{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"1811.07246","title":"PointConv: Deep Convolutional Networks on 3D Point Clouds","created":"2018-11-17","cited_by_count":657},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"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":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"1904.08245","title":"End-to-End Learning of Representations for Asynchronous Event-Based Data","created":"2019-04-17","cited_by_count":217},{"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":"2002.12324","title":"Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC","created":"2020-02-27","cited_by_count":176},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"1904.03375","title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling","created":"2019-04-06","cited_by_count":151},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"1611.07890","title":"Image-based localization using LSTMs for structured feature correlation","created":"2016-11-23","cited_by_count":136},{"id":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"2107.11711","title":"Temporal-wise Attention Spiking Neural Networks for Event Streams Classification","created":"2021-07-25","cited_by_count":106},{"id":"1707.09733","title":"Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network","created":"2017-07-31","cited_by_count":79},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75},{"id":"2310.02642","title":"GET: Group Event Transformer for Event-Based Vision","created":"2023-10-04","cited_by_count":73},{"id":"2403.06467","title":"Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy","created":"2024-03-11","cited_by_count":73},{"id":"1804.08366","title":"VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry","created":"2018-04-23","cited_by_count":61},{"id":"1803.03642","title":"Deep Auxiliary Learning for Visual Localization and Odometry","created":"2018-03-09","cited_by_count":59},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"1812.07045","title":"EventNet: Asynchronous Recursive Event Processing","created":"2018-12-07","cited_by_count":58},{"id":"2004.03577","title":"Event Based, Near Eye Gaze Tracking Beyond 10,000Hz","created":"2020-04-07","cited_by_count":53},{"id":"2010.08946","title":"Temporal Binary Representation for Event-Based Action Recognition","created":"2020-10-18","cited_by_count":51},{"id":"2308.11771","title":"3ET: Efficient Event-based Eye Tracking using a Change-Based ConvLSTM Network","created":"2023-08-22","cited_by_count":30},{"id":"2310.07189","title":"SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition","created":"2023-10-11","cited_by_count":30},{"id":"2010.08278","title":"Real-Time Face & Eye Tracking and Blink Detection using Event Cameras","created":"2020-10-16","cited_by_count":27},{"id":"1907.05272","title":"Introduction to Camera Pose Estimation with Deep Learning","created":"2019-07-08","cited_by_count":25},{"id":"2003.12346","title":"Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction","created":"2020-03-27","cited_by_count":23},{"id":"2404.18174","title":"Mamba-FETrack: Frame-Event Tracking via State Space Model","created":"2024-04-28","cited_by_count":22},{"id":"1511.05768","title":"Labeled pupils in the wild: A dataset for studying pupil detection in unconstrained environments","created":"2015-11-18","cited_by_count":18},{"id":"2403.19412","title":"A Simple and Effective Point-based Network for Event Camera 6-DOFs Pose Relocalization","created":"2024-03-28","cited_by_count":17},{"id":"2401.11687","title":"TIM: An Efficient Temporal Interaction Module for Spiking Transformer","created":"2024-01-22","cited_by_count":12},{"id":"2308.09993","title":"TTPOINT: A Tensorized Point Cloud Network for Lightweight Action Recognition with Event Cameras","created":"2023-08-19","cited_by_count":11},{"id":"1812.07869","title":"Deep Global-Relative Networks for End-to-End 6-DoF Visual Localization and Odometry","created":"2018-12-19","cited_by_count":10},{"id":"2105.04216","title":"Event-LSTM: An Unsupervised and Asynchronous Learning-based Representation for Event-based Data","created":"2021-05-10","cited_by_count":7}],"next_cursor":null}