{"list":"other","total":56,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2007.05785","title":"Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks","created":"2020-07-11","cited_by_count":345},{"id":"2102.04159","title":"Deep Residual Learning in Spiking Neural Networks","created":"2021-02-08","cited_by_count":331},{"id":"1507.07629","title":"Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades","created":"2015-07-28","cited_by_count":314},{"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":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"2205.00459","title":"Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation","created":"2022-05-01","cited_by_count":89},{"id":"1908.06648","title":"Graph-Based Object Classification for Neuromorphic Vision Sensing","created":"2019-08-19","cited_by_count":85},{"id":"1711.01458","title":"DDD17: End-To-End DAVIS Driving Dataset","created":"2017-11-04","cited_by_count":84},{"id":"2309.14611","title":"Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline","created":"2023-09-26","cited_by_count":73},{"id":"2106.14999","title":"Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation","created":"2021-06-28","cited_by_count":68},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63},{"id":"2201.10943","title":"Event-based Video Reconstruction via Potential-assisted Spiking Neural Network","created":"2022-01-25","cited_by_count":59},{"id":"1812.07045","title":"EventNet: Asynchronous Recursive Event Processing","created":"2018-12-07","cited_by_count":58},{"id":"2211.11010","title":"Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric","created":"2022-11-20","cited_by_count":52},{"id":"2308.14419","title":"Graph-based Asynchronous Event Processing for Rapid Object Recognition","created":"2023-08-28","cited_by_count":51},{"id":"1901.07474","title":"Pedestrian Attribute Recognition: A Survey","created":"2019-01-22","cited_by_count":50},{"id":"2105.15076","title":"Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark","created":"2021-05-31","cited_by_count":47},{"id":"2211.09648","title":"HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors","created":"2022-11-17","cited_by_count":47},{"id":"2105.08810","title":"Sparse Spiking Gradient Descent","created":"2021-05-18","cited_by_count":41},{"id":"1708.05038","title":"ConvNet Architecture Search for Spatiotemporal Feature Learning","created":"2017-08-16","cited_by_count":40},{"id":"2003.02944","title":"Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network","created":"2020-02-19","cited_by_count":37},{"id":"2306.06354","title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","created":"2023-06-10","cited_by_count":36},{"id":"2303.11997","title":"E-MLB: Multilevel Benchmark for Event-Based Camera Denoising","created":"2023-03-21","cited_by_count":27},{"id":"2103.00806","title":"Representation Learning for Event-based Visuomotor Policies","created":"2021-03-01","cited_by_count":20},{"id":"2308.04369","title":"SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition","created":"2023-08-08","cited_by_count":20},{"id":"2306.11546","title":"Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition","created":"2023-06-20","cited_by_count":17},{"id":"2307.08228","title":"Video Frame Interpolation with Stereo Event and Intensity Camera","created":"2023-07-17","cited_by_count":10},{"id":"2302.04177","title":"A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition","created":"2023-02-08","cited_by_count":7},{"id":"2308.11937","title":"Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification","created":"2023-08-23","cited_by_count":6},{"id":"2309.02190","title":"Exchanging-based Multimodal Fusion with Transformer","created":"2023-09-05","cited_by_count":2}],"next_cursor":null}