AI Paper Atlas

Research map / Video / Action recognition

Re-Sign: Re-Aligned End-To-End Sequence Modelling With Deep Recurrent CNN-HMMs

Oscar Koller, Sepehr Zargaran, Hermann Ney

CVPR 2017 · Video › Action recognition · approach: Fully supervised temporal action detection · 281 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
Iteratively re-align training frame labels using the CNN-HMMCNN on PHOENIX 2014 · PHOENIX 2014 DevWER: 33.7 -> 29.0Improved
Iteratively re-align training frame labels using the CNN-HMMCNN-2BLSTM on PHOENIX 2014 · PHOENIX 2014 TestWER: 32.9 -> 26.8Improved
Use full-frame images instead of tracked right-hand patches (ablation)GoogLeNet recognition model · PHOENIX 2014 DevWER: 38.3 -> 33.7Improved
Add one LSTM layer to the CNN (ablation)GoogLeNet on PHOENIX 2014 · PHOENIX 2014 DevWER: 33.7 -> 44.2Hurt
Initialize the CNN-LSTM with a CNN trained on PHOENIX 2014 (ablation)CNN-LSTM on PHOENIX 2014 · PHOENIX 2014 DevWER: 44.2 -> 33.8Improved
Use two bidirectional LSTM layers instead of one (ablation)CNN-BLSTM on PHOENIX 2014 · PHOENIX 2014 DevWER: 30.2 -> 27.1Improved
Increase each BLSTM layer from 512 to 1024 hidden units (ablation)CNN-2BLSTM on PHOENIX 2014 · PHOENIX 2014 DevWER: 27.9 -> 27.1Improved
Use two BLSTM layers with 1024 units per layer rather than the one-layer CNN-LSTM setup (ablation)End-to-end CNN recurrent model · PHOENIX 2014 DevWER: 29.5 -> 27.1Improved
Apply iterative re-alignmentCNN-2BLSTM on SIGNUM · SIGNUM TestWER: 6.5 -> 4.8Improved
Increase the number of re-alignment iterations from two to three (ablation)Full-frame CNN on PHOENIX 2014 · PHOENIX 2014 DevWER: 30.7 -> 29.0Improved
Increase the number of re-alignment iterations from three to four (ablation)CNN-2BLSTM on PHOENIX 2014 · PHOENIX 2014 DevWER: 27.1 -> 27.2No clear effect

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