{"list":"other","total":54,"rows":[{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"1707.07045","title":"End-to-end Neural Coreference Resolution","created":"2017-07-21","cited_by_count":241},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"2303.11408","title":"Stable Bias: Analyzing Societal Representations in Diffusion Models","created":"2023-03-20","cited_by_count":226},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141},{"id":"1905.01989","title":"Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search","created":"2019-04-30","cited_by_count":138},{"id":"2108.02818","title":"Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications","created":"2021-08-05","cited_by_count":128},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90},{"id":"2108.04308","title":"Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development","created":"2021-08-09","cited_by_count":85},{"id":"1910.13913","title":"Toward Gender-Inclusive Coreference Resolution","created":"2019-10-30","cited_by_count":84},{"id":"1610.08559","title":"Measuring Fairness in Ranked Outputs","created":"2016-10-26","cited_by_count":81},{"id":"1609.08667","title":"Deep Reinforcement Learning for Mention-Ranking Coreference Models","created":"2016-09-27","cited_by_count":63},{"id":"2109.03858","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","created":"2021-09-08","cited_by_count":62},{"id":"1606.01323","title":"Improving Coreference Resolution by Learning Entity-Level Distributed Representations","created":"2016-06-04","cited_by_count":50},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44},{"id":"2306.03950","title":"MISGENDERED: Limits of Large Language Models in Understanding Pronouns","created":"2023-06-06","cited_by_count":43},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38},{"id":"2005.01655","title":"Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions","created":"2020-05-04","cited_by_count":33},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","cited_by_count":25},{"id":"1604.03035","title":"Learning Global Features for Coreference Resolution","created":"2016-04-11","cited_by_count":20},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20},{"id":"1704.07121","title":"Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets","created":"2017-04-24","cited_by_count":11},{"id":"2205.15237","title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models","created":"2022-05-30","cited_by_count":11},{"id":"2305.01788","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","created":"2023-05-02","cited_by_count":5},{"id":"1612.07833","title":"Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task","created":"2016-12-22","cited_by_count":2}],"next_cursor":null}