{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2203.00680","title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","created":"2022-03-01","cited_by_count":198},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2109.00179","title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","created":"2021-09-01","cited_by_count":180},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"1909.01300","title":"The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset","created":"2019-09-03","cited_by_count":134},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80},{"id":"2112.10646","title":"Raw High-Definition Radar for Multi-Task Learning","created":"2021-12-20","cited_by_count":69},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2005.01456","title":"CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations","created":"2020-05-04","cited_by_count":60},{"id":"2105.00363","title":"RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users","created":"2021-05-02","cited_by_count":52},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50},{"id":"2303.00462","title":"Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision","created":"2023-03-01","cited_by_count":36},{"id":"2105.05207","title":"Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment","created":"2021-05-11","cited_by_count":23},{"id":"2203.04440","title":"Pointillism: Accurate 3D bounding box estimation with multi-radars","created":"2022-03-08","cited_by_count":23},{"id":"2004.03451","title":"RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar","created":"2020-04-02","cited_by_count":22},{"id":"2209.02329","title":"Multimodal contrastive learning for remote sensing tasks","created":"2022-09-06","cited_by_count":18},{"id":"2309.00399","title":"Fine-grained Recognition with Learnable Semantic Data Augmentation","created":"2023-09-01","cited_by_count":17},{"id":"1810.08151","title":"Probably Unknown: Deep Inverse Sensor Modelling In Radar","created":"2018-10-18","cited_by_count":16},{"id":"2004.03449","title":"Deep Open Space Segmentation using Automotive Radar","created":"2020-03-18","cited_by_count":14},{"id":"2207.02370","title":"Unsupervised Learning for Human Sensing Using Radio Signals","created":"2022-07-06","cited_by_count":14},{"id":"2107.06652","title":"Self-Supervised Multi-Modal Alignment for Whole Body Medical Imaging","created":"2021-07-14","cited_by_count":6},{"id":"2111.02887","title":"Self-Supervised Radio-Visual Representation Learning for 6G Sensing","created":"2021-11-01","cited_by_count":6},{"id":"2112.04282","title":"Radar Occupancy Prediction with Lidar Supervision while Preserving Long-Range Sensing and Penetrating Capabilities","created":"2021-12-08","cited_by_count":5},{"id":"2308.01300","title":"Revisiting DETR Pre-training for Object Detection","created":"2023-08-02","cited_by_count":5},{"id":"2206.06424","title":"Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence","created":"2022-06-13","cited_by_count":3}],"next_cursor":null}