{"list":"other","total":62,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1707.09835","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","created":"2017-07-31","cited_by_count":379},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"1309.4168","title":"Exploiting Similarities among Languages for Machine Translation","created":"2013-09-17","cited_by_count":191},{"id":"1604.04573","title":"CNN-RNN: A Unified Framework for Multi-label Image Classification","created":"2016-04-15","cited_by_count":190},{"id":"1902.09720","title":"Learning a Deep ConvNet for Multi-label Classification with Partial Labels","created":"2019-02-26","cited_by_count":124},{"id":"1903.12290","title":"Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning","created":"2019-03-28","cited_by_count":121},{"id":"1909.08174","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","created":"2019-09-18","cited_by_count":118},{"id":"1905.01436","title":"Edge-labeling Graph Neural Network for Few-shot Learning","created":"2019-05-04","cited_by_count":114},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102},{"id":"1902.07104","title":"Adaptive Cross-Modal Few-Shot Learning","created":"2019-02-19","cited_by_count":95},{"id":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88},{"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":"2005.13826","title":"Boosting Few-Shot Learning With Adaptive Margin Loss","created":"2020-05-28","cited_by_count":83},{"id":"2106.09708","title":"Multi-Label Learning from Single Positive Labels","created":"2021-06-17","cited_by_count":81},{"id":"1912.07872","title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","created":"2019-12-17","cited_by_count":79},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70},{"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":"2104.07841","title":"Pareto Self-Supervised Training for Few-Shot Learning","created":"2021-04-16","cited_by_count":52},{"id":"2108.02456","title":"Residual Attention: A Simple but Effective Method for Multi-Label Recognition","created":"2021-08-05","cited_by_count":52},{"id":"2211.12739","title":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","created":"2022-11-23","cited_by_count":51},{"id":"1911.09996","title":"Orderless Recurrent Models for Multi-label Classification","created":"2019-11-22","cited_by_count":46},{"id":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44},{"id":"1902.09811","title":"LaSO: Label-Set Operations networks for multi-label few-shot learning","created":"2019-02-26","cited_by_count":38},{"id":"1906.05750","title":"The iMaterialist Fashion Attribute Dataset","created":"2019-06-13","cited_by_count":37},{"id":"1707.05495","title":"Order-Free RNN with Visual Attention for Multi-Label Classification","created":"2017-07-18","cited_by_count":26},{"id":"2109.09237","title":"MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models","created":"2021-09-19","cited_by_count":18},{"id":"1603.09065","title":"Structured Feature Learning for Pose Estimation","created":"2016-03-30","cited_by_count":17},{"id":"2207.11169","title":"Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark","created":"2022-07-22","cited_by_count":17},{"id":"2112.01037","title":"Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention","created":"2021-12-02","cited_by_count":15},{"id":"2405.08815","title":"Efficient Vision-Language Pre-training by Cluster Masking","created":"2024-05-14","cited_by_count":13},{"id":"2105.10195","title":"Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning","created":"2021-05-21","cited_by_count":12},{"id":"2203.04049","title":"Graph Attention Transformer Network for Multi-Label Image Classification","created":"2022-03-08","cited_by_count":11},{"id":"2210.02771","title":"Modelling Commonsense Properties using Pre-Trained Bi-Encoders","created":"2022-10-06","cited_by_count":9},{"id":"2305.09785","title":"Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models","created":"2023-05-16","cited_by_count":8},{"id":"2012.07580","title":"Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddings","created":"2020-12-04","cited_by_count":6},{"id":"2002.04193","title":"Compositional Embeddings for Multi-Label One-Shot Learning","created":"2020-02-11","cited_by_count":5},{"id":"2102.00801","title":"Few-shot Image Classification with Multi-Facet Prototypes","created":"2021-02-01","cited_by_count":3}],"next_cursor":null}