{"list":"other","total":63,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"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":"1812.03299","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","created":"2018-12-08","cited_by_count":140},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","cited_by_count":111},{"id":"1611.09978","title":"Modeling Relationships in Referential Expressions with Compositional Modular Networks","created":"2016-11-30","cited_by_count":106},{"id":"2006.09920","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","created":"2020-06-17","cited_by_count":102},{"id":"1906.01784","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","created":"2019-06-05","cited_by_count":98},{"id":"1712.01892","title":"Grounding Referring Expressions in Images by Variational Context","created":"2017-12-05","cited_by_count":82},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"1908.07129","title":"Zero-Shot Grounding of Objects from Natural Language Queries","created":"2019-08-20","cited_by_count":79},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"1812.03426","title":"Real-Time Referring Expression Comprehension by Single-Stage Grounding Network","created":"2018-12-09","cited_by_count":56},{"id":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"1903.11649","title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","created":"2019-03-27","cited_by_count":51},{"id":"2007.01951","title":"Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation","created":"2020-07-03","cited_by_count":51},{"id":"1805.03508","title":"Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding","created":"2018-05-09","cited_by_count":49},{"id":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41},{"id":"1705.01371","title":"Weakly-supervised Visual Grounding of Phrases with Linguistic Structures","created":"2017-05-03","cited_by_count":40},{"id":"2112.14238","title":"AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition","created":"2021-12-28","cited_by_count":37},{"id":"2103.12989","title":"Relation-aware Instance Refinement for Weakly Supervised Visual Grounding","created":"2021-03-24","cited_by_count":35},{"id":"2104.04382","title":"CondenseNet V2: Sparse Feature Reactivation for Deep Networks","created":"2021-04-09","cited_by_count":34},{"id":"2110.00428","title":"Zero-shot Natural Language Video Localization","created":"2021-08-29","cited_by_count":34},{"id":"1803.03879","title":"Knowledge Aided Consistency for Weakly Supervised Phrase Grounding","created":"2018-03-11","cited_by_count":32},{"id":"1510.06939","title":"Objects2action: Classifying and localizing actions without any video example","created":"2015-10-23","cited_by_count":26},{"id":"1908.07553","title":"Phrase Localization Without Paired Training Examples","created":"2019-08-20","cited_by_count":24},{"id":"1909.02860","title":"Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding","created":"2019-09-05","cited_by_count":21},{"id":"2106.04053","title":"Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding","created":"2021-06-08","cited_by_count":21},{"id":"1611.05546","title":"Zero-Shot Visual Question Answering","created":"2016-11-17","cited_by_count":20},{"id":"2003.05583","title":"ZSTAD: Zero-Shot Temporal Activity Detection","created":"2020-03-12","cited_by_count":16},{"id":"1803.11185","title":"Unsupervised Textual Grounding: Linking Words to Image Concepts","created":"2018-03-29","cited_by_count":13},{"id":"1705.01734","title":"Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning","created":"2017-05-04","cited_by_count":12},{"id":"1812.03213","title":"PIRC Net : Using Proposal Indexing, Relationships and Context for Phrase Grounding","created":"2018-12-07","cited_by_count":7},{"id":"1905.11539","title":"Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes","created":"2019-05-27","cited_by_count":3}],"next_cursor":null}