{"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"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":"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":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"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":"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":"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":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1911.11834","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","created":"2019-11-26","cited_by_count":252},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"1907.12461","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","created":"2019-07-29","cited_by_count":182},{"id":"1912.07726","title":"Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy","created":"2019-12-16","cited_by_count":156},{"id":"1906.02659","title":"Does Object Recognition Work for Everyone?","created":"2019-06-06","cited_by_count":151},{"id":"2004.07999","title":"REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets","created":"2020-04-16","cited_by_count":136},{"id":"1910.12008","title":"Fair Generative Modeling via Weak Supervision","created":"2019-10-26","cited_by_count":114},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89},{"id":"1902.11097","title":"Predictive Inequity in Object Detection","created":"2019-02-21","cited_by_count":77},{"id":"2201.11706","title":"A Systematic Study of Bias Amplification","created":"2022-01-27","cited_by_count":65},{"id":"2002.08911","title":"Measuring Social Biases in Grounded Vision and Language Embeddings","created":"2020-02-20","cited_by_count":61},{"id":"2207.09666","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","created":"2022-07-20","cited_by_count":56},{"id":"2102.12594","title":"Directional Bias Amplification","created":"2021-02-24","cited_by_count":54},{"id":"2104.08666","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models","created":"2021-04-18","cited_by_count":52},{"id":"2304.02828","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","created":"2023-04-06","cited_by_count":52},{"id":"2006.08315","title":"Mitigating Gender Bias in Captioning Systems","created":"2020-06-15","cited_by_count":50},{"id":"2205.08148","title":"Gender and Racial Bias in Visual Question Answering Datasets","created":"2022-05-17","cited_by_count":39},{"id":"2203.15395","title":"Quantifying Societal Bias Amplification in Image Captioning","created":"2022-03-29","cited_by_count":37},{"id":"1912.00578","title":"Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models","created":"2019-12-02","cited_by_count":36},{"id":"2102.02320","title":"One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision","created":"2021-02-03","cited_by_count":33},{"id":"1812.08999","title":"Feature-Wise Bias Amplification","created":"2018-12-21","cited_by_count":31},{"id":"2207.01056","title":"Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models","created":"2022-07-03","cited_by_count":28},{"id":"2001.09528","title":"Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses","created":"2020-01-26","cited_by_count":27},{"id":"2005.06251","title":"Mitigating Gender Bias Amplification in Distribution by Posterior Regularization","created":"2020-05-13","cited_by_count":27},{"id":"2210.11924","title":"Men Also Do Laundry: Multi-Attribute Bias Amplification","created":"2022-10-21","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":"2109.00545","title":"Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks","created":"2021-09-01","cited_by_count":16},{"id":"1704.07434","title":"Paying Attention to Descriptions Generated by Image Captioning Models","created":"2017-04-24","cited_by_count":12},{"id":"2110.14336","title":"Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias","created":"2021-10-27","cited_by_count":11},{"id":"2211.00168","title":"Improving Fairness in Image Classification via Sketching","created":"2022-10-31","cited_by_count":11},{"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}],"next_cursor":null}