{"list":"other","total":57,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1705.09655","title":"Style Transfer from Non-Parallel Text by Cross-Alignment","created":"2017-05-26","cited_by_count":248},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104},{"id":"1703.10660","title":"Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images","created":"2017-03-30","cited_by_count":101},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88},{"id":"2110.07356","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","created":"2021-09-09","cited_by_count":76},{"id":"1703.06029","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","created":"2017-03-17","cited_by_count":59},{"id":"1707.02268","title":"Text Summarization Techniques: A Brief Survey","created":"2017-07-07","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":"1611.08002","title":"Semantic Compositional Networks for Visual Captioning","created":"2016-11-23","cited_by_count":50},{"id":"1903.12020","title":"Describing like humans: on diversity in image captioning","created":"2019-03-28","cited_by_count":46},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41},{"id":"1611.06949","title":"Dense Captioning with Joint Inference and Visual Context","created":"2016-11-21","cited_by_count":40},{"id":"2111.08940","title":"Transparent Human Evaluation for Image Captioning","created":"2021-11-17","cited_by_count":40},{"id":"1903.05942","title":"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning","created":"2019-03-14","cited_by_count":35},{"id":"1711.07068","title":"Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space","created":"2017-11-19","cited_by_count":33},{"id":"1904.01410","title":"Context and Attribute Grounded Dense Captioning","created":"2019-04-02","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":"2010.13588","title":"Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale","created":"2020-10-26","cited_by_count":28},{"id":"1703.07022","title":"Recurrent Topic-Transition GAN for Visual Paragraph Generation","created":"2017-03-21","cited_by_count":25},{"id":"2006.01997","title":"Automatic Text Summarization of COVID-19 Medical Research Articles using BERT and GPT-2","created":"2020-06-03","cited_by_count":23},{"id":"2011.00966","title":"Diverse Image Captioning with Context-Object Split Latent Spaces","created":"2020-11-02","cited_by_count":22},{"id":"1908.08529","title":"Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning","created":"2019-08-22","cited_by_count":21},{"id":"2206.01843","title":"Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning","created":"2022-06-03","cited_by_count":21},{"id":"1909.03396","title":"Quality Estimation for Image Captions Based on Large-scale Human Evaluations","created":"2019-09-08","cited_by_count":17},{"id":"2002.06661","title":"Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings","created":"2020-02-16","cited_by_count":16},{"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":"2204.03938","title":"On Distinctive Image Captioning via Comparing and Reweighting","created":"2022-04-08","cited_by_count":7},{"id":"2205.06253","title":"What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics","created":"2022-05-12","cited_by_count":6},{"id":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6},{"id":"2205.01813","title":"Diverse Image Captioning with Grounded Style","created":"2022-05-03","cited_by_count":3}],"next_cursor":null}