{"list":"other","total":166,"rows":[{"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":"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"1911.07069","title":"Kvasir-SEG: A Segmented Polyp Dataset","created":"2019-11-16","cited_by_count":589},{"id":"1912.05074","title":"UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation","created":"2019-12-11","cited_by_count":586},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"2006.11392","title":"PraNet: Parallel Reverse Attention Network for Polyp Segmentation","created":"2020-06-13","cited_by_count":460},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"1711.10684","title":"Road Extraction by Deep Residual U-Net","created":"2017-11-29","cited_by_count":333},{"id":"1408.5093","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","created":"2014-06-20","cited_by_count":288},{"id":"2102.08005","title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","created":"2021-02-16","cited_by_count":258},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252},{"id":"2304.12306","title":"Segment Anything in Medical Images","created":"2023-04-24","cited_by_count":227},{"id":"1612.00799","title":"A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images","created":"2016-12-02","cited_by_count":221},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"1911.07067","title":"ResUNet++: An Advanced Architecture for Medical Image Segmentation","created":"2019-11-16","cited_by_count":211},{"id":"2406.02918","title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation","created":"2024-06-05","cited_by_count":179},{"id":"1912.02911","title":"Deep learning with noisy labels: exploring techniques and remedies in medical image analysis","created":"2019-12-05","cited_by_count":173},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160},{"id":"2108.06932","title":"Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers","created":"2021-08-16","cited_by_count":159},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"2402.11530","title":"Efficient Multimodal Learning from Data-centric Perspective","created":"2024-02-18","cited_by_count":122},{"id":"2108.00882","title":"Shallow Attention Network for Polyp Segmentation","created":"2021-08-02","cited_by_count":107},{"id":"2011.10217","title":"DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets","created":"2020-11-20","cited_by_count":94},{"id":"2406.11832","title":"Unveiling Encoder-Free Vision-Language Models","created":"2024-06-17","cited_by_count":94},{"id":"2203.14291","title":"Video Polyp Segmentation: A Deep Learning Perspective","created":"2022-03-27","cited_by_count":82},{"id":"2108.05082","title":"Automatic Polyp Segmentation via Multi-scale Subtraction Network","created":"2021-08-11","cited_by_count":77},{"id":"2105.08468","title":"Progressively Normalized Self-Attention Network for Video Polyp Segmentation","created":"2021-05-18","cited_by_count":75},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75},{"id":"2112.08122","title":"Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue","created":"2021-12-15","cited_by_count":72},{"id":"2209.15517","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","created":"2022-09-30","cited_by_count":66},{"id":"2205.12853","title":"Deep Gradient Learning for Efficient Camouflaged Object Detection","created":"2022-05-25","cited_by_count":65},{"id":"2402.19470","title":"Towards Generalizable Tumor Synthesis","created":"2024-02-29","cited_by_count":65},{"id":"2405.06880","title":"EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation","created":"2024-05-11","cited_by_count":64},{"id":"2408.08870","title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","created":"2024-08-16","cited_by_count":64},{"id":"2106.04463","title":"A multi-centre polyp detection and segmentation dataset for generalisability assessment","created":"2021-06-08","cited_by_count":63},{"id":"2107.02368","title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","created":"2021-07-06","cited_by_count":61},{"id":"2104.07434","title":"Points as Queries: Weakly Semi-supervised Object Detection by Points","created":"2021-04-15","cited_by_count":60},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60},{"id":"2205.04280","title":"TGANet: Text-guided attention for improved polyp segmentation","created":"2022-05-09","cited_by_count":59},{"id":"1307.5101","title":"Large-scale Multi-label Learning with Missing Labels","created":"2013-07-18","cited_by_count":58},{"id":"2203.03635","title":"Stepwise Feature Fusion: Local Guides Global","created":"2022-03-07","cited_by_count":56},{"id":"2011.08065","title":"Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy","created":"2020-10-23","cited_by_count":54}],"next_cursor":"100"}