{"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"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":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"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":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1706.02609","title":"Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks","created":"2017-06-08","cited_by_count":406},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"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":"2209.15425","title":"Spikformer: When Spiking Neural Network Meets Transformer","created":"2022-09-29","cited_by_count":271},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","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":"2203.17149","title":"AEGNN: Asynchronous Event-based Graph Neural Networks","created":"2022-03-31","cited_by_count":118},{"id":"2003.06696","title":"Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks","created":"2020-03-14","cited_by_count":98},{"id":"1911.03977","title":"Multimodal Intelligence: Representation Learning, Information Fusion, and Applications","created":"2019-11-10","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":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"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":"2011.06176","title":"LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing","created":"2020-11-12","cited_by_count":56},{"id":"2211.11010","title":"Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric","created":"2022-11-20","cited_by_count":52},{"id":"1807.10936","title":"Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception","created":"2018-07-28","cited_by_count":48},{"id":"2211.09648","title":"HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors","created":"2022-11-17","cited_by_count":47},{"id":"1909.10837","title":"Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance","created":"2019-09-24","cited_by_count":46},{"id":"1908.08019","title":"Spiking Neural Networks and Online Learning: An Overview and Perspectives","created":"2019-07-23","cited_by_count":41},{"id":"1711.09550","title":"Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification","created":"2017-11-27","cited_by_count":29},{"id":"2303.11997","title":"E-MLB: Multilevel Benchmark for Event-Based Camera Denoising","created":"2023-03-21","cited_by_count":27},{"id":"2003.12346","title":"Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction","created":"2020-03-27","cited_by_count":23},{"id":"2112.03423","title":"Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision","created":"2021-12-06","cited_by_count":22},{"id":"1912.10280","title":"\\emph{cm}SalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks","created":"2019-12-21","cited_by_count":21},{"id":"1411.4006","title":"A Discriminative CNN Video Representation for Event Detection","created":"2014-11-14","cited_by_count":20},{"id":"1911.08261","title":"Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neurons","created":"2019-11-19","cited_by_count":14},{"id":"2009.00855","title":"e-TLD: Event-based Framework for Dynamic Object Tracking","created":"2020-09-02","cited_by_count":13},{"id":"2303.14176","title":"A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception","created":"2023-03-24","cited_by_count":13},{"id":"1710.07354","title":"Learning to Recognize Actions from Limited Training Examples Using a Recurrent Spiking Neural Model","created":"2017-10-19","cited_by_count":7},{"id":"1911.03630","title":"Action Recognition Using Supervised Spiking Neural Networks","created":"2019-11-09","cited_by_count":2}],"next_cursor":null}