{"list":"other","total":101,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"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":"1911.07069","title":"Kvasir-SEG: A Segmented Polyp Dataset","created":"2019-11-16","cited_by_count":589},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2304.10517","title":"Segment Anything Model for Medical Image Analysis: an Experimental Study","created":"2023-04-20","cited_by_count":291},{"id":"1805.06561","title":"DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images","created":"2018-05-17","cited_by_count":277},{"id":"2110.08733","title":"LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation","created":"2021-10-17","cited_by_count":261},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2105.09451","title":"Anabranch Network for Camouflaged Object Segmentation","created":"2021-05-20","cited_by_count":227},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212},{"id":"1603.00275","title":"Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest","created":"2016-03-01","cited_by_count":203},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2204.03610","title":"Unified Contrastive Learning in Image-Text-Label Space","created":"2022-04-07","cited_by_count":194},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2109.08937","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","created":"2021-09-18","cited_by_count":167},{"id":"2102.06583","title":"Reviving Iterative Training with Mask Guidance for Interactive Segmentation","created":"2021-02-12","cited_by_count":163},{"id":"1907.12347","title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","created":"2019-07-29","cited_by_count":160},{"id":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"2107.07933","title":"Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks","created":"2021-07-16","cited_by_count":143},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"1911.09296","title":"xBD: A Dataset for Assessing Building Damage from Satellite Imagery","created":"2019-11-21","cited_by_count":139},{"id":"1901.07973","title":"DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images","created":"2019-01-23","cited_by_count":134},{"id":"2108.02818","title":"Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications","created":"2021-08-05","cited_by_count":128},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"id":"1807.05713","title":"Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models","created":"2018-07-16","cited_by_count":119},{"id":"2011.12954","title":"RELLIS-3D Dataset: Data, Benchmarks and Analysis","created":"2020-11-17","cited_by_count":119},{"id":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2104.06064","title":"Mixed supervision for surface-defect detection: from weakly to fully supervised learning","created":"2021-04-13","cited_by_count":101},{"id":"2004.01241","title":"Semantic Segmentation of Underwater Imagery: Dataset and Benchmark","created":"2020-04-02","cited_by_count":95},{"id":"1909.10980","title":"PST900: RGB-Thermal Calibration, Dataset and Segmentation Network","created":"2019-09-20","cited_by_count":85},{"id":"1412.0623","title":"Material Recognition in the Wild with the Materials in Context Database","created":"2014-12-01","cited_by_count":79},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2001.01306","title":"Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis","created":"2020-01-05","cited_by_count":61},{"id":"2008.12603","title":"A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis","created":"2020-08-28","cited_by_count":57},{"id":"2104.12137","title":"A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images","created":"2021-04-25","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},{"id":"2101.00442","title":"CryoNuSeg: A Dataset for Nuclei Instance Segmentation of Cryosectioned H&E-Stained Histological Images","created":"2021-01-02","cited_by_count":51},{"id":"2302.10307","title":"ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency","created":"2023-01-31","cited_by_count":51},{"id":"2004.06500","title":"SpaceNet 6: Multi-Sensor All Weather Mapping Dataset","created":"2020-04-14","cited_by_count":47},{"id":"2106.02740","title":"ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes","created":"2021-06-04","cited_by_count":47},{"id":"2007.08097","title":"TrashCan: A Semantically-Segmented Dataset towards Visual Detection of Marine Debris","created":"2020-07-16","cited_by_count":45},{"id":"2105.05409","title":"A Large-Scale Benchmark for Food Image Segmentation","created":"2021-05-12","cited_by_count":45},{"id":"2003.06975","title":"TACO: Trash Annotations in Context for Litter Detection","created":"2020-03-16","cited_by_count":38},{"id":"1807.01394","title":"ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations","created":"2018-07-03","cited_by_count":33},{"id":"1808.02473","title":"SketchyScene: Richly-Annotated Scene Sketches","created":"2018-08-07","cited_by_count":32},{"id":"2108.07020","title":"Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark","created":"2021-08-16","cited_by_count":31},{"id":"2207.06825","title":"Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions","created":"2022-07-14","cited_by_count":31},{"id":"2010.10032","title":"TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power Lines","created":"2020-10-20","cited_by_count":28},{"id":"2210.03416","title":"Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding","created":"2022-10-07","cited_by_count":26},{"id":"2211.13523","title":"Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark","created":"2022-11-24","cited_by_count":26},{"id":"2005.13359","title":"NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation","created":"2020-05-27","cited_by_count":24},{"id":"2101.00535","title":"RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs using a Novel Multi-scale Generative Adversarial Network","created":"2021-01-03","cited_by_count":24},{"id":"2102.09528","title":"Image Compositing for Segmentation of Surgical Tools without Manual Annotations","created":"2021-02-18","cited_by_count":23},{"id":"2203.03238","title":"Semantic Segmentation in Art Paintings","created":"2022-03-07","cited_by_count":23},{"id":"2207.10614","title":"A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing","created":"2022-07-21","cited_by_count":23},{"id":"2112.00570","title":"Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark","created":"2021-12-01","cited_by_count":22},{"id":"2101.03409","title":"Active Fire Detection in Landsat-8 Imagery: a Large-Scale Dataset and a Deep-Learning Study","created":"2021-01-09","cited_by_count":21},{"id":"1804.08292","title":"MVTec D2S: Densely Segmented Supermarket Dataset","created":"2018-04-23","cited_by_count":20},{"id":"2003.10299","title":"Robust Medical Instrument Segmentation Challenge 2019","created":"2020-03-23","cited_by_count":20},{"id":"1803.03317","title":"Analysis of Hand Segmentation in the Wild","created":"2018-03-08","cited_by_count":18},{"id":"2012.03111","title":"LandCoverNet: A global benchmark land cover classification training dataset","created":"2020-12-05","cited_by_count":18},{"id":"1706.06169","title":"Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition","created":"2017-06-19","cited_by_count":10},{"id":"2111.11567","title":"ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images","created":"2021-11-22","cited_by_count":10},{"id":"2209.09070","title":"SOCRATES: A Stereo Camera Trap for Monitoring of Biodiversity","created":"2022-09-19","cited_by_count":10},{"id":"2107.12499","title":"CalCROP21: A Georeferenced multi-spectral dataset of Satellite Imagery and Crop Labels","created":"2021-07-26","cited_by_count":8},{"id":"1702.03600","title":"Underwater Optical Image Processing: A Comprehensive Review","created":"2017-02-13","cited_by_count":7},{"id":"1807.06081","title":"A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation","created":"2018-07-16","cited_by_count":7},{"id":"2212.02749","title":"A Hyperspectral and RGB Dataset for Building Facade Segmentation","created":"2022-12-06","cited_by_count":7},{"id":"2301.00345","title":"MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction","created":"2023-01-01","cited_by_count":7},{"id":"2303.08692","title":"SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation","created":"2023-03-15","cited_by_count":7},{"id":"2212.09368","title":"TAS-NIR: A VIS+NIR Dataset for Fine-grained Semantic Segmentation in Unstructured Outdoor Environments","created":"2022-12-19","cited_by_count":5},{"id":"1606.02382","title":"Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation","created":"2016-06-08","cited_by_count":4}],"next_cursor":"100"}