{"total":235,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208,"area":null},{"id":"2204.03610","title":"Unified Contrastive Learning in Image-Text-Label Space","created":"2022-04-07","cited_by_count":194,"area":null},{"id":"2208.12262","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","created":"2022-08-25","cited_by_count":187,"area":"distill"},{"id":"2301.11320","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","created":"2023-01-26","cited_by_count":187,"area":null},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2202.10261","title":"A Self-Supervised Descriptor for Image Copy Detection","created":"2022-02-21","cited_by_count":176,"area":null},{"id":"2305.13873","title":"Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models","created":"2023-05-23","cited_by_count":175,"area":"diffusion"},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151,"area":"mllm"},{"id":"2311.17179","title":"SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery","created":"2023-11-28","cited_by_count":151,"area":null},{"id":"2212.06785","title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","created":"2022-12-13","cited_by_count":144,"area":null},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141,"area":null},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123,"area":"mllm"},{"id":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115,"area":null},{"id":"2101.01710","title":"Learning Accurate Dense Correspondences and When to Trust Them","created":"2021-01-05","cited_by_count":113,"area":null},{"id":"2205.14204","title":"Multimodal Masked Autoencoders Learn Transferable Representations","created":"2022-05-27","cited_by_count":109,"area":null},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"area":null},{"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,"area":"mllm"},{"id":"2204.14095","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","created":"2022-04-29","cited_by_count":104,"area":"mllm"},{"id":"2304.00451","title":"Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild","created":"2023-04-02","cited_by_count":97,"area":null},{"id":"2311.15537","title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","created":"2023-11-27","cited_by_count":97,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2105.05837","title":"When Does Contrastive Visual Representation Learning Work?","created":"2021-05-12","cited_by_count":92,"area":null},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92,"area":null},{"id":"2105.08054","title":"Divide and Contrast: Self-supervised Learning from Uncurated Data","created":"2021-05-17","cited_by_count":85,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"area":null},{"id":"2303.16378","title":"A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion","created":"2023-03-29","cited_by_count":76,"area":"diffusion"},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2207.08455","title":"Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding","created":"2022-07-18","cited_by_count":67,"area":null},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66,"area":null},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64,"area":null},{"id":"2301.07094","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","created":"2023-01-17","cited_by_count":58,"area":"rag"},{"id":"2303.17561","title":"SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger","created":"2023-03-30","cited_by_count":56,"area":"mllm"},{"id":"2312.05208","title":"ControlRoom3D: Room Generation using Semantic Proxy Rooms","created":"2023-12-08","cited_by_count":56,"area":null},{"id":"2204.04588","title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","created":"2022-04-10","cited_by_count":55,"area":"distill"},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2303.04249","title":"Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes","created":"2023-03-07","cited_by_count":55,"area":null},{"id":"2108.04063","title":"Co-learning: Learning from Noisy Labels with Self-supervision","created":"2021-08-05","cited_by_count":51,"area":null},{"id":"2211.09454","title":"DeepPrivacy2: Towards Realistic Full-Body Anonymization","created":"2022-11-17","cited_by_count":51,"area":null},{"id":"2101.00591","title":"Progressive Correspondence Pruning by Consensus Learning","created":"2021-01-03","cited_by_count":46,"area":null},{"id":"2206.09140","title":"Certified Graph Unlearning","created":"2022-06-18","cited_by_count":46,"area":"safety"},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46,"area":null},{"id":"2305.12726","title":"Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach","created":"2023-05-22","cited_by_count":45,"area":null},{"id":"2106.09672","title":"The 2021 Image Similarity Dataset and Challenge","created":"2021-06-17","cited_by_count":44,"area":null},{"id":"2205.13616","title":"Towards A Proactive ML Approach for Detecting Backdoor Poison Samples","created":"2022-05-26","cited_by_count":40,"area":null},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2107.02170","title":"On Model Calibration for Long-Tailed Object Detection and Instance Segmentation","created":"2021-07-05","cited_by_count":39,"area":null},{"id":"2205.08148","title":"Gender and Racial Bias in Visual Question Answering Datasets","created":"2022-05-17","cited_by_count":39,"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":"2404.18873","title":"OpenStreetView-5M: The Many Roads to Global Visual Geolocation","created":"2024-04-29","cited_by_count":38,"area":null},{"id":"2210.03482","title":"CLAD: A realistic Continual Learning benchmark for Autonomous Driving","created":"2022-10-07","cited_by_count":36,"area":null},{"id":"2109.10016","title":"CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval","created":"2021-09-21","cited_by_count":33,"area":null},{"id":"2303.07700","title":"PATS: Patch Area Transportation with Subdivision for Local Feature Matching","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32,"area":null},{"id":"2203.06965","title":"UniVIP: A Unified Framework for Self-Supervised Visual Pre-training","created":"2022-03-14","cited_by_count":31,"area":null},{"id":"2211.09807","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","created":"2022-11-17","cited_by_count":31,"area":null},{"id":"2405.03690","title":"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs","created":"2024-05-06","cited_by_count":30,"area":"lr"},{"id":"2502.11748","title":"ILIAS: Instance-Level Image retrieval At Scale","created":"2025-02-17","cited_by_count":30,"area":"mllm"},{"id":"2303.17342","title":"PMatch: Paired Masked Image Modeling for Dense Geometric Matching","created":"2023-03-30","cited_by_count":29,"area":null},{"id":"2211.16175","title":"Context-Aware Robust Fine-Tuning","created":"2022-11-29","cited_by_count":28,"area":null},{"id":"2211.12109","title":"Video compression dataset and benchmark of learning-based video-quality metrics","created":"2022-11-22","cited_by_count":27,"area":null},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27,"area":null},{"id":"2401.17592","title":"Local Feature Matching Using Deep Learning: A Survey","created":"2024-01-31","cited_by_count":26,"area":null},{"id":"2409.00031","title":"Quality Assessment in the Era of Large Models: A Survey","created":"2024-08-17","cited_by_count":26,"area":null},{"id":"2210.09304","title":"Non-Contrastive Learning Meets Language-Image Pre-Training","created":"2022-10-17","cited_by_count":25,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2104.01769","title":"Procrustean Training for Imbalanced Deep Learning","created":"2021-04-05","cited_by_count":24,"area":null},{"id":"2207.10141","title":"AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2403.15604","title":"Investigating Use Cases of AI-Powered Scene Description Applications for Blind and Low Vision People","created":"2024-03-22","cited_by_count":24,"area":null},{"id":"2106.16245","title":"How to Train Your MAML to Excel in Few-Shot Classification","created":"2021-06-30","cited_by_count":22,"area":null},{"id":"2310.01755","title":"ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2310.18574","title":"Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning","created":"2023-10-28","cited_by_count":22,"area":"safety"},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21,"area":null},{"id":"2205.03860","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","created":"2022-05-08","cited_by_count":21,"area":"mllm"},{"id":"2303.06471","title":"Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review","created":"2023-03-11","cited_by_count":20,"area":null},{"id":"2304.05173","title":"Improving Image Recognition by Retrieving from Web-Scale Image-Text Data","created":"2023-04-11","cited_by_count":20,"area":"rag"},{"id":"2304.05947","title":"Visual Localization using Imperfect 3D Models from the Internet","created":"2023-04-12","cited_by_count":20,"area":null},{"id":"2105.07645","title":"Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2307.16813","title":"Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment","created":"2023-07-31","cited_by_count":18,"area":null},{"id":"2108.08669","title":"Video Relation Detection via Tracklet based Visual Transformer","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2301.04647","title":"EXIF as Language: Learning Cross-Modal Associations Between Images and Camera Metadata","created":"2023-01-11","cited_by_count":17,"area":null},{"id":"2111.15341","title":"ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds","created":"2021-11-30","cited_by_count":15,"area":null},{"id":"2203.03253","title":"Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information","created":"2022-03-07","cited_by_count":15,"area":null},{"id":"2212.07050","title":"Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders","created":"2022-12-14","cited_by_count":15,"area":null},{"id":"2304.08480","title":"DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training","created":"2023-04-17","cited_by_count":15,"area":null},{"id":"2409.07353","title":"Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks","created":"2024-09-11","cited_by_count":15,"area":"mllm"},{"id":"2111.12958","title":"Self-Distilled Self-Supervised Representation Learning","created":"2021-11-25","cited_by_count":14,"area":"distill"}],"next_cursor":"100"}