{"list":"other","total":56,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"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":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1905.03670","title":"S4L: Self-Supervised Semi-Supervised Learning","created":"2019-05-09","cited_by_count":335},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2012.11014","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","created":"2020-12-20","cited_by_count":125},{"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":"2110.08484","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","created":"2021-10-16","cited_by_count":101},{"id":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84},{"id":"1809.02805","title":"Faithful Multimodal Explanation for Visual Question Answering","created":"2018-09-08","cited_by_count":64},{"id":"1603.01417","title":"Dynamic Memory Networks for Visual and Textual Question Answering","created":"2016-03-04","cited_by_count":62},{"id":"1807.09956","title":"Pythia v0.1: the Winning Entry to the VQA Challenge 2018","created":"2018-07-26","cited_by_count":62},{"id":"1903.11260","title":"Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods","created":"2019-03-27","cited_by_count":62},{"id":"1905.09998","title":"Self-Critical Reasoning for Robust Visual Question Answering","created":"2019-05-24","cited_by_count":61},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60},{"id":"1709.01362","title":"Predicting Visual Features from Text for Image and Video Caption Retrieval","created":"2017-09-05","cited_by_count":53},{"id":"2010.07526","title":"Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs","created":"2020-10-15","cited_by_count":46},{"id":"1909.03918","title":"Hierarchy Parsing for Image Captioning","created":"2019-09-09","cited_by_count":44},{"id":"1908.06306","title":"U-CAM: Visual Explanation using Uncertainty based Class Activation Maps","created":"2019-08-17","cited_by_count":36},{"id":"1707.04968","title":"Visual Question Answering with Memory-Augmented Networks","created":"2017-07-17","cited_by_count":25},{"id":"2112.06204","title":"Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup","created":"2021-12-12","cited_by_count":16},{"id":"2205.12469","title":"Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI","created":"2022-05-25","cited_by_count":11},{"id":"2205.02456","title":"Declaration-based Prompt Tuning for Visual Question Answering","created":"2022-05-05","cited_by_count":9},{"id":"2207.11401","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","created":"2022-07-23","cited_by_count":8},{"id":"2211.05190","title":"Towards Reasoning-Aware Explainable VQA","created":"2022-11-09","cited_by_count":2}],"next_cursor":null}