{"list":"other","total":55,"rows":[{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1910.12933","title":"Hyperbolic Graph Convolutional Neural Networks","created":"2019-10-28","cited_by_count":402},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"1904.02239","title":"Hyperbolic Image Embeddings","created":"2019-04-03","cited_by_count":221},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1904.09658","title":"Probabilistic Face Embeddings","created":"2019-04-21","cited_by_count":173},{"id":"1810.06546","title":"Poincar\\'e GloVe: Hyperbolic Word Embeddings","created":"2018-10-15","cited_by_count":156},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129},{"id":"2203.10833","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","created":"2022-03-21","cited_by_count":111},{"id":"2203.05898","title":"Hyperbolic Image Segmentation","created":"2022-03-11","cited_by_count":102},{"id":"1905.01298","title":"SCOPS: Self-Supervised Co-Part Segmentation","created":"2019-05-03","cited_by_count":100},{"id":"1412.6623","title":"Word Representations via Gaussian Embedding","created":"2014-12-20","cited_by_count":96},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57},{"id":"2204.03609","title":"Pin the Memory: Learning to Generalize Semantic Segmentation","created":"2022-04-07","cited_by_count":49},{"id":"2104.01257","title":"Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision","created":"2021-04-02","cited_by_count":39},{"id":"2003.04845","title":"Hierarchical Human Parsing with Typed Part-Relation Reasoning","created":"2020-03-10","cited_by_count":38},{"id":"2001.06804","title":"Learning Compositional Neural Information Fusion for Human Parsing","created":"2020-01-19","cited_by_count":36},{"id":"2103.05271","title":"Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation","created":"2021-03-09","cited_by_count":35},{"id":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","cited_by_count":34},{"id":"2010.16143","title":"HyperText: Endowing FastText with Hyperbolic Geometry","created":"2020-10-30","cited_by_count":28},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28},{"id":"2212.14258","title":"HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization","created":"2022-12-29","cited_by_count":26},{"id":"2304.00779","title":"Probabilistic Prompt Learning for Dense Prediction","created":"2023-04-03","cited_by_count":17},{"id":"2210.00314","title":"Learning Hierarchical Image Segmentation For Recognition and By Recognition","created":"2022-10-01","cited_by_count":16},{"id":"1804.09843","title":"Hierarchical Density Order Embeddings","created":"2018-04-26","cited_by_count":13},{"id":"1704.08424","title":"Multimodal Word Distributions","created":"2017-04-27","cited_by_count":12},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12},{"id":"2011.14211","title":"Curvature Regularization to Prevent Distortion in Graph Embedding","created":"2020-11-28","cited_by_count":8},{"id":"2009.04264","title":"Unsupervised Part Discovery by Unsupervised Disentanglement","created":"2020-09-09","cited_by_count":5}],"next_cursor":null}