hurt
Use more ordered frames rather than a single frame (ablation)3D ResNet-50 · AViDaccuracy: 32.5 -> 47.9Improved

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