{"list":"other","total":82,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"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":"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":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"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":"2103.10504","title":"UNETR: Transformers for 3D Medical Image Segmentation","created":"2021-03-18","cited_by_count":959},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2004.09666","title":"Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images","created":"2020-04-20","cited_by_count":745},{"id":"1902.03368","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2019-02-09","cited_by_count":669},{"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":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"1811.08839","title":"fastMRI: An Open Dataset and Benchmarks for Accelerated MRI","created":"2018-11-21","cited_by_count":470},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"1902.09063","title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","created":"2019-02-25","cited_by_count":373},{"id":"2206.08023","title":"AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation","created":"2022-06-16","cited_by_count":351},{"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":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2304.13785","title":"Customized Segment Anything Model for Medical Image Segmentation","created":"2023-04-26","cited_by_count":280},{"id":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236},{"id":"1902.06426","title":"2017 Robotic Instrument Segmentation Challenge","created":"2019-02-18","cited_by_count":168},{"id":"2403.09977","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","created":"2024-03-15","cited_by_count":146},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141},{"id":"2007.00478","title":"PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones","created":"2020-07-01","cited_by_count":118},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112},{"id":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90},{"id":"2402.05892","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","created":"2024-02-08","cited_by_count":84},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84},{"id":"2309.08842","title":"MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation","created":"2023-09-16","cited_by_count":82},{"id":"2404.09498","title":"FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba","created":"2024-04-15","cited_by_count":81},{"id":"2101.12355","title":"A Petri Dish for Histopathology Image Analysis","created":"2021-01-29","cited_by_count":64},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64},{"id":"2403.02148","title":"MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection","created":"2024-03-04","cited_by_count":60},{"id":"2404.09476","title":"FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining","created":"2024-04-15","cited_by_count":57},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54},{"id":"2307.08473","title":"EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation","created":"2023-07-17","cited_by_count":53},{"id":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51},{"id":"2308.05862","title":"Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge","created":"2023-08-10","cited_by_count":50},{"id":"1701.03056","title":"CNN-based Segmentation of Medical Imaging Data","created":"2017-01-11","cited_by_count":48},{"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":"2210.06583","title":"S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces","created":"2022-10-12","cited_by_count":41},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39},{"id":"2306.09579","title":"MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification","created":"2023-06-16","cited_by_count":38},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38},{"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":"2404.08406","title":"MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion","created":"2024-04-12","cited_by_count":35},{"id":"2107.09011","title":"Image Fusion Transformer","created":"2021-07-19","cited_by_count":24},{"id":"2403.05795","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","created":"2024-03-09","cited_by_count":22},{"id":"2210.16898","title":"Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation","created":"2022-10-30","cited_by_count":21},{"id":"2404.07932","title":"FusionMamba: Efficient Remote Sensing Image Fusion with State Space Model","created":"2024-04-11","cited_by_count":21},{"id":"2209.02048","title":"Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation","created":"2022-09-05","cited_by_count":18},{"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":"2404.01082","title":"The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023","created":"2024-04-01","cited_by_count":15},{"id":"2006.15720","title":"Progressive Generation of Long Text with Pretrained Language Models","created":"2020-06-28","cited_by_count":14},{"id":"2404.15009","title":"The Brain Tumor Segmentation in Pediatrics (BraTS-PEDs) Challenge: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)","created":"2024-04-23","cited_by_count":14},{"id":"2403.05146","title":"Motion-Guided Dual-Camera Tracker for Endoscope Tracking and Motion Analysis in a Mechanical Gastric Simulator","created":"2024-03-08","cited_by_count":10},{"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":"2406.05992","title":"MHS-VM: Multi-Head Scanning in Parallel Subspaces for Vision Mamba","created":"2024-06-10","cited_by_count":2},{"id":"2409.07896","title":"MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space Models","created":"2024-09-12","cited_by_count":2}],"next_cursor":null}