Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CNN

CNN

Reported on 122 benchmarks across 41 tasks · 23 papers · 29 SOTA

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

Methodology41 results

ClassificationonCIFAKE: Real and AI-Generated Synthetic Images
Validation Accuracy· 2023-03-24
93.55
SOTA
CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images arXiv:2303.14126
ClassificationonCWRU Bearing Dataset
10 fold Cross validation· uses extra data· 2020-10-05
7
best: 99.93 (MixMamba-Fewshot)
SOTA
FaultNet: A Deep Convolutional Neural Network for bearing fault classification arXiv:2010.02146
Unsupervised Pre-trainingonMeasles
Accuracy (%)· uses extra data· 2020-05-18
73
best: 95 (15RDLs)
SOTA
Measles Rash Identification Using Residual Deep Convolutional Neural Network arXiv:2005.09112
Transfer Learningon100 sleep nights of 8 caregivers
10-20% Mask PSNR· 2020-03-05
3.23
SOTA
Plant Disease Detection from Images arXiv:2003.05379
ClassificationonSHD
Percentage correct· 2019-10-16
92.4
best: 95.9 (Event-SSM)
SOTA
The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks arXiv:1910.07407
Feature Engineeringon2019_test set
14 gestures accuracy· uses extra data· 2018-06-07
0.98
SOTA
Evaluating surgical skills from kinematic data using convolutional neural networks arXiv:1806.02750
Zero-Shot LearningonGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401
ClassificationonDBpedia
Error· 2016-02-07
0.84
best: 0.62 (XLNet)
SOTA
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings arXiv:1602.02373
ClassificationonAG News
Error· 2016-02-07
6.57
best: 4.45 (XLNet)
SOTA
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings arXiv:1602.02373
3DonINI-30
Euclidean Distance· 2023-12-01
0.5
best: 1.75 (TinyissimoV8)
Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware arXiv:2312.00425
2D ClassificationonINI-30
Euclidean Distance· 2023-12-01
0.5
best: 1.75 (TinyissimoV8)
Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware arXiv:2312.00425
2D Object DetectiononINI-30
Euclidean Distance· 2023-12-01
0.5
best: 1.75 (TinyissimoV8)
Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware arXiv:2312.00425
16konINI-30
Euclidean Distance· 2023-12-01
0.5
best: 1.75 (TinyissimoV8)
Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware arXiv:2312.00425
Multi-Label ClassificationonMIMIC-IV ICD-9
AUC Macro· 2023-04-21
89.4
best: 97.2 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
AUC Micro· 2023-04-21
98.1
best: 99.4 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
Exact Match Ratio· 2023-04-21
0.6
best: 1 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
F1 Macro· 2023-04-21
12.6
best: 29.8 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
F1 Micro· 2023-04-21
52.4
best: 62.6 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
Precision@15· 2023-04-21
45.6
best: 53.5 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
Precision@8· 2023-04-21
61.3
best: 70 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
R-Prec· 2023-04-21
52.9
best: 62.7 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-9
mAP· 2023-04-21
55.2
best: 68 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
AUC Macro· 2023-04-21
87.9
best: 96.6 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
AUC Micro· 2023-04-21
97.5
best: 99.2 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
Exact Match Ratio· 2023-04-21
0.3
best: 0.4 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
F1 Macro· 2023-04-21
8
best: 21.1 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
F1 Micro· 2023-04-21
47.2
best: 58.5 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
Precision@15· 2023-04-21
45.7
best: 55 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
Precision@8· 2023-04-21
60.3
best: 69.9 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
R-Prec· 2023-04-21
47.3
best: 57.9 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-IV ICD-10
mAP· 2023-04-21
48.2
best: 61.9 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Multi-Label ClassificationonMIMIC-III
Macro-AUC· 2018-02-15
80.6
best: 96.2 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Multi-Label ClassificationonMIMIC-III
Macro-F1· 2018-02-15
4.2
best: 24.7 (PLM-CA)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Multi-Label ClassificationonMIMIC-III
Micro-AUC· 2018-02-15
96.9
best: 99.3 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Multi-Label ClassificationonMIMIC-III
Micro-F1· 2018-02-15
41.9
best: 61.2 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Multi-Label ClassificationonMIMIC-III
Precision@15· 2018-02-15
44.3
best: 62.4 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Multi-Label ClassificationonMIMIC-III
Precision@8· 2018-02-15
58.1
best: 77.7 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
ClassificationonMVICTOR (type)
Average F1
0.7061
best: 0.7505 (CNN + CRF)
ClassificationonMVICTOR (type)
Weighted F1
0.9464
best: 0.9537 (CNN + CRF)
ClassificationonSVICTOR (type)
Average F1
0.7584
best: 0.774 (CNN + CRF)
ClassificationonSVICTOR (type)
Weighted F1
0.9472
best: 0.9533 (CNN + CRF)

Natural Language Processing28 results

Semantic Textual Similarityon2017_test set
10 fold Cross validation· 2018-06-12
50
SOTA
Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering arXiv:1806.04330
Paraphrase Identificationon2017_test set
10 fold Cross validation· 2018-06-12
50
SOTA
Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering arXiv:1806.04330
3D Action RecognitiononGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401
Sentiment AnalysisonYelp Fine-grained classification
Error· 2016-02-07
32.39
best: 27.05 (XLNet)
SOTA
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings arXiv:1602.02373
Sentiment AnalysisonYelp Binary classification
Error· 2016-02-07
2.9
best: 1.37 (XLNet)
SOTA
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings arXiv:1602.02373
Text ClassificationonDBpedia
Error· 2016-02-07
0.84
best: 0.62 (XLNet)
SOTA
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings arXiv:1602.02373
Text ClassificationonAG News
Error· 2016-02-07
6.57
best: 4.45 (XLNet)
SOTA
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings arXiv:1602.02373
Question AnsweringonTrecQA
MAP· 2014-12-04
0.711
best: 0.954 (TANDA DeBERTa-V3-Large + ALL)
SOTA
Deep Learning for Answer Sentence Selection arXiv:1412.1632
Question AnsweringonTrecQA
MRR· 2014-12-04
0.785
best: 0.998 (RLAS-BIABC)
SOTA
Deep Learning for Answer Sentence Selection arXiv:1412.1632
Relation ExtractiononACE 2005
Relation classification F1· 2023-04-21
61.3
best: 80.8 (Dual Pointer Network(multi-head))
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Dialogue UnderstandingonYouTube News dataset (No Noise)
Accuracy · 2021-10-05
0.948
best: 0.967 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
Dialogue UnderstandingonIndicTTS
Classification Accuracy· 2021-10-05
0.983
best: 0.987 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
Dialogue UnderstandingonYouTube News dataset (White Noise)
Accuracy · 2021-10-05
0.871
best: 0.912 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
Question AnsweringonYahooCQA
MRR· 2017-07-25
0.632
best: 0.863 (sMIM (1024) +)
Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering arXiv:1707.07847
Question AnsweringonYahooCQA
P@1· 2017-07-25
0.413
best: 0.757 (sMIM (1024) +)
Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering arXiv:1707.07847
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2017-07-06
91.2
best: 97.5 (T5-11B)
On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis arXiv:1707.01780
Relation ExtractiononSemEval-2010 Task-8
F1
82.7
best: 91.9 (SP)
Visual Question Answering (VQA)onGQA Test2019
Accuracy
17.82
best: 89.3 (human)
Visual Question Answering (VQA)onGQA Test2019
Binary
36.05
best: 91.2 (human)
Visual Question Answering (VQA)onGQA Test2019
Consistency
62.4
best: 98.4 (human)
Visual Question Answering (VQA)onGQA Test2019
Distribution
19.99
best: 93.08 (GlobalPrior)
Visual Question Answering (VQA)onGQA Test2019
Open
1.74
best: 87.4 (human)
Visual Question Answering (VQA)onGQA Test2019
Plausibility
34.84
best: 97.2 (human)
Visual Question Answering (VQA)onGQA Test2019
Validity
35.78
best: 98.9 (human)
Text ClassificationonMVICTOR (type)
Average F1
0.7061
best: 0.7505 (CNN + CRF)
Text ClassificationonMVICTOR (type)
Weighted F1
0.9464
best: 0.9537 (CNN + CRF)
Text ClassificationonSVICTOR (type)
Average F1
0.7584
best: 0.774 (CNN + CRF)
Text ClassificationonSVICTOR (type)
Weighted F1
0.9472
best: 0.9533 (CNN + CRF)

Medical26 results

Seizure predictiononMelbourne University Seizure Prediction
AUC· 2018-11-02
0.591
best: 0.84 (CNN+FCN)
SOTA
Convolutional Neural Networks for Epileptic Seizure Prediction arXiv:1811.00915
Surgical Skills EvaluationonJIGSAWS
Accuracy· 2018-06-07
0.98
SOTA
Evaluating surgical skills from kinematic data using convolutional neural networks arXiv:1806.02750
Medical Code PredictiononMIMIC-IV ICD-9
AUC Macro· 2023-04-21
89.4
best: 97.2 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
AUC Micro· 2023-04-21
98.1
best: 99.4 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
Exact Match Ratio· 2023-04-21
0.6
best: 1 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
F1 Macro· 2023-04-21
12.6
best: 29.8 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
F1 Micro· 2023-04-21
52.4
best: 62.6 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
Precision@15· 2023-04-21
45.6
best: 53.5 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
Precision@8· 2023-04-21
61.3
best: 70 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
R-Prec· 2023-04-21
52.9
best: 62.7 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-9
mAP· 2023-04-21
55.2
best: 68 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
AUC Macro· 2023-04-21
87.9
best: 96.6 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
AUC Micro· 2023-04-21
97.5
best: 99.2 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
Exact Match Ratio· 2023-04-21
0.3
best: 0.4 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
F1 Macro· 2023-04-21
8
best: 21.1 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
F1 Micro· 2023-04-21
47.2
best: 58.5 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
Precision@15· 2023-04-21
45.7
best: 55 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
Precision@8· 2023-04-21
60.3
best: 69.9 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
R-Prec· 2023-04-21
47.3
best: 57.9 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-IV ICD-10
mAP· 2023-04-21
48.2
best: 61.9 (PLM-ICD)
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study arXiv:2304.10909
Medical Code PredictiononMIMIC-III
Macro-AUC· 2018-02-15
80.6
best: 96.2 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Medical Code PredictiononMIMIC-III
Macro-F1· 2018-02-15
4.2
best: 24.7 (PLM-CA)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Medical Code PredictiononMIMIC-III
Micro-AUC· 2018-02-15
96.9
best: 99.3 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Medical Code PredictiononMIMIC-III
Micro-F1· 2018-02-15
41.9
best: 61.2 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Medical Code PredictiononMIMIC-III
Precision@15· 2018-02-15
44.3
best: 62.4 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695
Medical Code PredictiononMIMIC-III
Precision@8· 2018-02-15
58.1
best: 77.7 (GKI-ICD)
Explainable Prediction of Medical Codes from Clinical Text arXiv:1802.05695

Computer Vision10 results

VideoonGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401
Temporal Action LocalizationonGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401
Action LocalizationonGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401
Object DetectiononINI-30
Euclidean Distance· 2023-12-01
0.5
best: 1.75 (TinyissimoV8)
Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware arXiv:2312.00425
Image ClassificationonCelebA 64x64
Accuracy· 2020-08-12
0.67
best: 0.82 (cFlow)
Null-sampling for Interpretable and Fair Representations arXiv:2008.05248
Image ClassificationonEMNIST-Balanced
Accuracy· 2020-07-07
79.61
best: 91.48 (EMNIST-mobile)
SpinalNet: Deep Neural Network with Gradual Input arXiv:2007.03347
Image ClassificationonEMNIST-Balanced
Trainable Parameters· 2020-07-07
21840
best: 3646000 (VGG-5)
SpinalNet: Deep Neural Network with Gradual Input arXiv:2007.03347
Image ClassificationonSTL-10
Percentage correct· 2017-03-27
70.7
best: 99.64 (µ2Net+ (ViT-L/16))
Scaling the Scattering Transform: Deep Hybrid Networks arXiv:1703.08961
Image Classificationon10 Monkey Species
Accuracy
95
best: 99.26 (Inception-v3 (Spinal FC))
Fine-Grained Image Classificationon10 Monkey Species
Accuracy
95
best: 99.26 (Inception-v3 (Spinal FC))

Speech7 results

DialogueonYouTube News dataset (No Noise)
Accuracy · 2021-10-05
0.948
best: 0.967 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
DialogueonIndicTTS
Classification Accuracy· 2021-10-05
0.983
best: 0.987 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
DialogueonYouTube News dataset (White Noise)
Accuracy · 2021-10-05
0.871
best: 0.912 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
Spoken Language UnderstandingonYouTube News dataset (No Noise)
Accuracy · 2021-10-05
0.948
best: 0.967 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
Spoken Language UnderstandingonIndicTTS
Classification Accuracy· 2021-10-05
0.983
best: 0.987 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
Spoken Language UnderstandingonYouTube News dataset (White Noise)
Accuracy · 2021-10-05
0.871
best: 0.912 (CRNN)
Is Attention always needed? A Case Study on Language Identification from Speech arXiv:2110.03427
Keyword SpottingonGoogle Speech Commands
Google Speech Commands V1 12· 2017-11-20
84.6
best: 98.56 (TripletLoss-res15)
Hello Edge: Keyword Spotting on Microcontrollers arXiv:1711.07128

Time Series3 results

Time Series ClassificationonBorealTC
Accuracy (5-fold)· 2024-03-25
93.96
SOTA
Proprioception Is All You Need: Terrain Classification for Boreal Forests arXiv:2403.16877
Action DetectiononGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401
Action RecognitiononGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401

Audio3 results

Emotion Recognitiononคลิปคุณพ่อให้ลูกสาวยืมโทรศัพท์และความสนุกสนาน
1'"· 2020-04-26
1
SOTA
A Spontaneous Driver Emotion Facial Expression (DEFE) Dataset for Intelligent Vehicles arXiv:2005.08626
Audio ClassificationonSHD
Percentage correct· 2019-10-16
92.4
best: 95.9 (Event-SSM)
SOTA
The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks arXiv:1910.07407
Speech RecognitiononSwitchboard + Hub500
Percentage error
11.5
best: 4.3 (IBM (LSTM+Conformer encoder-decoder))

Adversarial3 results

Neural Network SecurityonWebsite Traffic Data on Tor
Accuracy (%)
42
Website Fingerprinting AttacksonWebsite Traffic Data on Tor
Accuracy (%)
98.4
Website Fingerprinting DefenseonWebsite Traffic Data on Tor
Accuracy (%)
42

Robots1 result

Activity RecognitiononGaming 3D (G3D)
Accuracy· 2016-12-30
96
SOTA
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks arXiv:1612.09401