{"list":"other","total":55,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"1811.09716","title":"Robustness via curvature regularization, and vice versa","created":"2018-11-23","cited_by_count":175},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"1410.0210","title":"A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input","created":"2014-10-01","cited_by_count":112},{"id":"1411.4952","title":"From Captions to Visual Concepts and Back","created":"2014-11-18","cited_by_count":109},{"id":"1511.05099","title":"Yin and Yang: Balancing and Answering Binary Visual Questions","created":"2015-11-16","cited_by_count":109},{"id":"1703.09684","title":"An Analysis of Visual Question Answering Algorithms","created":"2017-03-28","cited_by_count":90},{"id":"1505.05612","title":"Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering","created":"2015-05-21","cited_by_count":80},{"id":"1603.01417","title":"Dynamic Memory Networks for Visual and Textual Question Answering","created":"2016-03-04","cited_by_count":62},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57},{"id":"1603.06059","title":"Generating Natural Questions About an Image","created":"2016-03-19","cited_by_count":56},{"id":"1610.01465","title":"Visual Question Answering: Datasets, Algorithms, and Future Challenges","created":"2016-10-05","cited_by_count":56},{"id":"1510.07712","title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","created":"2015-10-26","cited_by_count":54},{"id":"1505.01121","title":"Ask Your Neurons: A Neural-based Approach to Answering Questions about Images","created":"2015-05-05","cited_by_count":51},{"id":"2202.05798","title":"The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention","created":"2022-02-11","cited_by_count":46},{"id":"2011.00569","title":"DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation","created":"2020-11-01","cited_by_count":43},{"id":"1511.06973","title":"Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources","created":"2015-11-22","cited_by_count":42},{"id":"1902.07864","title":"Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering","created":"2019-02-21","cited_by_count":38},{"id":"1511.05756","title":"Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction","created":"2015-11-18","cited_by_count":26},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","cited_by_count":26},{"id":"2004.03661","title":"Query-controllable Video Summarization","created":"2020-04-07","cited_by_count":24},{"id":"1506.00333","title":"Learning to Answer Questions From Image Using Convolutional Neural Network","created":"2015-06-01","cited_by_count":23},{"id":"1711.06232","title":"A Novel Framework for Robustness Analysis of Visual QA Models","created":"2017-11-16","cited_by_count":20},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20},{"id":"1703.06492","title":"VQABQ: Visual Question Answering by Basic Questions","created":"2017-03-19","cited_by_count":17},{"id":"1709.04625","title":"Robustness Analysis of Visual QA Models by Basic Questions","created":"2017-09-14","cited_by_count":17},{"id":"1806.06423","title":"A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases","created":"2018-06-17","cited_by_count":16},{"id":"2104.12471","title":"Contextualized Keyword Representations for Multi-modal Retinal Image Captioning","created":"2021-04-26","cited_by_count":16},{"id":"2105.14538","title":"Longer Version for \"Deep Context-Encoding Network for Retinal Image Captioning\"","created":"2021-05-30","cited_by_count":16},{"id":"1902.04147","title":"Synthesizing New Retinal Symptom Images by Multiple Generative Models","created":"2019-02-11","cited_by_count":15},{"id":"1808.05754","title":"Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model","created":"2018-08-16","cited_by_count":9},{"id":"1605.02697","title":"Ask Your Neurons: A Deep Learning Approach to Visual Question Answering","created":"2016-05-09","cited_by_count":7},{"id":"1410.8027","title":"Towards a Visual Turing Challenge","created":"2014-10-29","cited_by_count":5},{"id":"1511.04670","title":"Uncovering Temporal Context for Video Question and Answering","created":"2015-11-15","cited_by_count":3},{"id":"1501.03302","title":"Hard to Cheat: A Turing Test based on Answering Questions about Images","created":"2015-01-14","cited_by_count":1}],"next_cursor":null}