CNN-LSTM

Reported on 7 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Sentiment AnalysisonSemEval 2017 Task 4-A
Average Recall
0.61
best: 0.681 (LSTMs+CNNs ensemble with multiple conv. ops)
Sentiment AnalysisonASTD
Average Recall
0.62
Sentiment AnalysisonArSAS
Average Recall
0.9

Audio1 result

Speech RecognitiononSwitchboard + Hub500
Percentage error· 2016-10-17
6.6
best: 4.3 (IBM (LSTM+Conformer encoder-decoder))
Achieving Human Parity in Conversational Speech Recognition arXiv:1610.05256

Robots1 result

Activity RecognitiononUCFSports
leave one out cross validation(LOOCV)
98.27

Medical1 result

Brain DecodingonBCI Competition IV: ECoG to Finger Movements
Pearson Correlation
0.52
best: 0.67 (FingerFlex)

Time Series1 result

Action RecognitiononUCFSports
leave one out cross validation(LOOCV)
98.27