{"list":"other","total":59,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1702.05747","title":"A Survey on Deep Learning in Medical Image Analysis","created":"2017-02-19","cited_by_count":1186},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"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":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1511.06432","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","created":"2015-11-19","cited_by_count":148},{"id":"1709.06750","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","created":"2017-09-20","cited_by_count":92},{"id":"1506.06204","title":"Learning to Segment Object Candidates","created":"2015-06-20","cited_by_count":79},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79},{"id":"1807.06667","title":"Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video","created":"2018-07-17","cited_by_count":78},{"id":"2004.01800","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","created":"2020-04-03","cited_by_count":77},{"id":"1612.08871","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","created":"2016-12-28","cited_by_count":76},{"id":"2002.11433","title":"Efficient Semantic Video Segmentation with Per-frame Inference","created":"2020-02-26","cited_by_count":63},{"id":"1804.00389","title":"Low-Latency Video Semantic Segmentation","created":"2018-04-02","cited_by_count":61},{"id":"1608.03609","title":"Clockwork Convnets for Video Semantic Segmentation","created":"2016-08-11","cited_by_count":55},{"id":"2102.08643","title":"Temporal Memory Attention for Video Semantic Segmentation","created":"2021-02-17","cited_by_count":50},{"id":"2403.16536","title":"VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting","created":"2024-03-25","cited_by_count":35},{"id":"1911.12739","title":"Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow","created":"2019-11-28","cited_by_count":31},{"id":"2310.18954","title":"Mask Propagation for Efficient Video Semantic Segmentation","created":"2023-10-29","cited_by_count":26},{"id":"2207.10436","title":"Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation","created":"2022-07-21","cited_by_count":25},{"id":"2204.03330","title":"Learning Local and Global Temporal Contexts for Video Semantic Segmentation","created":"2022-04-07","cited_by_count":24},{"id":"2303.12782","title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","created":"2023-03-22","cited_by_count":23},{"id":"2103.11015","title":"Video Class Agnostic Segmentation Benchmark for Autonomous Driving","created":"2021-03-19","cited_by_count":22},{"id":"1603.03911","title":"Optical Flow with Semantic Segmentation and Localized Layers","created":"2016-03-12","cited_by_count":21},{"id":"1807.07946","title":"Future Semantic Segmentation with Convolutional LSTM","created":"2018-07-20","cited_by_count":14},{"id":"1905.01058","title":"Semantic Segmentation of Video Sequences with Convolutional LSTMs","created":"2019-05-03","cited_by_count":14},{"id":"2010.09466","title":"Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation","created":"2020-10-19","cited_by_count":14},{"id":"1606.00487","title":"Recurrent Fully Convolutional Networks for Video Segmentation","created":"2016-06-01","cited_by_count":10},{"id":"2203.16632","title":"Controllable Augmentations for Video Representation Learning","created":"2022-03-30","cited_by_count":10},{"id":"2309.08020","title":"Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation","created":"2023-09-14","cited_by_count":7}],"next_cursor":null}