AI Paper Atlas

Research map / Video / Action recognition

Mode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition

Wissam J. Baddar, Yong Man Ro

AAAI 2019 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 36 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 a separate bias cell and static-sequence path to the LSTMLSTM · Oulu-CASIArecognition rate (%): 78.21 -> 83.94Improved
Add a separate bias cell and static-sequence path to the LSTMLSTM · KAIST Face MPMIrecognition rate (%): 79.93 -> 82.61Improved
Add a separate bias cell and static-sequence path to the LSTMLSTM · AFEW validationvisual recognition rate (%): 48.83 vs 48.60Improved
Add cross-cell peephole connections between the dynamics and bias cellsMode variational LSTM · Oulu-CASIArecognition rate (%): 83.94 -> 85.18Improved
Add cross-cell peephole connections between the dynamics and bias cellsMode variational LSTM · AFEW validationvisual recognition rate (%): 48.83 -> 51.44Improved
Add cross-cell peephole connections between the dynamics and bias cellsMode variational LSTM · KAIST Face MPMIrecognition rate (%): 82.61 -> 84.98Improved
Add a separate bias cell and static-sequence pathLSTM · Oulu-CASIA cross-race, Asian train to Caucasian testrecognition rate (%): 73.39 -> 79.14Improved
Add a separate bias cell and static-sequence pathLSTM · Oulu-CASIA cross-race, Caucasian train to Asian testrecognition rate (%): 74.67 -> 80.95Improved
Use the mode variational LSTM with cross-cell peepholeLSTM · KAIST Face MPMI, room illuminationrecognition rate (%): 78.21 -> 83.11Improved
Use the mode variational LSTM with cross-cell peepholeLSTM · KAIST Face MPMI, bright illuminationrecognition rate (%): 76.98 -> 83.03Improved
Use the mode variational LSTM with cross-cell peepholeLSTM · KAIST Face MPMI, left illuminationrecognition rate (%): 73.67 -> 82.87Improved
Use the mode variational LSTM with cross-cell peepholeLSTM · KAIST Face MPMI, right illuminationrecognition rate (%): 74.39 -> 82.91Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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