result SOTA: MHP v2.0 (multi-human parsing) [computer vision] in the open CK format
result SOTA: MIB Datasets (twitter bot detection) [miscellaneous] in the open CK format
result SOTA: Middlebury (video frame interpolation) [computer vision] in the open CK format
result SOTA: MIMIC-III (blood pressure estimation) [medical] in the open CK format
result SOTA: MIMIC-III (blood pressure estimation) [medical] in the open CK format
result SOTA: MIMIC-III (mortality prediction) [medical] in the open CK format
result SOTA: MIMIC-III (mortality prediction) [medical] in the open CK format
result SOTA: MIMIC-III (multivariate time series forecasting) [time series] in the open CK format
result SOTA: Mini-ImageNet - 5-Shot Learning (few-shot camera-adaptive color constancy) [computer vision] in the open CK format
result SOTA: Mini-ImageNet - 5-Shot Learning (few-shot image classification) [computer vision] in the open CK format
result SOTA: Mini-ImageNet - 5-Shot Learning (few-shot image classification) [computer vision] in the open CK format
result SOTA: MiniKinetics (action classification) [computer vision] in the open CK format
result SOTA: miniSports (action recognition in videos) [computer vision] in the open CK format
result SOTA: miniSports (action recognition in videos) [computer vision] in the open CK format
result SOTA: miniSports (action recognition in videos) [computer vision] in the open CK format
result SOTA: MIT-BIH AF (atrial fibrillation detection) [medical] in the open CK format
result SOTA: MIT-BIH AR (heartbeat classification) [medical] in the open CK format
result SOTA: MIT-BIH AR (qrs complex detection) [medical] in the open CK format
result SOTA: MIT-BIH+BIDMC (congestive heart failure detection) [medical] in the open CK format
result SOTA: MIT-BIH+BIDMC (heartbeat classification) [medical] in the open CK format
result SOTA: MLDoc Zero-Shot English-to-French (cross-lingual document classification) [natural language processing] in the open CK format
result SOTA: MLDoc Zero-Shot English-to-German (cross-lingual document classification) [natural language processing] in the open CK format
result SOTA: MLDoc Zero-Shot English-to-Spanish (cross-lingual document classification) [natural language processing] in the open CK format
result SOTA: MMI (facial expression recognition) [computer vision] in the open CK format
result SOTA: MNIST (image clustering) [computer vision] in the open CK format
result SOTA: MNIST (unsupervised mnist) [graphs] in the open CK format
result SOTA: MNIST (unsupervised mnist) [methodology] in the open CK format
result SOTA: ModelNet40 (3d object recognition) [computer vision] in the open CK format
result SOTA: ModelNet40 (classification) [miscellaneous] in the open CK format
result SOTA: Moments in Time Dataset (multimodal activity recognition) [computer vision] in the open CK format
result SOTA: Monologue (multimodal emotion recognition) [speech] in the open CK format
result SOTA: MORPH (age estimation) [computer vision] in the open CK format
result SOTA: MORPH Album2 (age estimation) [computer vision] in the open CK format
result SOTA: MORPH Album2 (facial attribute classification) [computer vision] in the open CK format
result SOTA: MOT16 (online multi-object tracking) [computer vision] in the open CK format
result SOTA: Movementlibras (feature selection) [computer code] in the open CK format
result SOTA: MoveToBeacon (starcraft ii) [playing games] in the open CK format
result SOTA: MovieQA (video story qa) [computer vision] in the open CK format
result SOTA: MPED (emotion recognition) [speech] in the open CK format
result SOTA: MS ACADEMIC (node classification) [graphs] in the open CK format
result SOTA: MSNBC (entity disambiguation) [natural language processing] in the open CK format
result SOTA: MSNBC (entity linking) [natural language processing] in the open CK format
result SOTA: MSR Action3D (3d human action recognition) [computer vision] in the open CK format
result SOTA: MSR Action3D (3d human action recognition) [computer vision] in the open CK format
result SOTA: MSR Action3D (hand gesture recognition) [computer vision] in the open CK format
result SOTA: MSR Action3D (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: MSR Action3D (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: MSR Daily Activity3D dataset (multimodal activity recognition) [computer vision] in the open CK format
result SOTA: MSR-VTT (video retrieval) [computer vision] in the open CK format
result SOTA: MSRA (chinese named entity recognition) [natural language processing] in the open CK format
result SOTA: MSRA (chinese word segmentation) [natural language processing] in the open CK format
result SOTA: MSRA Hands (hand pose estimation) [adversarial] in the open CK format
result SOTA: MSRA Hands (hand pose estimation) [computer vision] in the open CK format
result SOTA: MSRC-21 (per-class) (semantic segmentation) [computer vision] in the open CK format
result SOTA: MSRC-21 (per-pixel) (semantic segmentation) [computer vision] in the open CK format
result SOTA: MSRVTT-QA (visual question answering) [computer vision] in the open CK format
result SOTA: MSU-MFSD (face anti-spoofing) [computer vision] in the open CK format
result SOTA: MSVD (video retrieval) [computer vision] in the open CK format
result SOTA: MSVD-QA (visual question answering) [computer vision] in the open CK format
result SOTA: mtrl-auto-uav (autonomous flight (dense forest)) [miscellaneous] in the open CK format
result SOTA: MuJoCo (multivariate time series forecasting) [time series] in the open CK format
result SOTA: MuJoCo (multivariate time series imputation) [time series] in the open CK format
result SOTA: Multi-day Continuous BP Prediction (blood pressure estimation) [medical] in the open CK format
result SOTA: Multi-day Continuous BP Prediction (blood pressure estimation) [medical] in the open CK format
result SOTA: Multi-THUMOS (action detection) [computer vision] in the open CK format
result SOTA: Mushroom (multi-armed bandits) [miscellaneous] in the open CK format
result SOTA: N-UCLA (3d human action recognition) [computer vision] in the open CK format
result SOTA: N-UCLA (3d human action recognition) [computer vision] in the open CK format
result SOTA: N-UCLA (hand gesture recognition) [computer vision] in the open CK format
result SOTA: N-UCLA (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: N-UCLA (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: N3-Reuters-128 (entity linking) [natural language processing] in the open CK format
result SOTA: NB15-Backdoor (network intrusion detection) [miscellaneous] in the open CK format
result SOTA: NC1 (graph classification) [graphs] in the open CK format
result SOTA: NCBI-disease (named entity recognition) [natural language processing] in the open CK format
result SOTA: NCI-123 (graph classification) [graphs] in the open CK format
result SOTA: NCI-83 (graph classification) [graphs] in the open CK format
result SOTA: NCI33 (graph classification) [graphs] in the open CK format
result SOTA: NLVR (visual reasoning) [reasoning] in the open CK format
result SOTA: NOCS-REAL275 (6d pose estimation using rgb) [adversarial] in the open CK format
result SOTA: NOCS-REAL275 (6d pose estimation) [adversarial] in the open CK format
result SOTA: Noun Phrase Canonicalization (open knowledge graph canonicalization) [knowledge base] in the open CK format
result SOTA: NTU Hand Digit (gesture-to-gesture translation) [computer vision] in the open CK format
result SOTA: NTU RGB+D (action recognition in videos) [computer vision] in the open CK format
result SOTA: NTU RGB+D (action recognition in videos) [computer vision] in the open CK format
result SOTA: NTU RGB+D (action recognition in videos) [computer vision] in the open CK format
result SOTA: NTU RGB+D 120 (action recognition in videos) [computer vision] in the open CK format
result SOTA: NTU RGB+D 120 (action recognition in videos) [computer vision] in the open CK format
result SOTA: NTU RGB+D 120 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Numenta Anomaly Benchmark (anomaly detection) [graphs] in the open CK format
result SOTA: Nurse Care Activity Recognition Challenge (multimodal activity recognition) [computer vision] in the open CK format
result SOTA: NUS-WIDE (image retrieval) [computer vision] in the open CK format
result SOTA: NYU Depth v2 (instance segmentation) [computer vision] in the open CK format
result SOTA: NYU Depth v2 (real-time semantic segmentation) [computer vision] in the open CK format
result SOTA: NYU Depth v2 (scene segmentation) [computer vision] in the open CK format
result SOTA: NYU Depth v2 (semantic segmentation) [computer vision] in the open CK format
result SOTA: NYU Hands (hand pose estimation) [adversarial] in the open CK format
result SOTA: NYU Hands (hand pose estimation) [computer vision] in the open CK format
result SOTA: OccludedLINEMOD (6d pose estimation using rgb) [adversarial] in the open CK format
result SOTA: OCCLUSION (6d pose estimation using rgb) [adversarial] in the open CK format
result SOTA: Office-31 (domain adaptation) [computer vision] in the open CK format
result SOTA: Office-31 (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: Office-Home (transfer learning) [computer vision] in the open CK format
result SOTA: Office-Home (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: OKE-2015 (entity linking) [natural language processing] in the open CK format
result SOTA: OKE-2016 (entity linking) [natural language processing] in the open CK format
result SOTA: Olivetti Faces 5 Image (face recognition) [computer vision] in the open CK format
result SOTA: OMNIGLOT (multi-task learning) [computer vision] in the open CK format
result SOTA: OMNIGLOT - 1-Shot Learning (few-shot camera-adaptive color constancy) [computer vision] in the open CK format
result SOTA: OMNIGLOT - 1-Shot Learning (few-shot image classification) [computer vision] in the open CK format
result SOTA: OMNIGLOT - 1-Shot Learning (few-shot image classification) [computer vision] in the open CK format
result SOTA: OMNIGLOT - 5-Shot Learning (few-shot camera-adaptive color constancy) [computer vision] in the open CK format
result SOTA: OMNIGLOT - 5-Shot Learning (few-shot image classification) [computer vision] in the open CK format
result SOTA: OMNIGLOT - 5-Shot Learning (few-shot image classification) [computer vision] in the open CK format
result SOTA: OntoNotes 4 (chinese named entity recognition) [natural language processing] in the open CK format
result SOTA: Ontonotes v5 (English) (named entity recognition) [natural language processing] in the open CK format
result SOTA: ontontoes chinese v5 (named entity recognition) [natural language processing] in the open CK format
result SOTA: Optical Recognition of Handwritten Digits (classification) [miscellaneous] in the open CK format
result SOTA: OQMD v1.2 (band gap) [graphs] in the open CK format
result SOTA: OQMD v1.2 (formation energy) [graphs] in the open CK format
result SOTA: OQMD v1.2 (materials screening) [graphs] in the open CK format
result SOTA: OQMD v1.2 (total magnetization) [graphs] in the open CK format
result SOTA: OTB-100 (visual tracking) [computer vision] in the open CK format
result SOTA: PA-100K (pedestrian attribute recognition) [miscellaneous] in the open CK format
result SOTA: PACS (domain generalization) [computer vision] in the open CK format
result SOTA: Paris StreetView (image inpainting) [adversarial] in the open CK format
result SOTA: Paris StreetView (image inpainting) [computer vision] in the open CK format
result SOTA: PASCAL Context (semantic segmentation) [computer vision] in the open CK format
result SOTA: PASCAL Face (face detection) [computer vision] in the open CK format
result SOTA: PASCAL VOC 2012 val (semantic segmentation) [computer vision] in the open CK format
result SOTA: PASCAL VOC 2012 val (unsupervised semantic segmentation) [computer vision] in the open CK format
result SOTA: PASCAL-Person-Part (multi-human parsing) [computer vision] in the open CK format
result SOTA: PCBA (drug discovery) [medical] in the open CK format
result SOTA: PE-CAD FPRED (pulmonary embolism detection) [medical] in the open CK format
result SOTA: PEMS-SF (multivariate time series imputation) [time series] in the open CK format
result SOTA: Penn Treebank (chunking) [natural language processing] in the open CK format
result SOTA: PeopleArt (object detection) [computer vision] in the open CK format
result SOTA: PETA (pedestrian attribute recognition) [miscellaneous] in the open CK format
result SOTA: Photo-Art-50 (depiction invariant object recognition) [computer vision] in the open CK format
result SOTA: Physionet 2017 Atrial Fibrillation (time series classification) [time series] in the open CK format
result SOTA: PhysioNet Challenge 2012 (multivariate time series forecasting) [time series] in the open CK format
result SOTA: PhysioNet Challenge 2012 (multivariate time series imputation) [time series] in the open CK format
result SOTA: Pima (classification) [miscellaneous] in the open CK format
result SOTA: PKU-MMD (3d human action recognition) [computer vision] in the open CK format
result SOTA: PKU-MMD (3d human action recognition) [computer vision] in the open CK format
result SOTA: PKU-MMD (hand gesture recognition) [computer vision] in the open CK format
result SOTA: PKU-MMD (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: PKU-MMD (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: Places2 val (image inpainting) [adversarial] in the open CK format
result SOTA: Places2 val (image inpainting) [computer vision] in the open CK format
result SOTA: PolyAI OpenSubtitles (conversational response selection) [natural language processing] in the open CK format
result SOTA: Polyvore (recommendation systems) [miscellaneous] in the open CK format
result SOTA: PoseTrack2017 (multi-person pose estimation) [adversarial] in the open CK format
result SOTA: Potsdam (unsupervised semantic segmentation) [computer vision] in the open CK format
result SOTA: Potsdam-3 (unsupervised semantic segmentation) [computer vision] in the open CK format
result SOTA: PPG-DaLiA (heart rate estimation) [medical] in the open CK format
result SOTA: PPG-DaLiA (heart rate estimation) [medical] in the open CK format
result SOTA: PPI (link prediction) [graphs] in the open CK format
result SOTA: PreSIL to KITTI (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: PRID2011 (person re-identification) [computer vision] in the open CK format
result SOTA: PTB dataset, ECG lead II (myocardial infarction detection) [medical] in the open CK format
result SOTA: Pubmed (graph clustering) [graphs] in the open CK format
result SOTA: Pubmed (link prediction) [graphs] in the open CK format
result SOTA: Q2Q Arabic Benchmark (question similarity) [natural language processing] in the open CK format
result SOTA: QM9 (drug discovery) [medical] in the open CK format
result SOTA: QT (qrs complex detection) [medical] in the open CK format
result SOTA: Query Wellformedness (query wellformedness) [natural language processing] in the open CK format
result SOTA: Quora Question Pairs (natural language inference) [natural language processing] in the open CK format
result SOTA: RAP (pedestrian attribute recognition) [miscellaneous] in the open CK format
result SOTA: RCV1-v2 (multi-label text classification) [natural language processing] in the open CK format
result SOTA: Real-World Affective Faces (facial expression recognition) [computer vision] in the open CK format
result SOTA: Red Wine (classification) [miscellaneous] in the open CK format
result SOTA: Replay Mobile (face anti-spoofing) [computer vision] in the open CK format
result SOTA: Replay Mobile (face presentation attack detection) [computer vision] in the open CK format
result SOTA: Restricted (grammatical error correction) [natural language processing] in the open CK format
result SOTA: Resume NER (chinese named entity recognition) [natural language processing] in the open CK format
result SOTA: Reuters-21578 (multi-label text classification) [natural language processing] in the open CK format
result SOTA: Reverb (question answering) [natural language processing] in the open CK format
result SOTA: Room2Room (vision-language navigation) [computer vision] in the open CK format
result SOTA: RT-GENE (gaze estimation) [computer vision] in the open CK format
result SOTA: RumourEval (stance detection) [natural language processing] in the open CK format
result SOTA: RWTH-PHOENIX-Weather 2014 (sign language recognition) [computer vision] in the open CK format
result SOTA: RWTH-PHOENIX-Weather 2014 T (sign language translation) [computer vision] in the open CK format
result SOTA: SBD (edge detection) [computer vision] in the open CK format
result SOTA: SBU (3d human action recognition) [computer vision] in the open CK format
result SOTA: SBU (3d human action recognition) [computer vision] in the open CK format
result SOTA: SBU (hand gesture recognition) [computer vision] in the open CK format
result SOTA: SBU (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: SBU (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: Scan2CAD (3d reconstruction) [computer vision] in the open CK format
result SOTA: ScanNet (scene recognition) [computer vision] in the open CK format
result SOTA: ScanNet (scene segmentation) [computer vision] in the open CK format
result SOTA: ScanNet (semantic segmentation) [computer vision] in the open CK format
result SOTA: ScanNetV2 (semantic segmentation) [computer vision] in the open CK format
result SOTA: SciERC (named entity recognition) [natural language processing] in the open CK format
result SOTA: SCUT-FBP (facial beauty prediction) [computer vision] in the open CK format
result SOTA: SCv1 (sarcasm detection) [natural language processing] in the open CK format
result SOTA: Second dialogue state tracking challenge (dialogue state tracking) [natural language processing] in the open CK format
result SOTA: SEED-IV (eeg) [medical] in the open CK format
result SOTA: SEED-IV (emotion recognition) [speech] in the open CK format
result SOTA: SEMAINE (emotion recognition in conversation) [speech] in the open CK format
result SOTA: Semantic3D (semantic segmentation) [computer vision] in the open CK format
result SOTA: SemanticKITTI (3d semantic segmentation) [computer vision] in the open CK format
result SOTA: SemanticKITTI (real-time 3d semantic segmentation) [computer vision] in the open CK format
result SOTA: SemEval 2007 Task 17 (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: SemEval 2007 Task 7 (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: SemEval 2013 Task 12 (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: SemEval 2015 Task 13 (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: SemEval 2017 Task 4-A (sentiment analysis) [natural language processing] in the open CK format
result SOTA: SemEvalCQA (question answering) [natural language processing] in the open CK format
result SOTA: SensEval 2 (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: SensEval 2 Lexical Sample (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: SensEval 3 Lexical Sample (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: SensEval 3 Task 1 (word sense disambiguation) [natural language processing] in the open CK format
result SOTA: Senz3D (gesture-to-gesture translation) [computer vision] in the open CK format
result SOTA: Set5-2x (super-resolution) [computer vision] in the open CK format
result SOTA: SFU Review Corpus (negation scope resolution) [natural language processing] in the open CK format
result SOTA: SFU Review Corpus (speculation scope resolution) [natural language processing] in the open CK format
result SOTA: ShanghaiTech (crowd counting) [computer vision] in the open CK format
result SOTA: ShanghaiTech A (crowd counting) [computer vision] in the open CK format
result SOTA: ShanghaiTech B (crowd counting) [computer vision] in the open CK format
result SOTA: ShapeNet (semantic segmentation) [computer vision] in the open CK format
result SOTA: ShapeNet (single-view 3d reconstruction) [computer vision] in the open CK format
result SOTA: ShapeNet Car (novel view synthesis) [computer vision] in the open CK format
result SOTA: ShapeNet Chair (novel view synthesis) [computer vision] in the open CK format
result SOTA: ShapeNet-Part (3d part segmentation) [computer vision] in the open CK format
result SOTA: SHREC 2017 track on 3D Hand Gesture Recognition (3d human action recognition) [computer vision] in the open CK format
result SOTA: SHREC 2017 track on 3D Hand Gesture Recognition (3d human action recognition) [computer vision] in the open CK format
result SOTA: SHREC 2017 track on 3D Hand Gesture Recognition (hand gesture recognition) [computer vision] in the open CK format
result SOTA: SHREC 2017 track on 3D Hand Gesture Recognition (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: SHREC 2017 track on 3D Hand Gesture Recognition (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: SighanNER (chinese named entity recognition) [natural language processing] in the open CK format
result SOTA: SIM10K to BDD100K (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: SIM10K to Cityscapes (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: SimpleQuestions (question answering) [natural language processing] in the open CK format
result SOTA: SIXray (object detection) [computer vision] in the open CK format
result SOTA: SkyScapes-Dense (semantic segmentation) [computer vision] in the open CK format
result SOTA: SkyScapes-Lane (semantic segmentation) [computer vision] in the open CK format
result SOTA: SLAM 2018 (language acquisition) [natural language processing] in the open CK format
result SOTA: Slashdot (multi-label text classification) [natural language processing] in the open CK format
result SOTA: Sleep-EDF (sleep stage detection) [medical] in the open CK format
result SOTA: Sleep-EDF-SC (multimodal sleep stage detection) [medical] in the open CK format
result SOTA: Sleep-EDF-ST (multimodal sleep stage detection) [medical] in the open CK format
result SOTA: SNIPS (intent detection) [natural language processing] in the open CK format
result SOTA: SNIPS (slot filling) [natural language processing] in the open CK format
result SOTA: Social media (part-of-speech tagging) [natural language processing] in the open CK format
result SOTA: SOFA (direction of arrival estimation) [audio] in the open CK format
result SOTA: SoftBioSearch (person retrieval) [computer vision] in the open CK format
result SOTA: Something-Something V1 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Something-Something V1 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Something-Something V1 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Something-Something V2 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Something-Something V2 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Something-Something V2 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Sonar (classification) [miscellaneous] in the open CK format
result SOTA: Sonar (feature selection) [computer code] in the open CK format
result SOTA: SOTS Indoor (image dehazing) [computer vision] in the open CK format
result SOTA: SOTS Outdoor (image dehazing) [computer vision] in the open CK format
result SOTA: Species-800 (named entity recognition) [natural language processing] in the open CK format
result SOTA: Spect (feature selection) [computer code] in the open CK format
result SOTA: spider (semantic parsing) [natural language processing] in the open CK format
result SOTA: Sports-1M (action recognition in videos) [computer vision] in the open CK format
result SOTA: Sports-1M (action recognition in videos) [computer vision] in the open CK format
result SOTA: Sports-1M (action recognition in videos) [computer vision] in the open CK format
result SOTA: Stanford Cars (image classification) [computer vision] in the open CK format
result SOTA: Stanford Sleep Cohort (SSC) (spindle detection) [medical] in the open CK format
result SOTA: STM-corpus (scientific concept extraction) [natural language processing] in the open CK format
result SOTA: Street Scene (video-to-video synthesis) [computer vision] in the open CK format
result SOTA: street2shop - topwear (image retrieval) [computer vision] in the open CK format
result SOTA: Sudoko 9x9 (game of suduko) [playing games] in the open CK format
result SOTA: SumMe (video compressive sensing) [computer vision] in the open CK format
result SOTA: SUN-RGBD (scene segmentation) [computer vision] in the open CK format
result SOTA: SUN-RGBD (semantic segmentation) [computer vision] in the open CK format
result SOTA: SUN360 (outdoor light source estimation) [computer vision] in the open CK format
result SOTA: SunYs (pulmonary artery–vein classification) [computer vision] in the open CK format
result SOTA: Surrey-cEEGGrid (multimodal sleep stage detection) [medical] in the open CK format
result SOTA: Surrey-PSG (multimodal sleep stage detection) [medical] in the open CK format
result SOTA: SVNH-to-MNIST (domain adaptation) [computer vision] in the open CK format
result SOTA: SWAG (question answering) [natural language processing] in the open CK format
result SOTA: swb_hub_500 WER fullSWBCH (speech recognition) [speech] in the open CK format
result SOTA: Switchboard (300hr) (speech recognition) [speech] in the open CK format
result SOTA: Switchboard + Hub500 (speech recognition) [speech] in the open CK format
result SOTA: Switchboard corpus (dialogue act classification) [natural language processing] in the open CK format
result SOTA: Synscapes to BDD100K (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: Synthia Novel View Synthesis (novel view synthesis) [computer vision] in the open CK format
result SOTA: SYNTHIA-CVPR’16 (semantic segmentation) [computer vision] in the open CK format
result SOTA: SYNTHIE (graph classification) [graphs] in the open CK format
result SOTA: SYSU 3D (3d human action recognition) [computer vision] in the open CK format
result SOTA: SYSU 3D (3d human action recognition) [computer vision] in the open CK format
result SOTA: SYSU 3D (hand gesture recognition) [computer vision] in the open CK format
result SOTA: SYSU 3D (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: SYSU 3D (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: T-LESS (6d pose estimation using rgb) [adversarial] in the open CK format
result SOTA: TAC-KBP 2010 (entity linking) [natural language processing] in the open CK format
result SOTA: TAC2010 (entity disambiguation) [natural language processing] in the open CK format
result SOTA: TCD-TIMIT corpus (mixed-speech) (speech enhancement) [speech] in the open CK format
result SOTA: TCD-TIMIT corpus (mixed-speech) (speech separation) [speech] in the open CK format
result SOTA: Teaching Assistant Evaluation (classification) [miscellaneous] in the open CK format
result SOTA: Teaching Assistant Evaluation (classification) [miscellaneous] in the open CK format
result SOTA: TempEval-3 (temporal information extraction) [natural language processing] in the open CK format
result SOTA: The ARRAU Corpus (abstract anaphora resolution) [natural language processing] in the open CK format
result SOTA: The China Physiological Signal Challenge 2018 (arrhythmia detection) [medical] in the open CK format
result SOTA: The Extended Cohn-Kanade Dataset(CK+) (facial expression recognition) [computer vision] in the open CK format
result SOTA: The PhysioNet Computing in Cardiology Challenge 2017 (arrhythmia detection) [medical] in the open CK format
result SOTA: THUMOS' 14 (action detection) [computer vision] in the open CK format
result SOTA: THUMOS’14 (action recognition in videos) [computer vision] in the open CK format
result SOTA: THUMOS’14 (action recognition in videos) [computer vision] in the open CK format
result SOTA: THUMOS’14 (action recognition in videos) [computer vision] in the open CK format
result SOTA: THUMOS’14 (temporal action localization) [computer vision] in the open CK format
result SOTA: THUMOS’14 (temporal action localization) [computer vision] in the open CK format
result SOTA: Thyroid (anomaly detection) [graphs] in the open CK format
result SOTA: Thyroid (classification) [miscellaneous] in the open CK format
result SOTA: TimeBank (temporal information extraction) [natural language processing] in the open CK format
result SOTA: TIMIT (speech recognition) [speech] in the open CK format
result SOTA: Total Capture (3d absolute human pose estimation) [computer vision] in the open CK format
result SOTA: Total Capture (3d absolute human pose estimation) [natural language processing] in the open CK format
result SOTA: TrackingNet (action recognition in videos) [computer vision] in the open CK format
result SOTA: TrackingNet (visual object tracking) [computer vision] in the open CK format
result SOTA: TrailerFaces (video generation) [computer vision] in the open CK format
result SOTA: TREC Robust04 (ad-hoc information retrieval) [natural language processing] in the open CK format
result SOTA: TREC-50 (text classification) [natural language processing] in the open CK format
result SOTA: TREC-PM (information retrieval) [natural language processing] in the open CK format
result SOTA: Tsinghua-Tencent 100K (traffic sign recognition) [miscellaneous] in the open CK format
result SOTA: TuSimple (lane detection) [miscellaneous] in the open CK format
result SOTA: TvSum (video compressive sensing) [computer vision] in the open CK format
result SOTA: UCF --> HMDB (full) (domain adaptation) [computer vision] in the open CK format
result SOTA: UCF CC 50 (crowd counting) [computer vision] in the open CK format
result SOTA: UCF101 (action recognition in videos) [computer vision] in the open CK format
result SOTA: UCF101 (action recognition in videos) [computer vision] in the open CK format
result SOTA: UCF101 (action recognition in videos) [computer vision] in the open CK format
result SOTA: UCF101 (video frame interpolation) [computer vision] in the open CK format
result SOTA: UCI localization data (multivariate time series imputation) [time series] in the open CK format
result SOTA: UCSD (abnormal event detection in video) [graphs] in the open CK format
result SOTA: UD (part-of-speech tagging) [natural language processing] in the open CK format
result SOTA: Udacity (steering control) [computer vision] in the open CK format
result SOTA: UK CF trust (disease trajectory forecasting) [medical] in the open CK format
result SOTA: Ultra Video Group HD - 4x upscaling (video super-resolution) [computer vision] in the open CK format
result SOTA: UnoViS_auto2012 (ecg denoising) [medical] in the open CK format
result SOTA: Unrestricted (grammatical error correction) [natural language processing] in the open CK format
result SOTA: UPenn Action (3d human action recognition) [computer vision] in the open CK format
result SOTA: UPenn Action (3d human action recognition) [computer vision] in the open CK format
result SOTA: UPenn Action (hand gesture recognition) [computer vision] in the open CK format
result SOTA: UPenn Action (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: UPenn Action (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: USHCN-Daily (multivariate time series forecasting) [time series] in the open CK format
result SOTA: UT Multi-view (gaze estimation) [computer vision] in the open CK format
result SOTA: UT-Kinect (3d human action recognition) [computer vision] in the open CK format
result SOTA: UT-Kinect (3d human action recognition) [computer vision] in the open CK format
result SOTA: UT-Kinect (hand gesture recognition) [computer vision] in the open CK format
result SOTA: UT-Kinect (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: UT-Kinect (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: UTD-MHAD (action recognition in videos) [computer vision] in the open CK format
result SOTA: UTD-MHAD (action recognition in videos) [computer vision] in the open CK format
result SOTA: UTD-MHAD (action recognition in videos) [computer vision] in the open CK format
result SOTA: UTD-MHAD (multimodal activity recognition) [computer vision] in the open CK format
result SOTA: UTKFace (age estimation) [computer vision] in the open CK format
result SOTA: UWA3D (3d human action recognition) [computer vision] in the open CK format
result SOTA: UWA3D (3d human action recognition) [computer vision] in the open CK format
result SOTA: UWA3D (hand gesture recognition) [computer vision] in the open CK format
result SOTA: UWA3D (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: UWA3D (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: V-SNLI (natural language inference) [natural language processing] in the open CK format
result SOTA: Varying-view RGB-D Action-Skeleton (3d human action recognition) [computer vision] in the open CK format
result SOTA: Varying-view RGB-D Action-Skeleton (3d human action recognition) [computer vision] in the open CK format
result SOTA: Varying-view RGB-D Action-Skeleton (hand gesture recognition) [computer vision] in the open CK format
result SOTA: Varying-view RGB-D Action-Skeleton (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: Varying-view RGB-D Action-Skeleton (skeleton based action recognition) [computer vision] in the open CK format
result SOTA: Vehicle Silhouettes (classification) [miscellaneous] in the open CK format
result SOTA: Vehicle Silhouettes (classification) [miscellaneous] in the open CK format
result SOTA: Vehicule (feature selection) [computer code] in the open CK format
result SOTA: VGGFace2 (2.3M) (face recognition) [computer vision] in the open CK format
result SOTA: VggFace2 (facial inpainting) [computer vision] in the open CK format
result SOTA: Vid4 - 4x upscaling (video super-resolution) [computer vision] in the open CK format
result SOTA: Vimeo90k (video frame interpolation) [computer vision] in the open CK format
result SOTA: VIRAT Ground 2.0 (action recognition in videos) [computer vision] in the open CK format
result SOTA: VIRAT Ground 2.0 (action recognition in videos) [computer vision] in the open CK format
result SOTA: VIRAT Ground 2.0 (action recognition in videos) [computer vision] in the open CK format
result SOTA: Virtual KITTI to BDD100K (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: VisDA2017 (domain adaptation) [computer vision] in the open CK format
result SOTA: VisDA2017 (unsupervised domain adaptation) [computer vision] in the open CK format
result SOTA: Visual Dialog v0.9 (common sense reasoning) [reasoning] in the open CK format
result SOTA: Visual Dialog v1.0 (common sense reasoning) [reasoning] in the open CK format
result SOTA: Visual Genome (object detection) [computer vision] in the open CK format
result SOTA: Visual Genome (pairs) (visual question answering) [computer vision] in the open CK format
result SOTA: Visual Genome (phrase grounding) [natural language processing] in the open CK format
result SOTA: Visual Genome (scene graph generation) [computer vision] in the open CK format
result SOTA: Visual Genome (subjects) (visual question answering) [computer vision] in the open CK format
result SOTA: Visual Question Generation (question generation) [natural language processing] in the open CK format
result SOTA: VIVA Hand Gestures Dataset (action recognition in videos) [computer vision] in the open CK format
result SOTA: VIVA Hand Gestures Dataset (action recognition in videos) [computer vision] in the open CK format
result SOTA: VIVA Hand Gestures Dataset (action recognition in videos) [computer vision] in the open CK format
result SOTA: VIVA Hand Gestures Dataset (hand-gesture recognition) [computer vision] in the open CK format
result SOTA: VIVA Hand Gestures Dataset (hand-gesture recognition) [computer vision] in the open CK format
result SOTA: VOT2016 (action recognition in videos) [computer vision] in the open CK format
result SOTA: VOT2016 (visual object tracking) [computer vision] in the open CK format
result SOTA: VOT2017 (action recognition in videos) [computer vision] in the open CK format
result SOTA: VOT2017 (visual object tracking) [computer vision] in the open CK format
result SOTA: VOT2017/18 (action recognition in videos) [computer vision] in the open CK format
result SOTA: VOT2017/18 (visual object tracking) [computer vision] in the open CK format
result SOTA: VOT2019 (action recognition in videos) [computer vision] in the open CK format
result SOTA: VOT2019 (visual object tracking) [computer vision] in the open CK format
result SOTA: Vowel (classification) [miscellaneous] in the open CK format
result SOTA: Vowel (feature selection) [computer code] in the open CK format
result SOTA: VoxCeleb1 - 1-shot learning (talking head generation) [computer vision] in the open CK format
result SOTA: VoxCeleb1 - 1-shot learning (talking head generation) [natural language processing] in the open CK format
result SOTA: VoxCeleb1 - 32-shot learning (talking head generation) [computer vision] in the open CK format
result SOTA: VoxCeleb1 - 32-shot learning (talking head generation) [natural language processing] in the open CK format
result SOTA: VoxCeleb1 - 8-shot learning (talking head generation) [computer vision] in the open CK format
result SOTA: VoxCeleb1 - 8-shot learning (talking head generation) [natural language processing] in the open CK format
result SOTA: VoxCeleb2 - 1-shot learning (talking head generation) [computer vision] in the open CK format
result SOTA: VoxCeleb2 - 1-shot learning (talking head generation) [natural language processing] in the open CK format
result SOTA: VoxCeleb2 - 32-shot learning (talking head generation) [computer vision] in the open CK format
result SOTA: VoxCeleb2 - 32-shot learning (talking head generation) [natural language processing] in the open CK format
result SOTA: VoxCeleb2 - 8-shot learning (talking head generation) [computer vision] in the open CK format
result SOTA: VoxCeleb2 - 8-shot learning (talking head generation) [natural language processing] in the open CK format
result SOTA: VoxForge American-Canadian (accented speech recognition) [speech] in the open CK format
result SOTA: VoxForge Commonwealth (accented speech recognition) [speech] in the open CK format
result SOTA: VoxForge European (accented speech recognition) [speech] in the open CK format
result SOTA: VoxForge Indian (accented speech recognition) [speech] in the open CK format
result SOTA: VRD (scene graph generation) [computer vision] in the open CK format
result SOTA: WDBC (feature selection) [computer code] in the open CK format
result SOTA: WebFace (facial inpainting) [computer vision] in the open CK format
result SOTA: WebQSP-WD (entity linking) [natural language processing] in the open CK format
result SOTA: Weibo NER (chinese named entity recognition) [natural language processing] in the open CK format
result SOTA: WESAD (heart rate estimation) [medical] in the open CK format
result SOTA: WESAD (heart rate estimation) [medical] in the open CK format
result SOTA: WetLab (named entity recognition) [natural language processing] in the open CK format
result SOTA: WFLW (face alignment) [computer vision] in the open CK format
result SOTA: Wiki (link prediction) [graphs] in the open CK format
result SOTA: Wiki (node classification) [graphs] in the open CK format
result SOTA: WikiSQL (code generation) [computer code] in the open CK format
result SOTA: WikiSQL (sql-to-text) [computer code] in the open CK format
result SOTA: Wine (classification) [miscellaneous] in the open CK format
result SOTA: Wine (classification) [miscellaneous] in the open CK format
result SOTA: Wine (feature selection) [computer code] in the open CK format
result SOTA: Wisconsin Sleep Cohort (WSC) (spindle detection) [medical] in the open CK format
result SOTA: Wizard-of-Oz (dialogue state tracking) [natural language processing] in the open CK format
result SOTA: WMCA (face presentation attack detection) [computer vision] in the open CK format
result SOTA: WMT 2017 English-Latvian (machine translation) [natural language processing] in the open CK format
result SOTA: WMT 2017 Latvian-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT 2018 English-Estonian (machine translation) [natural language processing] in the open CK format
result SOTA: WMT 2018 English-Finnish (machine translation) [natural language processing] in the open CK format
result SOTA: WMT 2018 Estonian-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT 2018 Finnish-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2014 French-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2014 German-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2015 English-German (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2015 English-Russian (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2016 Czech-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2016 English-Czech (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2016 Finnish-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2016 German-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2016 Romanian-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2016 Russian-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2017 Chinese-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2017 Finnish-English (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2019 English-Lithuanian (machine translation) [natural language processing] in the open CK format
result SOTA: WMT2019 Finnish-English (machine translation) [natural language processing] in the open CK format
result SOTA: WN18RR (knowledge graph completion) [knowledge base] in the open CK format
result SOTA: WNED-CWEB (entity disambiguation) [natural language processing] in the open CK format
result SOTA: WNED-WIKI (entity disambiguation) [natural language processing] in the open CK format
result SOTA: WSJ eval92 (speech recognition) [speech] in the open CK format
result SOTA: WSJ eval93 (speech recognition) [speech] in the open CK format
result SOTA: Xiph HD - 4x upscaling (video super-resolution) [computer vision] in the open CK format
result SOTA: Yahoo Questions (text generation) [natural language processing] in the open CK format
result SOTA: Yahoo! Answers (language modelling) [natural language processing] in the open CK format
result SOTA: YahooCQA (question answering) [natural language processing] in the open CK format
result SOTA: YahooMusic (recommendation systems) [miscellaneous] in the open CK format
result SOTA: YCB-Video (6d pose estimation using rgb) [adversarial] in the open CK format
result SOTA: YCB-Video (6d pose estimation) [adversarial] in the open CK format
result SOTA: Yeast (classification) [miscellaneous] in the open CK format
result SOTA: Yelp-5 (document classification) [natural language processing] in the open CK format
result SOTA: Yelp15 (language modelling) [natural language processing] in the open CK format
result SOTA: York Urban Dataset (horizon line estimation) [computer vision] in the open CK format
result SOTA: You Snooze You Win - The PhysioNet Computing in Cardiology Challenge 2018 (sleep arousal detection) [medical] in the open CK format
result SOTA: YouTube (node classification) [graphs] in the open CK format
result SOTA: YouTube (video object segmentation) [computer vision] in the open CK format
result SOTA: YouTube Dancing (video-to-video synthesis) [computer vision] in the open CK format
result SOTA: YouTube-8M (video classification) [computer vision] in the open CK format
result SOTA: YouTube-VOS (action recognition in videos) [computer vision] in the open CK format
result SOTA: YouTube-VOS (visual object tracking) [computer vision] in the open CK format
result SOTA: Zoo (classification) [miscellaneous] in the open CK format
result SOTA: Zoo (classification) [miscellaneous] in the open CK format
result SOTA: Zoo (feature selection) [computer code] in the open CK format
result SOTA:  SEED (eeg) [medical] in the open CK format
result Testing crowd-experiments (auto/crowd-tune GCC compiler flags (minimize execution time))
result Testing crowd-experiments (auto/crowd-tune GCC compiler flags (minimize execution time, do not degrade code size))
result Testing crowd-experiments (auto/crowd-tune LLVM compiler flags (minimize execution time))
result Testing crowd-experiments (auto/crowd-tune LLVM compiler flags (minimize execution time, do not degrade code size))
result Testing crowd-experiments (auto/crowd-tune OpenCL-based CLBlast (GFLOPs))
result Testing crowd-experiments (CK wrapper for OpenCL bug reports from Imperial)
result Testing crowd-experiments (crowd-benchmark DNN libraries and models (Caffe - dev))
result Testing crowd-experiments (crowd-benchmark DNN libraries and models (Caffe2))
result Testing crowd-experiments (crowd-benchmark DNN libraries and models (TensorFlow))
result Testing crowd-experiments (crowd-benchmark DNN libraries and models (training - on-going))
result Testing crowd-experiments (crowd-benchmark DNN libraries and models using mobile devices)
result Testing crowd-experiments (crowd-benchmark DNN libraries and models)
result Testing crowd-experiments (crowd-benchmark shared workloads via ARM WA framework)
result Testing crowd-experiments (crowdsource modeling of program behavior)
result Testing crowd-experiments (Open ACM ReQuEST @ ASPLOS'18 tournament (image classification))