AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition

Toby Perrett, Dima Damen

CVPR 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 32 citations (OpenAlex)

Check 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
Replace standard batch normalization with learned dual-domain cross-contamination in input-to-hidden and hidden-to-hidden LSTM weightsLSTM trained jointly on two datasets · 50 Salads, MPII Cooking 2, and Breakfast dataset pairsframe-level accuracy: 5.1%; 2.5%; 3.7%; 3.8%; 4.2%; 1.0%Improved
Use jointly trained DDLSTM rather than jointly trained LSTM50 Salads (paired with MPII Cooking 2) · 50 Saladsframe-level accuracy: 41.6 -> 47.1Improved
Use jointly trained DDLSTM rather than jointly trained LSTMMPII Cooking 2 (paired with 50 Salads) · MPII Cooking 2frame-level accuracy: 39.0 -> 41.5Improved
Use jointly trained DDLSTM rather than jointly trained LSTMBreakfast (paired with 50 Salads) · Breakfastframe-level accuracy: 24.7 -> 29.1Improved
Use jointly trained DDLSTM rather than pre-training/fine-tuning LSTM50 Salads (paired with Breakfast) · 50 Saladsframe-level accuracy: 42.5 -> 46.3Improved
Use jointly trained DDLSTM rather than jointly trained LSTMBreakfast (paired with MPII Cooking 2) · Breakfastframe-level accuracy: 26.3 -> 30.5Improved
Use jointly trained DDLSTM rather than jointly trained LSTMMPII Cooking 2 (paired with Breakfast) · MPII Cooking 2frame-level accuracy: 39.1 -> 40.1Improved
Use 3 LSTM layers rather than 1 (ablation)DDLSTM · 50 Salads, MPII Cooking 2, and Breakfast dataset pairsframe-level accuracy: 45.7 -> 47.1; 41.3 -> 41.5; 28.4 -> 29.1; 45.0 -> 46.3; 29.2 -> 30.5; 40.8 -> 40.1Mixed
Use 3 LSTM layers rather than 2 (ablation)DDLSTM · 50 Salads, MPII Cooking 2, and Breakfast dataset pairsframe-level accuracy: 46.6 -> 47.1; 41.0 -> 41.5; 29.0 -> 29.1; 45.2 -> 46.3; 29.9 -> 30.5; 40.1 -> 40.1Mixed
Use 3 LSTM layers rather than 4 (ablation)DDLSTM · 50 Salads, MPII Cooking 2, and Breakfast dataset pairsframe-level accuracy: 46.1 -> 47.1; 40.6 -> 41.5; 28.6 -> 29.1; 44.3 -> 46.3; 30.5 -> 30.5; 38.8 -> 40.1Mixed
Use 3 LSTM layers rather than 5 (ablation)DDLSTM · 50 Salads, MPII Cooking 2, and Breakfast dataset pairsframe-level accuracy: 41.0 -> 47.1; 40.3 -> 41.5; 29.0 -> 29.1; 46.0 -> 46.3; 30.3 -> 30.5; 38.4 -> 40.1Improved
Use 3 LSTM layers rather than 10 (ablation)DDLSTM · 50 Salads, MPII Cooking 2, and Breakfast dataset pairsframe-level accuracy: 39.7 -> 47.1; 38.0 -> 41.5; 25.5 -> 29.1; 40.7 -> 46.3; 28.1 -> 30.5; 35.6 -> 40.1Improved

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