{"list":"other","total":52,"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"1604.04573","title":"CNN-RNN: A Unified Framework for Multi-label Image Classification","created":"2016-04-15","cited_by_count":190},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"1503.08677","title":"Label-Embedding for Image Classification","created":"2015-03-30","cited_by_count":165},{"id":"1511.02251","title":"Learning Visual Features from Large Weakly Supervised Data","created":"2015-11-06","cited_by_count":165},{"id":"1312.5650","title":"Zero-Shot Learning by Convex Combination of Semantic Embeddings","created":"2013-12-19","cited_by_count":135},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127},{"id":"1902.09720","title":"Learning a Deep ConvNet for Multi-label Classification with Partial Labels","created":"2019-02-26","cited_by_count":124},{"id":"1908.07325","title":"Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition","created":"2019-08-20","cited_by_count":116},{"id":"1612.09161","title":"Learning Visual N-Grams from Web Data","created":"2016-12-29","cited_by_count":95},{"id":"1702.05891","title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","created":"2017-02-20","cited_by_count":85},{"id":"1711.02816","title":"Multi-label Image Recognition by Recurrently Discovering Attentional Regions","created":"2017-11-08","cited_by_count":83},{"id":"1711.06526","title":"Multi-Label Zero-Shot Learning with Structured Knowledge Graphs","created":"2017-11-17","cited_by_count":72},{"id":"2009.09450","title":"Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition","created":"2020-09-20","cited_by_count":69},{"id":"1911.09243","title":"Multi-Label Classification with Label Graph Superimposing","created":"2019-11-21","cited_by_count":65},{"id":"1512.06974","title":"Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels","created":"2015-12-22","cited_by_count":64},{"id":"1807.03903","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","created":"2018-07-10","cited_by_count":56},{"id":"2108.02456","title":"Residual Attention: A Simple but Effective Method for Multi-Label Recognition","created":"2021-08-05","cited_by_count":52},{"id":"1911.09996","title":"Orderless Recurrent Models for Multi-label Classification","created":"2019-11-22","cited_by_count":46},{"id":"2112.10941","title":"Structured Semantic Transfer for Multi-Label Recognition with Partial Labels","created":"2021-12-21","cited_by_count":41},{"id":"1809.05884","title":"Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection","created":"2018-09-16","cited_by_count":37},{"id":"2203.02172","title":"Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels","created":"2022-03-04","cited_by_count":29},{"id":"2108.09301","title":"Discriminative Region-based Multi-Label Zero-Shot Learning","created":"2021-08-20","cited_by_count":27},{"id":"2105.05926","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","created":"2021-05-12","cited_by_count":24},{"id":"1605.09759","title":"Fast Zero-Shot Image Tagging","created":"2016-05-31","cited_by_count":21},{"id":"2101.11606","title":"Generative Multi-Label Zero-Shot Learning","created":"2021-01-27","cited_by_count":19},{"id":"1611.05490","title":"Semantic Regularisation for Recurrent Image Annotation","created":"2016-11-16","cited_by_count":14},{"id":"1803.06051","title":"Deep Multiple Instance Learning for Zero-shot Image Tagging","created":"2018-03-16","cited_by_count":8}],"next_cursor":null}