{"total":70,"rows":[{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473,"area":null},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2309.05569","title":"ITI-GEN: Inclusive Text-to-Image Generation","created":"2023-09-11","cited_by_count":64,"area":null},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56,"area":null},{"id":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52,"area":null},{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2304.03916","title":"Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning","created":"2023-04-08","cited_by_count":47,"area":null},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43,"area":null},{"id":"2207.00691","title":"American == White in Multimodal Language-and-Image AI","created":"2022-07-01","cited_by_count":39,"area":null},{"id":"2402.07220","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","created":"2024-02-11","cited_by_count":38,"area":null},{"id":"2205.10764","title":"Evidence for Hypodescent in Visual Semantic AI","created":"2022-05-22","cited_by_count":30,"area":null},{"id":"2205.11378","title":"Markedness in Visual Semantic AI","created":"2022-05-23","cited_by_count":29,"area":null},{"id":"2406.00783","title":"AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2302.07159","title":"A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?","created":"2023-02-14","cited_by_count":25,"area":null},{"id":"2305.14711","title":"Gender Biases in Automatic Evaluation Metrics for Image Captioning","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2306.15521","title":"What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation","created":"2023-06-27","cited_by_count":24,"area":null},{"id":"2302.03675","title":"Auditing Gender Presentation Differences in Text-to-Image Models","created":"2023-02-07","cited_by_count":22,"area":null},{"id":"2210.14562","title":"FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization","created":"2022-10-26","cited_by_count":20,"area":null},{"id":"2411.12785","title":"Joint Vision-Language Social Bias Removal for CLIP","created":"2024-11-19","cited_by_count":18,"area":null},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2112.08594","title":"Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2210.12637","title":"Neural Eigenfunctions Are Structured Representation Learners","created":"2022-10-23","cited_by_count":16,"area":null},{"id":"2401.16092","title":"Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You","created":"2024-01-29","cited_by_count":15,"area":null},{"id":"2405.08209","title":"Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp","created":"2024-05-13","cited_by_count":15,"area":null},{"id":"2410.19314","title":"Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)","created":"2024-10-25","cited_by_count":15,"area":null},{"id":"2203.07511","title":"Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations","created":"2022-03-14","cited_by_count":14,"area":null},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2210.15110","title":"Masked Vision-Language Transformer in Fashion","created":"2022-10-27","cited_by_count":14,"area":null},{"id":"2212.00784","title":"Improving Zero-Shot Models with Label Distribution Priors","created":"2022-12-01","cited_by_count":14,"area":null},{"id":"2404.02900","title":"DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","created":"2024-04-03","cited_by_count":14,"area":null},{"id":"2503.23398","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2403.02580","title":"What do we learn from inverting CLIP models?","created":"2024-03-05","cited_by_count":13,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2403.02695","title":"Controllable Prompt Tuning For Balancing Group Distributional Robustness","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2210.05248","title":"Self-supervised debiasing using low rank regularization","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2211.07275","title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2501.00962","title":"OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes","created":"2025-01-01","cited_by_count":8,"area":null},{"id":"2211.02580","title":"Evaluating and Improving Factuality in Multimodal Abstractive Summarization","created":"2022-11-04","cited_by_count":6,"area":null},{"id":"2310.17530","title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2401.02651","title":"Benchmarking PathCLIP for Pathology Image Analysis","created":"2024-01-05","cited_by_count":6,"area":null},{"id":"2302.08572","title":"Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers","created":"2023-02-16","cited_by_count":5,"area":null},{"id":"2412.10604","title":"EvalGIM: A Library for Evaluating Generative Image Models","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2503.18324","title":"Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2307.09233","title":"Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2206.08349","title":"Know your audience: specializing grounded language models with listener subtraction","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2303.02688","title":"Text2Face: A Multi-Modal 3D Face Model","created":"2023-03-05","cited_by_count":3,"area":null},{"id":"2311.06694","title":"Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2505.13429","title":"Understanding Complexity in VideoQA via Visual Program Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2406.18562","title":"Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2508.09450","title":"From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2508.17750","title":"From Global to Local: Social Bias Transfer in CLIP","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2603.11793","title":"Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2306.06077","title":"Semantically-Prompted Language Models Improve Visual Descriptions","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2404.08461","title":"OTTER: Effortless Label Distribution Adaptation of Zero-shot Models","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2405.06319","title":"Decoding Emotions in Abstract Art: Cognitive Plausibility of CLIP in Recognizing Color-Emotion Associations","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2406.01449","title":"SLANT: Spurious Logo ANalysis Toolkit","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2407.17474","title":"\"My Kind of Woman\": Analysing Gender Stereotypes in AI through The Averageness Theory and EU Law","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2502.15739","title":"Detecting Content Rating Violations in Android Applications: A Vision-Language Approach","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2503.17899","title":"What Time Tells Us? An Explorative Study of Time Awareness Learned from Static Images","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2603.22260","title":"Greater accessibility can amplify discrimination in generative AI","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2304.01204","title":"Automatic Geo-alignment of Artwork in Children's Story Books","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2504.06313","title":"Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activities","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2603.12227","title":"Interpreting Contrastive Embeddings in Specific Domains with Fuzzy Rules","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.15623","title":"Finder: A Multimodal AI-Powered Search Framework for Pharmaceutical Data Retrieval","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2606.00640","title":"An Attribute-Based Measure of Video Complexity","created":"2026-05-30","cited_by_count":0,"area":null}],"next_cursor":null}