{"list":"other","total":54,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"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":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1711.02512","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","created":"2017-11-03","cited_by_count":499},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1612.06321","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","created":"2016-12-19","cited_by_count":238},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"1611.10012","title":"Speed/accuracy trade-offs for modern convolutional object detectors","created":"2016-11-30","cited_by_count":198},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"id":"1909.02701","title":"Visual Semantic Reasoning for Image-Text Matching","created":"2019-09-06","cited_by_count":185},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"1604.01325","title":"Deep Image Retrieval: Learning global representations for image search","created":"2016-04-05","cited_by_count":147},{"id":"1511.06078","title":"Learning Deep Structure-Preserving Image-Text Embeddings","created":"2015-11-19","cited_by_count":139},{"id":"2001.07966","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","created":"2020-01-22","cited_by_count":137},{"id":"2011.04305","title":"Learning the Best Pooling Strategy for Visual Semantic Embedding","created":"2020-11-09","cited_by_count":137},{"id":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121},{"id":"2003.03772","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","created":"2020-03-08","cited_by_count":115},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"1909.05506","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","created":"2019-09-12","cited_by_count":110},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"1703.05605","title":"Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval","created":"2017-03-16","cited_by_count":68},{"id":"1608.01807","title":"SIFT Meets CNN: A Decade Survey of Instance Retrieval","created":"2016-08-05","cited_by_count":67},{"id":"1910.05134","title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","created":"2019-10-11","cited_by_count":66},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64},{"id":"2008.05231","title":"Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders","created":"2020-08-12","cited_by_count":47},{"id":"2010.03403","title":"Universal Weighting Metric Learning for Cross-Modal Matching","created":"2020-10-07","cited_by_count":34},{"id":"2003.03669","title":"Adaptive Offline Quintuplet Loss for Image-Text Matching","created":"2020-03-07","cited_by_count":26},{"id":"1504.06063","title":"Multimodal Convolutional Neural Networks for Matching Image and Sentence","created":"2015-04-23","cited_by_count":25},{"id":"1706.06064","title":"Recent Advance in Content-based Image Retrieval: A Literature Survey","created":"2017-06-19","cited_by_count":24},{"id":"2004.09144","title":"Transformer Reasoning Network for Image-Text Matching and Retrieval","created":"2020-04-20","cited_by_count":19},{"id":"1608.07973","title":"Linking Image and Text with 2-Way Nets","created":"2016-08-29","cited_by_count":14},{"id":"2010.02949","title":"Learning to Represent Image and Text with Denotation Graph","created":"2020-10-06","cited_by_count":13},{"id":"2010.14438","title":"Structured Visual Search via Composition-aware Learning","created":"2020-10-27","cited_by_count":5},{"id":"1709.09106","title":"Region-Based Image Retrieval Revisited","created":"2017-09-26","cited_by_count":4},{"id":"1908.06327","title":"Language Features Matter: Effective Language Representations for Vision-Language Tasks","created":"2019-08-17","cited_by_count":4},{"id":"1407.4764","title":"Efficient On-the-fly Category Retrieval using ConvNets and GPUs","created":"2014-07-17","cited_by_count":2},{"id":"1611.09392","title":"Generating Holistic 3D Scene Abstractions for Text-based Image Retrieval","created":"2016-11-28","cited_by_count":2},{"id":"1909.12526","title":"Query by Semantic Sketch","created":"2019-09-27","cited_by_count":2},{"id":"1509.08902","title":"Scalable Nonlinear Embeddings for Semantic Category-based Image Retrieval","created":"2015-09-29","cited_by_count":1}],"next_cursor":null}