{"list":"other","total":64,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"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":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2106.01226","title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","created":"2021-06-02","cited_by_count":463},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2103.16372","title":"Source-Free Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":168},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"id":"2007.03943","title":"Remix: Rebalanced Mixup","created":"2020-07-08","cited_by_count":144},{"id":"2004.00431","title":"M2m: Imbalanced Classification via Major-to-minor Translation","created":"2020-04-01","cited_by_count":134},{"id":"1512.05830","title":"Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks","created":"2015-12-18","cited_by_count":115},{"id":"1807.07428","title":"Modeling Visual Context is Key to Augmenting Object Detection Datasets","created":"2018-07-19","cited_by_count":106},{"id":"2110.05474","title":"Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning","created":"2021-10-11","cited_by_count":101},{"id":"2112.00412","title":"The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification","created":"2021-12-01","cited_by_count":100},{"id":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75},{"id":"1611.08408","title":"Semantic Segmentation using Adversarial Networks","created":"2016-11-25","cited_by_count":73},{"id":"1504.01013","title":"Efficient piecewise training of deep structured models for semantic segmentation","created":"2015-04-04","cited_by_count":71},{"id":"1804.03287","title":"Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing","created":"2018-04-10","cited_by_count":60},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"2010.05210","title":"Generalized Few-shot Semantic Segmentation","created":"2020-10-11","cited_by_count":59},{"id":"2102.01066","title":"Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details","created":"2021-02-01","cited_by_count":57},{"id":"1811.12596","title":"Parsing R-CNN for Instance-Level Human Analysis","created":"2018-11-30","cited_by_count":53},{"id":"1702.08272","title":"A Dataset for Developing and Benchmarking Active Vision","created":"2017-02-27","cited_by_count":50},{"id":"2212.03863","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","created":"2022-12-07","cited_by_count":49},{"id":"2104.08569","title":"RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features","created":"2021-04-17","cited_by_count":47},{"id":"2201.02593","title":"Equalized Focal Loss for Dense Long-Tailed Object Detection","created":"2022-01-07","cited_by_count":46},{"id":"1509.02634","title":"Semantic Image Segmentation via Deep Parsing Network","created":"2015-09-09","cited_by_count":44},{"id":"2003.04262","title":"Cascaded Human-Object Interaction Recognition","created":"2020-03-09","cited_by_count":40},{"id":"2303.07336","title":"MP-Former: Mask-Piloted Transformer for Image Segmentation","created":"2023-03-13","cited_by_count":39},{"id":"1811.12026","title":"Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network","created":"2018-11-29","cited_by_count":38},{"id":"2104.06402","title":"DropLoss for Long-Tail Instance Segmentation","created":"2021-04-13","cited_by_count":32},{"id":"2306.02061","title":"Balancing Logit Variation for Long-tailed Semantic Segmentation","created":"2023-06-03","cited_by_count":26},{"id":"2012.14700","title":"Image-to-Image Retrieval by Learning Similarity between Scene Graphs","created":"2020-12-29","cited_by_count":23},{"id":"2003.08736","title":"Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes","created":"2020-03-11","cited_by_count":19},{"id":"2301.00394","title":"Deep Learning Technique for Human Parsing: A Survey and Outlook","created":"2023-01-01","cited_by_count":18},{"id":"2204.01969","title":"Region Rebalance for Long-Tailed Semantic Segmentation","created":"2022-04-05","cited_by_count":17},{"id":"2112.07383","title":"Improving Human-Object Interaction Detection via Phrase Learning and Label Composition","created":"2021-12-14","cited_by_count":15},{"id":"2111.12263","title":"APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation","created":"2021-11-24","cited_by_count":11},{"id":"2203.04187","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","created":"2022-03-08","cited_by_count":11},{"id":"2112.07999","title":"Self-Ensembling GAN for Cross-Domain Semantic Segmentation","created":"2021-12-15","cited_by_count":7}],"next_cursor":null}