{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"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":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"1610.00081","title":"Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction","created":"2016-10-01","cited_by_count":333},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"2003.01460","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","created":"2020-03-03","cited_by_count":195},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184},{"id":"1706.03458","title":"Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model","created":"2017-06-12","cited_by_count":182},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"1804.01523","title":"Stochastic Adversarial Video Prediction","created":"2018-04-04","cited_by_count":173},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"1804.06300","title":"PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning","created":"2018-04-17","cited_by_count":122},{"id":"1610.00527","title":"Video Pixel Networks","created":"2016-10-03","cited_by_count":108},{"id":"1811.07490","title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","created":"2018-11-19","cited_by_count":92},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"1711.09026","title":"Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty","created":"2017-11-24","cited_by_count":63},{"id":"2104.00924","title":"Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning","created":"2021-04-02","cited_by_count":62},{"id":"2306.11249","title":"OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning","created":"2023-06-20","cited_by_count":54},{"id":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53},{"id":"2002.09905","title":"Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction","created":"2020-02-23","cited_by_count":52},{"id":"2402.03526","title":"nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model","created":"2024-02-05","cited_by_count":45},{"id":"1712.00311","title":"Folded Recurrent Neural Networks for Future Video Prediction","created":"2017-12-01","cited_by_count":44},{"id":"1812.00452","title":"Disentangling Propagation and Generation for Video Prediction","created":"2018-12-02","cited_by_count":44},{"id":"1711.08362","title":"RGB-D-based Human Motion Recognition with Deep Learning: A Survey","created":"2017-10-31","cited_by_count":37},{"id":"2308.09891","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","created":"2023-08-19","cited_by_count":32},{"id":"2308.16154","title":"MMVP: Motion-Matrix-based Video Prediction","created":"2023-08-30","cited_by_count":18},{"id":"2309.07849","title":"TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation","created":"2023-09-14","cited_by_count":13},{"id":"2310.02676","title":"PostRainBench: A comprehensive benchmark and a new model for precipitation forecasting","created":"2023-10-04","cited_by_count":8}],"next_cursor":null}