{"list":"other","total":104,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2203.02923","title":"GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation","created":"2022-03-06","cited_by_count":516},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2106.04156","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","created":"2021-06-08","cited_by_count":313},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"1708.01642","title":"Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection","created":"2017-08-04","cited_by_count":209},{"id":"2204.03610","title":"Unified Contrastive Learning in Image-Text-Label Space","created":"2022-04-07","cited_by_count":194},{"id":"1706.00527","title":"Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks","created":"2017-06-02","cited_by_count":131},{"id":"2210.05475","title":"GENIE: Higher-Order Denoising Diffusion Solvers","created":"2022-10-11","cited_by_count":127},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"1907.11879","title":"Multi-task Self-Supervised Learning for Human Activity Detection","created":"2019-07-27","cited_by_count":102},{"id":"2008.07404","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","created":"2020-08-17","cited_by_count":98},{"id":"2009.05475","title":"Adversarial score matching and improved sampling for image generation","created":"2020-09-11","cited_by_count":96},{"id":"1604.08880","title":"Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables","created":"2016-04-29","cited_by_count":94},{"id":"1608.04363","title":"Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification","created":"2016-08-15","cited_by_count":85},{"id":"2011.11542","title":"Exploring Contrastive Learning in Human Activity Recognition for Healthcare","created":"2020-11-23","cited_by_count":75},{"id":"2206.02909","title":"Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data","created":"2022-06-06","cited_by_count":75},{"id":"2202.12938","title":"Assessing the State of Self-Supervised Human Activity Recognition using Wearables","created":"2022-02-22","cited_by_count":65},{"id":"2302.05905","title":"Single Motion Diffusion","created":"2023-02-12","cited_by_count":65},{"id":"1703.09370","title":"Ensembles of Deep LSTM Learners for Activity Recognition using Wearables","created":"2017-03-28","cited_by_count":62},{"id":"2011.14097","title":"Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding","created":"2020-11-28","cited_by_count":58},{"id":"2012.05333","title":"Contrastive Predictive Coding for Human Activity Recognition","created":"2020-12-09","cited_by_count":55},{"id":"1802.07802","title":"Protecting Sensory Data against Sensitive Inferences","created":"2018-02-21","cited_by_count":45},{"id":"2202.05998","title":"What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?","created":"2022-02-12","cited_by_count":40},{"id":"2210.14395","title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","created":"2022-10-26","cited_by_count":37},{"id":"1903.12489","title":"Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networks","created":"2019-03-29","cited_by_count":35},{"id":"1805.07648","title":"On Attention Models for Human Activity Recognition","created":"2018-05-19","cited_by_count":34},{"id":"1912.07756","title":"Data augmentation approaches for improving animal audio classification","created":"2019-12-16","cited_by_count":31},{"id":"2102.06073","title":"SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data","created":"2021-02-11","cited_by_count":31},{"id":"2108.00702","title":"Improving Deep Learning for HAR with shallow LSTMs","created":"2021-08-02","cited_by_count":30},{"id":"1810.04038","title":"Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention","created":"2018-10-07","cited_by_count":27},{"id":"2003.09018","title":"Human Activity Recognition from Wearable Sensor Data Using Self-Attention","created":"2020-03-17","cited_by_count":27},{"id":"2311.08245","title":"TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition","created":"2023-11-14","cited_by_count":25},{"id":"2006.05675","title":"IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition","created":"2020-05-29","cited_by_count":22},{"id":"2202.00758","title":"ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition","created":"2022-02-01","cited_by_count":22},{"id":"2402.01049","title":"IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition","created":"2024-02-01","cited_by_count":22},{"id":"2208.00467","title":"COCOA: Cross Modality Contrastive Learning for Sensor Data","created":"2022-07-31","cited_by_count":21},{"id":"2212.00724","title":"SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition","created":"2022-11-25","cited_by_count":21},{"id":"2305.03187","title":"Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition","created":"2023-05-04","cited_by_count":19},{"id":"2402.19229","title":"CAPTURE-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition","created":"2024-02-29","cited_by_count":19},{"id":"2403.01133","title":"Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data","created":"2024-03-02","cited_by_count":17},{"id":"2405.17893","title":"Arithmetic Reasoning with LLM: Prolog Generation & Permutation","created":"2024-05-28","cited_by_count":17},{"id":"2006.14435","title":"DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors","created":"2020-06-25","cited_by_count":14},{"id":"2401.10185","title":"Transfer Learning in Human Activity Recognition: A Survey","created":"2024-01-18","cited_by_count":14},{"id":"2210.01459","title":"Learning from the Best: Contrastive Representations Learning Across Sensor Locations for Wearable Activity Recognition","created":"2022-10-04","cited_by_count":13},{"id":"2405.12368","title":"Layout Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)","created":"2024-05-20","cited_by_count":13},{"id":"2407.07196","title":"Large Language Models for Wearable Sensor-Based Human Activity Recognition, Health Monitoring, and Behavioral Modeling: A Survey of Early Trends, Datasets, and Challenges","created":"2024-07-09","cited_by_count":12},{"id":"2003.01874","title":"A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors","created":"2020-03-04","cited_by_count":11},{"id":"2209.09092","title":"TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation","created":"2022-09-14","cited_by_count":10},{"id":"2308.03805","title":"Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables","created":"2023-08-06","cited_by_count":10},{"id":"2408.12023","title":"Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them","created":"2024-08-21","cited_by_count":10},{"id":"2302.00391","title":"PresSim: An End-to-end Framework for Dynamic Ground Pressure Profile Generation from Monocular Videos Using Physics-based 3D Simulation","created":"2023-02-01","cited_by_count":9},{"id":"2408.06352","title":"Using Large Language Models to Compare Explainable Models for Smart Home Human Activity Recognition","created":"2024-07-24","cited_by_count":9},{"id":"1906.02399","title":"SparseSense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks","created":"2019-06-06","cited_by_count":7},{"id":"2203.05692","title":"Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks","created":"2022-03-11","cited_by_count":7},{"id":"2306.01108","title":"Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition","created":"2023-06-01","cited_by_count":7},{"id":"2202.10562","title":"CROMOSim: A Deep Learning-based Cross-modality Inertial Measurement Simulator","created":"2022-02-21","cited_by_count":6},{"id":"2308.03514","title":"Worker Activity Recognition in Manufacturing Line Using Near-body Electric Field","created":"2023-08-07","cited_by_count":6}],"next_cursor":"100"}