General

open-data-registry aws-pds sustainability earth observation agriculture geospatial life sciences climate genomic weather meteorological satellite imagery genetic biology environmental machine learning bioinformatics natural resource imaging cancer natural language processing hacktoberfest deep learning oceans whole genome sequencing mapping coastal image processing biodiversity health atmosphere elevation covid-19 cog strides neuroscience global cities coronavirus lidar 神经影像学 open source software ecosystems climate model 水 neurobiology archives aerial imagery land transcriptomics air quality astronomy csv urban energy food security internet bam parquet continuously operating reference station - cors gps homo sapiens conservation fastq analytics encyclopedic stac cell biology cell imaging broadcast ephemeris medicine gnss gene expression census nara solar json infrastructure robotics cyber security earthquakes chemistry biotech blueprint demography signal processing labeled tutorial ice reference index magnetic resonance imaging molecule protein vcf 数据science mus musculus python transportation mlops genetic maps 1940 census multimedia planetary biomolecular modeling 洪水 video neurophysiology regulatory microscopy statistics computer security marine navigation electron microscopy geoscience population genetics osm population chemical biology fasta civic digital preservation genelab reproducibility-challenge smd ai commerce survey broadband molecular docking demographics short read sequencing long read sequencing bathymetry nifti sars amino acid seismology government records market data copyright monitoring blockchain digital forensics financial markets us-dc metadata computer forensics traffic epigenomics metagenomics fluorescence imaging genome wide association study fast5 mers 数据manipulation music events ml pipelines electrophysiology xgboost free software source code deeplearning research space biology complaints speech processing covid high-throughput imaging segmentation mining software repositories virus culture cloud computing museum tiles cmip5 autism spectrum disorder text analysis space weather molecular dynamics cram live song identification hiring malware music features dataset pediatric cultural preservation timho benchmark wildlife structural biology mixed file dataset 数据center msa pharmaceutical geophysics privacy near-surface specific humidity 数据visualization economics near-surface air temperature recombination maps tertiary analysis xml structural variation geothermal x-ray tomography loftee vep emotion trading organelle national archives catalog ensemble learning radiation precipitation protein folding txt workload analysis seafloor openfold network traffic marine mammals microbiome computational fluid dynamics alchemical free energy calculations cover song identification 1950 census scholarly communication meta learning art 数据assimilation netcdf speaker identification protein template fisheries sqlite enzyme movies mining simulations alphafold automatic speech recognition turbulence industrial green aviation forecast marine 数据analytics media ukraine low-pressure turbine hydrography japanese hpc flask csi foldingathome cmip6 fewshot bitcoin acoustics ransomware cell painting histopathology variant annotation 数据science project whole exome sequencing intrusion detection 历史 kaggle education 数据cleaning 数据 github actions random forests medical python library mlflow-serving artificial-intelligence cml julia science streamlit bias snowflake mnist fastai continuous integration dagshub predictive analysis gradient boosting x-ray noaa cors network - ncn 数据pipelines keras codepeak gans bento ml mammography python pakage projects sdsd dialogpt bot sad http traffic data numeric arrays pil cognitive control scorecard 数据review titanic fdfwsf shap dsd scw wordle ai voice clone app instruction following heroku ai voice assistant unet latent diffusion models ai personal assistant video-object-segmentation disease eda cnn asv preverified tactical decision catboost toy pune escorts services pytorch2 jitter click test neural network social good new upcoming data science projects for 2020 tim ho quantitative mouse video-object-segmentatino 动态时间扭曲 snails 2023 data science collection repo ai planning tutorials neural search action video games machine nextjs corpus medical terminology pytest 数据frame vector database alzheimers document image type orchest movie discord vsdvsdvsdvssf chatgpt plugins dagshub as a my favourite data science tool unit testing weather impacts olympics extract mfccs prevention covid19 vaccine seo production optimization azure huggingface animals gradio deployment number recognition fdffwfwf 2022 data science related notes awesome list mri best pune escorts triathlon remote working file system bot bark voice clone individuals happy chat llama colab vaccine skimage master bark voice cloning ai voice cloning singapore cps wdl instruct chatgpt test product webscraping on food systesms reviewer recommendation sea vector embeddings ai4 sustainable agri-food adsadad asdsadsa -dsadsadsadasdasdasdasdasd imporoving logistics and optimizing routing obesity aws torchdata wav mlops zoomcamp moez code review jigsaw food search interpretability malware detection albumentations omdena-milan chapter mirrored from github repo neutral vector embedding database sdw baseline supermarket website scraping visualization africa transformers ditmodel engine semantic search nltk bark hebrew diabetes recipe fastapi news newreposistory for to learning - how dagshub works + 434

Task

disaster response classification object detection autonomous vehicles image classification vision information retrieval denoising machine translation anomaly detection time series forecasting semantic segmentation music information retrieval text classification language modelling activity recognition sentiment analysis speech recognition question answering face recognition text-to-image generation 3d human pose estimation reading comprehension depth estimation object classification real-time object detection zero-shot object detection face sketch synthesis text generation colorization face identification sequence-to-sequence language modeling salient object detection food recognition image generation video object segmentation object counting face reconstruction face reenactment transfer learning fine-grained image classification image-to-image translation medical image segmentation domain adaptation edge detection text-to-speech synthesis few-shot learning feature engineering object recognition automl news classification multi-label text classification domain generalization pose estimation visual tracking explainable artificial intelligence face verification autonomous driving time series natural language understanding chatbot named entity recognition object detection in aerial images object skeleton detection speech enhancement face model face detection table detection active learning license plate recognition video super-resolution text summarization clustering algorithms evaluation visual dialog matrix completion video semantic segmentation line segment detection vision-language navigation relational reasoning disparity estimation 3d face animation image clustering 3d action recognition panoptic segmentation scene understanding learning-to-rank region proposal robust object detection hand gesture recognition 3d absolute human pose estimation stereo matching aspect-based sentiment analysis drug discovery 3d instance segmentation genre classification single image dehazing interactive segmentation optical character recognition weather forecasting video description fine-grained visual recognition handwriting generation video question answering metric learning audio classification 3d semantic segmentation sign language translation image dehazing unsupervised anomaly detection image registration unsupervised image classification self-supervised learning action recognition text-to-sql vehicle re-identification video recognition 3d shape representation 3d shape reconstruction hand pose estimation image enhancement image super-resolution speech synthesis out-of-distribution detection scene graph detection unsupervised facial landmark detection passage retrieval self-supervised action recognition hand segmentation action localization object tracking open-domain question answering compressive sensing pedestrian detection quantization image quality assessment causal inference incremental learning 3d reconstruction anomaly detection in surveillance videos fake news detection age estimation network intrusion detection probabilistic deep learning stereo matching hand language identification dialogue state tracking scene segmentation image restoration weakly supervised object detection graph regression multimodal sentiment analysis imputation neural architecture search morphological analysis paraphrase identification video generation graph generation change point detection scene text detection motion capture image compression event-based vision misinformation 3d multi-person pose estimation cross-lingual transfer 动作检测 image matting answer selection word sense disambiguation dimensionality reduction brain tumor segmentation face presentation attack detection motion prediction stance detection image/document clustering action anticipation continuous control chinese named entity recognition table-to-text generation outlier detection entity typing content-based image retrieval graph embedding multi-person pose estimation image cropping fairness relation classification keypoint detection 摘要式的文字总结rization node classification conversational response selection super-resolution imitation learning face swapping sentence classification decision making structure from motion chinese reading comprehension spoken language understanding click-through rate prediction tokenization dialogue understanding gaussian processes face alignment community question answering fine-grained visual categorization partial domain adaptation cross-modal retrieval general reinforcement learning 3d pose estimation using rgbd slot filling multi-future trajectory prediction rectification chunking variational inference human detection video salient object detection music modeling text-image retrieval dependency parsing scene classification cross-lingual question answering transliteration compositional zero-shot learning text simplification bayesian inference autonomous navigation graph clustering multi-agent reinforcement learning action recognition in videos monocular 3d object detection node clustering contrastive learning lesion segmentation music classification ssim network pruning relation extraction paraphrase generation document ranking word embeddings keyword extraction federated learning synthetic-to-real translation face anti-spoofing program repair discourse parsing robotic grasping image captioning eeg visual navigation entity disambiguation nested named entity recognition semi-supervised video object segmentation math word problem solving weakly-supervised semantic segmentation intent classification 数据-to-text generation long-tail learning sign language recognition event extraction simultaneous localization and mapping structured prediction keyword spotting jpeg artifact correction covid- diagnosis multi-class classification action classification image retrieval zero-shot learning style transfer knowledge graph completion speaker diarization traffic sign recognition self-driving cars biomedical information retrieval weakly-supervised named entity recognition motion estimation depth completion real-time semantic segmentation visual odometry part-of-speech tagging animal pose estimation recommendation systems semantic textual similarity feature importance scene recognition 3d multi-object tracking eye tracking code search question generation video reconstruction cross-lingual ner 面部表达sion recognition semantic role labeling 数据augmentation visual question answering video classification community detection video prediction lesion classification unsupervised domain adaptation graph matching low-light image enhancement common sense reasoning real-time strategy games robot navigation text style transfer video-based person re-identification graph classification semantic correspondence action spotting machine reading comprehension scientific document summarization visual object tracking weakly supervised action localization graph representation learning 3d point cloud classification trajectory forecasting color image denoising multimodal activity recognition adversarial attack deepfake detection head pose estimation video captioning knowledge base question answering open information extraction audio tagging visual localization continual learning code generation topic models link prediction abuse detection constituency parsing visual reasoning 3d pose estimation using rgb gaze estimation lane detection semantic parsing scene text recognition point cloud registration time series analysis music source separation online multi-object tracking emotion recognition in conversation visual place recognition saliency prediction sarcasm detection 3d human reconstruction boundary detection core set discovery document layout analysis classification with binary neural network egocentric activity recognition product recommendation action quality assessment unsupervised video object segmentation sound event detection source code summarization 3d object recognition speech separation curriculum learning 3d object tracking audio source separation abnormal event detection in video object localization scene flow estimation video inpainting multimodal unsupervised image-to-image translation optical flow estimation monocular depth estimation multiple object tracking temporal action localization colorectal polyps characterization document classification 密集的视频字幕 facial landmark detection abusive language multimodal machine translation lexical entailment patch matching bias detection activity detection grasp contact prediction automatic post-editing dictionary learning remote sensing image classification video understanding binarization unsupervised object segmentation classification with binary weight network one-shot learning deblurring video frame interpolation automated theorem proving human action generation retinal vessel segmentation emotion recognition scene text feature selection adversarial defense depression detection natural language inference 科学成果提取 multi-label classification fact verification computed tomography (ct) human part segmentation homography estimation image denoising offline rl 3d pose estimation video object detection goal-oriented dialog handwriting recognition referring expression segmentation gesture recognition person search sketch-based image retrieval semantic similarity clique prediction video segmentation generalized zero-shot learning multi-task learning aesthetics quality assessment human-object interaction detection multivariate time series forecasting sentence embedding cross-view image-to-image translation kg-to-text generation rgb salient object detection 人群计数 latent variable models mathematical question answering multiple instance learning color constancy instance segmentation action unit detection stochastic optimization pedestrian attribute recognition sentence embeddings 联合提取实体和关系 motion segmentation emotion classification fact checking saliency detection few-shot image classification dense pixel correspondence estimation scene generation grammatical error correction minecraft music transcription hate speech detection meta-learning video retrieval action segmentation atari games defect detection conditional image generation document summarization coreference resolution dialogue generation skeleton based action recognition trajectory prediction network embedding 3d object detection density estimation starcraft tumor segmentation image stitching task-oriented dialogue systems audio generation rgb-d salient object detection entity linking lipreading human robot interaction small data image classification music generation semi-supervised image classification hyperspectral image classification text matching person re-identification knowledge graphs novel view synthesis intent detection multi-object tracking acoustic scene classification 3d hand pose estimation vision and language navigation whole slide images unsupervised machine translation multi-document summarization virtual try-on opinion mining video summarization image inpainting + 490

Data Domain

computer vision audio nlp tabular 3d model 医学成像 graph reinforcement learning point cloud + 2

Framework

pytorch tensorflow scikit-learn huggingface transformers flax jax pycaret spacy tf lite + 2

Integration

aws s3 dvc git mlflow arxiv github bitbucket label studio jenkins google cloud storage new relic s3 compatible storage gitlab + 6