{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"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":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"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":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"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":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"2012.15409","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","created":"2020-12-31","cited_by_count":239},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176},{"id":"2011.02593","title":"Detecting Hallucinated Content in Conditional Neural Sequence Generation","created":"2020-11-05","cited_by_count":152},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102},{"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":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89},{"id":"2110.01705","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","created":"2021-10-04","cited_by_count":76},{"id":"2210.07688","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","created":"2022-10-14","cited_by_count":72},{"id":"1903.00802","title":"Calibration of Encoder Decoder Models for Neural Machine Translation","created":"2019-03-03","cited_by_count":68},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"2005.00963","title":"On the Inference Calibration of Neural Machine Translation","created":"2020-05-03","cited_by_count":61},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47},{"id":"1807.10018","title":"Move Forward and Tell: A Progressive Generator of Video Descriptions","created":"2018-07-26","cited_by_count":35},{"id":"2109.06352","title":"Uncertainty-Aware Machine Translation Evaluation","created":"2021-09-13","cited_by_count":35},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33},{"id":"2211.07443","title":"Calibrated Interpretation: Confidence Estimation in Semantic Parsing","created":"2022-11-14","cited_by_count":33},{"id":"2105.13868","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","created":"2021-05-28","cited_by_count":21},{"id":"2003.03107","title":"Show, Edit and Tell: A Framework for Editing Image Captions","created":"2020-03-06","cited_by_count":18},{"id":"2212.10549","title":"Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment","created":"2022-12-20","cited_by_count":17},{"id":"1909.03169","title":"Look and Modify: Modification Networks for Image Captioning","created":"2019-09-07","cited_by_count":10},{"id":"2207.09625","title":"Explicit Image Caption Editing","created":"2022-07-20","cited_by_count":7},{"id":"2207.10897","title":"Efficient Modeling of Future Context for Image Captioning","created":"2022-07-22","cited_by_count":5},{"id":"2010.08101","title":"Modeling Token-level Uncertainty to Learn Unknown Concepts in SLU via Calibrated Dirichlet Prior RNN","created":"2020-10-16","cited_by_count":4}],"next_cursor":null}