{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"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":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"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":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"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":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"2406.07887","title":"An Empirical Study of Mamba-based Language Models","created":"2024-06-12","cited_by_count":186},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"1909.00179","title":"Boundary-Aware Feature Propagation for Scene Segmentation","created":"2019-08-31","cited_by_count":107},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"id":"1709.06750","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","created":"2017-09-20","cited_by_count":92},{"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":"2408.12879","title":"Frequency-aware Feature Fusion for Dense Image Prediction","created":"2024-08-23","cited_by_count":48},{"id":"2504.16053","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","created":"2025-04-22","cited_by_count":42},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","cited_by_count":41},{"id":"1911.12739","title":"Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow","created":"2019-11-28","cited_by_count":31},{"id":"2206.10590","title":"Temporally Consistent Semantic Video Editing","created":"2022-06-21","cited_by_count":28},{"id":"2310.18954","title":"Mask Propagation for Efficient Video Semantic Segmentation","created":"2023-10-29","cited_by_count":26},{"id":"2101.01715","title":"Local Memory Attention for Fast Video Semantic Segmentation","created":"2021-01-05","cited_by_count":25},{"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":"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":"1912.11844","title":"Efficient Video Semantic Segmentation with Labels Propagation and Refinement","created":"2019-12-26","cited_by_count":18},{"id":"2503.20824","title":"Exploiting Temporal State Space Sharing for Video Semantic Segmentation","created":"2025-03-26","cited_by_count":15},{"id":"1905.01058","title":"Semantic Segmentation of Video Sequences with Convolutional LSTMs","created":"2019-05-03","cited_by_count":14},{"id":"2505.04575","title":"Componential Prompt-Knowledge Alignment for Domain Incremental Learning","created":"2025-05-07","cited_by_count":13},{"id":"2401.15261","title":"Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes","created":"2024-01-27","cited_by_count":12},{"id":"2412.09224","title":"DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification","created":"2024-12-12","cited_by_count":12},{"id":"2103.08834","title":"GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video","created":"2021-03-16","cited_by_count":11},{"id":"2405.16504","title":"Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation","created":"2024-05-26","cited_by_count":11},{"id":"2203.16632","title":"Controllable Augmentations for Video Representation Learning","created":"2022-03-30","cited_by_count":10},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10},{"id":"2211.10119","title":"Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance","created":"2022-11-18","cited_by_count":7},{"id":"2507.01884","title":"Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification","created":"2025-07-02","cited_by_count":7},{"id":"2510.12160","title":"State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding","created":"2025-10-14","cited_by_count":2}],"next_cursor":null}