{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"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":"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":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"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":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"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":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"1507.07629","title":"Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades","created":"2015-07-28","cited_by_count":314},{"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":"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":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98},{"id":"2112.01041","title":"N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras","created":"2021-12-02","cited_by_count":92},{"id":"1704.04516","title":"Interpretable 3D Human Action Analysis with Temporal Convolutional Networks","created":"2017-04-14","cited_by_count":89},{"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":"2103.06108","title":"Time-Ordered Recent Event (TORE) Volumes for Event Cameras","created":"2021-03-10","cited_by_count":73},{"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":"2310.02642","title":"GET: Group Event Transformer for Event-Based Vision","created":"2023-10-04","cited_by_count":73},{"id":"2211.13222","title":"SVFormer: Semi-supervised Video Transformer for Action Recognition","created":"2022-11-23","cited_by_count":68},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50},{"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":"2403.12534","title":"ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More","created":"2024-03-19","cited_by_count":33},{"id":"1611.02447","title":"Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks","created":"2016-11-08","cited_by_count":32},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28},{"id":"2110.12211","title":"ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks","created":"2021-10-23","cited_by_count":24},{"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":"2403.19316","title":"Hypergraph-based Multi-View Action Recognition using Event Cameras","created":"2024-03-28","cited_by_count":19},{"id":"2306.11546","title":"Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition","created":"2023-06-20","cited_by_count":17},{"id":"2407.05106","title":"DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition","created":"2024-07-06","cited_by_count":17},{"id":"2312.00096","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","created":"2023-11-30","cited_by_count":16},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15},{"id":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","cited_by_count":10},{"id":"2311.18592","title":"Semantic-Aware Frame-Event Fusion based Pattern Recognition via Large Vision-Language Models","created":"2023-11-30","cited_by_count":7},{"id":"2312.08644","title":"Generative Model-based Feature Knowledge Distillation for Action Recognition","created":"2023-12-14","cited_by_count":7},{"id":"2406.18845","title":"Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition","created":"2024-06-27","cited_by_count":3}],"next_cursor":null}