{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1802.05300","title":"Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise","created":"2018-02-14","cited_by_count":216},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"1703.02391","title":"Learning from Noisy Labels with Distillation","created":"2017-03-07","cited_by_count":161},{"id":"1910.03231","title":"Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates","created":"2019-10-08","cited_by_count":142},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"1701.01619","title":"Learning From Noisy Large-Scale Datasets With Minimal Supervision","created":"2017-01-06","cited_by_count":115},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"id":"2003.00387","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","created":"2020-03-01","cited_by_count":87},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"1910.05134","title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","created":"2019-10-11","cited_by_count":66},{"id":"1811.10652","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","created":"2018-11-26","cited_by_count":65},{"id":"1912.08265","title":"Learning from Synthetic Animals","created":"2019-12-17","cited_by_count":65},{"id":"1905.05816","title":"Curriculum Learning for Domain Adaptation in Neural Machine Translation","created":"2019-05-14","cited_by_count":59},{"id":"1805.12589","title":"Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech","created":"2018-05-31","cited_by_count":55},{"id":"2007.11731","title":"Comprehensive Image Captioning via Scene Graph Decomposition","created":"2020-07-23","cited_by_count":52},{"id":"1805.01047","title":"EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction","created":"2018-05-02","cited_by_count":51},{"id":"1809.00068","title":"Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection","created":"2018-08-31","cited_by_count":43},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41},{"id":"2007.09580","title":"Length-Controllable Image Captioning","created":"2020-07-19","cited_by_count":36},{"id":"1903.05942","title":"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning","created":"2019-03-14","cited_by_count":35},{"id":"2102.04990","title":"In Defense of Scene Graphs for Image Captioning","created":"2021-02-09","cited_by_count":31},{"id":"1906.02365","title":"Context-Aware Visual Policy Network for Fine-Grained Image Captioning","created":"2019-06-06","cited_by_count":29},{"id":"1805.07030","title":"SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text","created":"2018-05-18","cited_by_count":27},{"id":"1807.03871","title":"\"Factual\" or \"Emotional\": Stylized Image Captioning with Adaptive Learning and Attention","created":"2018-07-10","cited_by_count":26},{"id":"1902.05715","title":"Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention","created":"2019-02-15","cited_by_count":26},{"id":"1703.07022","title":"Recurrent Topic-Transition GAN for Visual Paragraph Generation","created":"2017-03-21","cited_by_count":25},{"id":"2005.00908","title":"Clue: Cross-modal Coherence Modeling for Caption Generation","created":"2020-05-02","cited_by_count":24},{"id":"1905.03743","title":"Interactive Image Generation Using Scene Graphs","created":"2019-05-09","cited_by_count":17},{"id":"1704.06972","title":"Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition","created":"2017-04-23","cited_by_count":15},{"id":"2107.12604","title":"Image Scene Graph Generation (SGG) Benchmark","created":"2021-07-27","cited_by_count":15},{"id":"1709.02279","title":"Cynical Selection of Language Model Training Data","created":"2017-09-07","cited_by_count":13},{"id":"1809.00681","title":"Diverse and Coherent Paragraph Generation from Images","created":"2018-09-03","cited_by_count":13},{"id":"1908.00169","title":"Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation","created":"2019-08-01","cited_by_count":10},{"id":"1908.00249","title":"Convolutional Auto-encoding of Sentence Topics for Image Paragraph Generation","created":"2019-08-01","cited_by_count":8},{"id":"1904.09348","title":"Compact Scene Graphs for Layout Composition and Patch Retrieval","created":"2019-04-19","cited_by_count":4}],"next_cursor":null}