{"list":"other","total":66,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1909.00161","title":"Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach","created":"2019-08-31","cited_by_count":308},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1712.00981","title":"Feature Generating Networks for Zero-Shot Learning","created":"2017-12-04","cited_by_count":257},{"id":"1703.04394","title":"Zero-Shot Learning -- The Good, the Bad and the Ugly","created":"2017-03-13","cited_by_count":255},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2001.01526","title":"Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification","created":"2020-01-06","cited_by_count":215},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"1409.8403","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","created":"2014-09-30","cited_by_count":166},{"id":"1503.08677","title":"Label-Embedding for Image Classification","created":"2015-03-30","cited_by_count":165},{"id":"1903.10132","title":"f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning","created":"2019-03-25","cited_by_count":164},{"id":"2008.08290","title":"Attribute Prototype Network for Zero-Shot Learning","created":"2020-08-19","cited_by_count":160},{"id":"1803.08035","title":"Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs","created":"2018-03-21","cited_by_count":155},{"id":"1312.5650","title":"Zero-Shot Learning by Convex Combination of Semantic Embeddings","created":"2013-12-19","cited_by_count":135},{"id":"1712.03878","title":"Generalized Zero-Shot Learning via Synthesized Examples","created":"2017-12-11","cited_by_count":114},{"id":"1603.00550","title":"Synthesized Classifiers for Zero-Shot Learning","created":"2016-03-02","cited_by_count":113},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95},{"id":"2103.16173","title":"Contrastive Embedding for Generalized Zero-Shot Learning","created":"2021-03-30","cited_by_count":94},{"id":"1805.11724","title":"Rethinking Knowledge Graph Propagation for Zero-Shot Learning","created":"2018-05-29","cited_by_count":87},{"id":"2006.14610","title":"A causal view of compositional zero-shot recognition","created":"2020-06-25","cited_by_count":78},{"id":"2003.13261","title":"Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning","created":"2020-03-30","cited_by_count":71},{"id":"2103.03433","title":"Goal-Oriented Gaze Estimation for Zero-Shot Learning","created":"2021-03-05","cited_by_count":68},{"id":"2107.13807","title":"FREE: Feature Refinement for Generalized Zero-Shot Learning","created":"2021-07-29","cited_by_count":67},{"id":"1712.01928","title":"Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks","created":"2017-12-05","cited_by_count":66},{"id":"1909.03360","title":"Episode-based Prototype Generating Network for Zero-Shot Learning","created":"2019-09-08","cited_by_count":66},{"id":"1908.05832","title":"Transferable Contrastive Network for Generalized Zero-Shot Learning","created":"2019-08-16","cited_by_count":64},{"id":"1903.00502","title":"Semantic-Guided Multi-Attention Localization for Zero-Shot Learning","created":"2019-03-01","cited_by_count":58},{"id":"2109.15163","title":"HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning","created":"2021-09-30","cited_by_count":57},{"id":"1703.05908","title":"Learning Robust Visual-Semantic Embeddings","created":"2017-03-17","cited_by_count":56},{"id":"2004.00666","title":"Generalized Zero-Shot Learning Via Over-Complete Distribution","created":"2020-04-01","cited_by_count":56},{"id":"2007.01546","title":"Multiple Expert Brainstorming for Domain Adaptive Person Re-identification","created":"2020-07-03","cited_by_count":56},{"id":"2101.07978","title":"Semantics Disentangling for Generalized Zero-Shot Learning","created":"2021-01-20","cited_by_count":56},{"id":"2112.01683","title":"TransZero: Attribute-guided Transformer for Zero-Shot Learning","created":"2021-12-03","cited_by_count":54},{"id":"1501.04560","title":"Transductive Multi-view Zero-Shot Learning","created":"2015-01-19","cited_by_count":53},{"id":"2007.04873","title":"Invertible Zero-Shot Recognition Flows","created":"2020-07-09","cited_by_count":48},{"id":"2008.00923","title":"Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning","created":"2020-08-03","cited_by_count":46},{"id":"1803.11320","title":"Transductive Unbiased Embedding for Zero-Shot Learning","created":"2018-03-30","cited_by_count":44},{"id":"1803.02284","title":"Zero-Shot Sketch-Image Hashing","created":"2018-03-06","cited_by_count":43},{"id":"1605.08151","title":"Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning","created":"2016-05-26","cited_by_count":30},{"id":"1710.04837","title":"Recent Advances in Zero-shot Recognition","created":"2017-10-13","cited_by_count":28},{"id":"1803.06731","title":"Discriminative Learning of Latent Features for Zero-Shot Recognition","created":"2018-03-18","cited_by_count":24},{"id":"2109.14133","title":"Fine-Grained Zero-Shot Learning with DNA as Side Information","created":"2021-09-29","cited_by_count":20},{"id":"1810.08332","title":"Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning","created":"2018-10-19","cited_by_count":15},{"id":"2006.11397","title":"Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval","created":"2020-06-20","cited_by_count":10},{"id":"1705.05512","title":"Cooperative Learning with Visual Attributes","created":"2017-05-16","cited_by_count":8},{"id":"1904.04957","title":"On zero-shot recognition of generic objects","created":"2019-04-10","cited_by_count":6},{"id":"2110.07130","title":"Region Semantically Aligned Network for Zero-Shot Learning","created":"2021-10-14","cited_by_count":6}],"next_cursor":null}