{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485},{"id":"2205.04437","title":"Activating More Pixels in Image Super-Resolution Transformer","created":"2022-05-09","cited_by_count":438},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2304.13785","title":"Customized Segment Anything Model for Medical Image Segmentation","created":"2023-04-26","cited_by_count":280},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2305.03048","title":"Personalize Segment Anything Model with One Shot","created":"2023-05-04","cited_by_count":250},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","cited_by_count":214},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"1710.10400","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","created":"2017-10-28","cited_by_count":162},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"id":"1903.12473","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","created":"2019-03-28","cited_by_count":147},{"id":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"id":"2305.13310","title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","created":"2023-05-22","cited_by_count":142},{"id":"2308.16184","title":"SAM-Med2D","created":"2023-08-30","cited_by_count":124},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"1611.06779","title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","created":"2016-11-21","cited_by_count":119},{"id":"1801.02765","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","created":"2018-01-09","cited_by_count":119},{"id":"1908.05900","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","created":"2019-08-16","cited_by_count":114},{"id":"2308.08746","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","created":"2023-08-17","cited_by_count":104},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"id":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80},{"id":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70},{"id":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62},{"id":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47},{"id":"2011.14021","title":"Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach","created":"2020-11-27","cited_by_count":45},{"id":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44},{"id":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","cited_by_count":41},{"id":"2312.06660","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","created":"2023-12-11","cited_by_count":41},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39},{"id":"2306.05399","title":"Matting Anything","created":"2023-06-08","cited_by_count":31},{"id":"2205.05320","title":"Arbitrary Shape Text Detection via Boundary Transformer","created":"2022-05-11","cited_by_count":28},{"id":"2203.03911","title":"Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting","created":"2022-03-08","cited_by_count":27},{"id":"2201.11438","title":"DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer","created":"2022-01-27","cited_by_count":19},{"id":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18},{"id":"2310.04999","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","created":"2023-10-08","cited_by_count":14},{"id":"1904.00818","title":"COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation","created":"2019-04-01","cited_by_count":12},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12},{"id":"2308.10408","title":"Turning a CLIP Model into a Scene Text Spotter","created":"2023-08-21","cited_by_count":9},{"id":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","cited_by_count":8},{"id":"2303.10848","title":"Weakly-Supervised Text Instance Segmentation","created":"2023-03-20","cited_by_count":4}],"next_cursor":null}