{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"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":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"1809.10486","title":"nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation","created":"2018-09-27","cited_by_count":291},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"2206.12037","title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","created":"2022-06-24","cited_by_count":122},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108},{"id":"2402.04248","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","created":"2024-02-06","cited_by_count":105},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90},{"id":"2403.03849","title":"MedMamba: Vision Mamba for Medical Image Classification","created":"2024-03-06","cited_by_count":88},{"id":"2404.02668","title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","created":"2024-04-03","cited_by_count":81},{"id":"2404.09498","title":"FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba","created":"2024-04-15","cited_by_count":81},{"id":"2207.04978","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","created":"2022-07-11","cited_by_count":78},{"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":"2404.09146","title":"Fusion-Mamba for Cross-modality Object Detection","created":"2024-04-14","cited_by_count":67},{"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":"2404.09476","title":"FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining","created":"2024-04-15","cited_by_count":57},{"id":"2403.18795","title":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","created":"2024-03-27","cited_by_count":56},{"id":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45},{"id":"2402.05608","title":"Scalable Diffusion Models with State Space Backbone","created":"2024-02-08","cited_by_count":45},{"id":"2404.03646","title":"Locating and Editing Factual Associations in Mamba","created":"2024-04-04","cited_by_count":37},{"id":"2404.08406","title":"MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion","created":"2024-04-12","cited_by_count":35},{"id":"2308.12216","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","created":"2023-08-23","cited_by_count":32},{"id":"2311.14495","title":"StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization","created":"2023-11-24","cited_by_count":30},{"id":"2402.10887","title":"Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation","created":"2024-02-16","cited_by_count":29},{"id":"2403.20106","title":"Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring","created":"2024-03-29","cited_by_count":25},{"id":"2404.01174","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","created":"2024-04-01","cited_by_count":25},{"id":"2404.11778","title":"CU-Mamba: Selective State Space Models with Channel Learning for Image Restoration","created":"2024-04-17","cited_by_count":24},{"id":"2402.08506","title":"P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular Segmentation","created":"2024-02-13","cited_by_count":21},{"id":"2404.05522","title":"3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering","created":"2024-04-08","cited_by_count":21},{"id":"2402.07245","title":"Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation","created":"2024-02-11","cited_by_count":20},{"id":"2404.13222","title":"Vim4Path: Self-Supervised Vision Mamba for Histopathology Images","created":"2024-04-20","cited_by_count":19},{"id":"2404.01065","title":"T-Mamba: A unified framework with Long-Range Dependency in dual-domain for 2D & 3D Tooth Segmentation","created":"2024-04-01","cited_by_count":17},{"id":"2404.11375","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","created":"2024-04-17","cited_by_count":16},{"id":"2403.16520","title":"CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification","created":"2024-03-25","cited_by_count":15},{"id":"2402.06378","title":"FD-Vision Mamba for Endoscopic Exposure Correction","created":"2024-02-09","cited_by_count":13},{"id":"2403.10935","title":"Understanding Robustness of Visual State Space Models for Image Classification","created":"2024-03-16","cited_by_count":12},{"id":"2403.08479","title":"MD-Dose: A diffusion model based on the Mamba for radiation dose prediction","created":"2024-03-13","cited_by_count":11},{"id":"2404.07705","title":"ViM-UNet: Vision Mamba for Biomedical Segmentation","created":"2024-04-11","cited_by_count":11},{"id":"2401.13934","title":"MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration","created":"2024-01-25","cited_by_count":10},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","cited_by_count":10},{"id":"2404.08027","title":"SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival Prediction","created":"2024-04-11","cited_by_count":7},{"id":"2404.09697","title":"HSIDMamba: Exploring Bidirectional State-Space Models for Hyperspectral Denoising","created":"2024-04-15","cited_by_count":7},{"id":"2404.05105","title":"VMambaMorph: a Multi-Modality Deformable Image Registration Framework based on Visual State Space Model with Cross-Scan Module","created":"2024-04-07","cited_by_count":6},{"id":"2404.13884","title":"MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 GFLOPs","created":"2024-04-22","cited_by_count":5},{"id":"2404.17235","title":"Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustment","created":"2024-04-26","cited_by_count":1}],"next_cursor":null}