{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"1906.07165","title":"High Speed and High Dynamic Range Video with an Event Camera","created":"2019-06-15","cited_by_count":345},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"1507.07629","title":"Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades","created":"2015-07-28","cited_by_count":314},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"1802.06898","title":"EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras","created":"2018-02-19","cited_by_count":224},{"id":"1803.07913","title":"HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification","created":"2018-03-21","cited_by_count":218},{"id":"1904.08245","title":"End-to-End Learning of Representations for Asynchronous Event-Based Data","created":"2019-04-17","cited_by_count":217},{"id":"1608.08782","title":"Training Deep Spiking Neural Networks using Backpropagation","created":"2016-08-31","cited_by_count":205},{"id":"1610.08336","title":"The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM","created":"2016-10-26","cited_by_count":203},{"id":"1804.01310","title":"Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars","created":"2018-04-04","cited_by_count":200},{"id":"1904.08298","title":"Events-to-Video: Bringing Modern Computer Vision to Event Cameras","created":"2019-04-17","cited_by_count":193},{"id":"2009.13436","title":"Learning to Detect Objects with a 1 Megapixel Event Camera","created":"2020-09-28","cited_by_count":186},{"id":"1912.03095","title":"Video to Events: Recycling Video Datasets for Event Cameras","created":"2019-12-06","cited_by_count":165},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159},{"id":"2108.10552","title":"E-RAFT: Dense Optical Flow from Event Cameras","created":"2021-08-24","cited_by_count":152},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"1803.04523","title":"Event-based Moving Object Detection and Tracking","created":"2018-03-12","cited_by_count":127},{"id":"1807.09713","title":"Asynchronous, Photometric Feature Tracking using Events and Frames","created":"2018-07-25","cited_by_count":118},{"id":"2203.17149","title":"AEGNN: Asynchronous Event-based Graph Neural Networks","created":"2022-03-31","cited_by_count":118},{"id":"2001.08499","title":"A Large Scale Event-based Detection Dataset for Automotive","created":"2020-01-23","cited_by_count":109},{"id":"2105.07197","title":"Are Convolutional Neural Networks or Transformers more like human vision?","created":"2021-05-15","cited_by_count":109},{"id":"2003.09148","title":"Event-based Asynchronous Sparse Convolutional Networks","created":"2020-03-20","cited_by_count":104},{"id":"1610.09513","title":"Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences","created":"2016-10-29","cited_by_count":99},{"id":"2112.01041","title":"N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras","created":"2021-12-02","cited_by_count":92},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"id":"2203.10016","title":"ESS: Learning Event-based Semantic Segmentation from Still Images","created":"2022-03-18","cited_by_count":82},{"id":"1607.03468","title":"Event-based, 6-DOF Camera Tracking from Photometric Depth Maps","created":"2016-07-12","cited_by_count":54},{"id":"1508.01176","title":"HFirst: A Temporal Approach to Object Recognition","created":"2015-08-05","cited_by_count":50},{"id":"1912.01584","title":"EventGAN: Leveraging Large Scale Image Datasets for Event Cameras","created":"2019-12-03","cited_by_count":48},{"id":"2111.12341","title":"EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation","created":"2021-11-24","cited_by_count":47},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41},{"id":"2109.02618","title":"Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation","created":"2021-09-06","cited_by_count":37},{"id":"1803.09025","title":"Realtime Time Synchronized Event-based Stereo","created":"2018-03-24","cited_by_count":28},{"id":"2203.12247","title":"Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition","created":"2022-03-23","cited_by_count":26},{"id":"2202.12307","title":"Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph","created":"2022-02-24","cited_by_count":6}],"next_cursor":null}