{"total":158,"rows":[{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804,"area":null},{"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,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485,"area":null},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317,"area":null},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2303.07240","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","created":"2023-03-13","cited_by_count":212,"area":null},{"id":"2301.04558","title":"Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing","created":"2023-01-11","cited_by_count":211,"area":null},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187,"area":null},{"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":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2209.07098","title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training","created":"2022-09-15","cited_by_count":104,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2311.16208","title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","created":"2023-11-27","cited_by_count":86,"area":null},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"area":null},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67,"area":null},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2303.15935","title":"When Brain-inspired AI Meets AGI","created":"2023-03-28","cited_by_count":54,"area":null},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2307.12914","title":"Towards a Visual-Language Foundation Model for Computational Pathology","created":"2023-07-24","cited_by_count":52,"area":null},{"id":"2209.07118","title":"Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge","created":"2022-09-15","cited_by_count":51,"area":null},{"id":"2404.10241","title":"Vision-and-Language Navigation via Causal Learning","created":"2024-04-16","cited_by_count":51,"area":null},{"id":"2307.09484","title":"MolFM: A Multimodal Molecular Foundation Model","created":"2023-06-06","cited_by_count":50,"area":null},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49,"area":null},{"id":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45,"area":null},{"id":"2311.12751","title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","created":"2023-11-21","cited_by_count":42,"area":null},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40,"area":null},{"id":"2310.12973","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","created":"2023-10-19","cited_by_count":39,"area":null},{"id":"2412.17007","title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","created":"2024-12-22","cited_by_count":38,"area":null},{"id":"2302.08958","title":"Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts","created":"2023-02-17","cited_by_count":36,"area":null},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2207.08150","title":"FashionViL: Fashion-Focused Vision-and-Language Representation Learning","created":"2022-07-17","cited_by_count":32,"area":null},{"id":"2306.05480","title":"Artificial General Intelligence for Medical Imaging Analysis","created":"2023-06-08","cited_by_count":32,"area":null},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2305.13631","title":"EDIS: Entity-Driven Image Search over Multimodal Web Content","created":"2023-05-23","cited_by_count":27,"area":null},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"area":null},{"id":"2202.07247","title":"CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval","created":"2022-02-15","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":"2205.01818","title":"i-Code: An Integrative and Composable Multimodal Learning Framework","created":"2022-05-03","cited_by_count":24,"area":null},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2212.08653","title":"Attentive Mask CLIP","created":"2022-12-16","cited_by_count":23,"area":null},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2112.08723","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","created":"2021-12-16","cited_by_count":22,"area":null},{"id":"2211.01412","title":"CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation","created":"2022-11-02","cited_by_count":22,"area":null},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22,"area":null},{"id":"2211.09790","title":"ConStruct-VL: Data-Free Continual Structured VL Concepts Learning","created":"2022-11-17","cited_by_count":20,"area":null},{"id":"2405.05615","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","created":"2024-05-09","cited_by_count":20,"area":null},{"id":"2303.13043","title":"Top-Down Visual Attention from Analysis by Synthesis","created":"2023-03-23","cited_by_count":19,"area":null},{"id":"2403.13499","title":"Improved Baselines for Data-efficient Perceptual Augmentation of LLMs","created":"2024-03-20","cited_by_count":18,"area":null},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2308.07593","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","created":"2023-08-15","cited_by_count":16,"area":null},{"id":"2308.09311","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2212.01803","title":"Controllable Image Captioning via Prompting","created":"2022-12-04","cited_by_count":15,"area":null},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15,"area":null},{"id":"2312.06179","title":"Dynamic Weighted Combiner for Mixed-Modal Image Retrieval","created":"2023-12-11","cited_by_count":15,"area":null},{"id":"2207.01426","title":"Dynamic Contrastive Distillation for Image-Text Retrieval","created":"2022-07-04","cited_by_count":14,"area":null},{"id":"2212.08985","title":"Efficient Image Captioning for Edge Devices","created":"2022-12-18","cited_by_count":14,"area":null},{"id":"2307.09721","title":"Multi-Grained Multimodal Interaction Network for Entity Linking","created":"2023-07-19","cited_by_count":13,"area":null},{"id":"2201.12723","title":"A Frustratingly Simple Approach for End-to-End Image Captioning","created":"2022-01-30","cited_by_count":12,"area":null},{"id":"2310.04550","title":"Module-wise Adaptive Distillation for Multimodality Foundation Models","created":"2023-10-06","cited_by_count":12,"area":null},{"id":"2205.09256","title":"Training Vision-Language Transformers from Captions","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2210.04183","title":"MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning","created":"2022-10-09","cited_by_count":11,"area":null},{"id":"2304.10824","title":"Rethinking Benchmarks for Cross-modal Image-text Retrieval","created":"2023-04-21","cited_by_count":10,"area":null},{"id":"2305.16295","title":"HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning","created":"2023-05-25","cited_by_count":10,"area":null},{"id":"2310.01358","title":"NEUCORE: Neural Concept Reasoning for Composed Image Retrieval","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2301.07836","title":"Masked Autoencoding Does Not Help Natural Language Supervision at Scale","created":"2023-01-19","cited_by_count":7,"area":null},{"id":"2309.12657","title":"Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding","created":"2023-09-22","cited_by_count":7,"area":null},{"id":"2405.11685","title":"ColorFoil: Investigating Color Blindness in Large Vision and Language Models","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2503.15978","title":"A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli","created":"2025-03-20","cited_by_count":7,"area":null},{"id":"2209.13822","title":"TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2302.05016","title":"Is Multimodal Vision Supervision Beneficial to Language?","created":"2023-02-10","cited_by_count":6,"area":null},{"id":"2407.02389","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","created":"2024-07-02","cited_by_count":6,"area":null},{"id":"2211.13235","title":"Unified Multimodal Model with Unlikelihood Training for Visual Dialog","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2305.15483","title":"Weakly Supervised Vision-and-Language Pre-training with Relative Representations","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2401.17797","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2406.01934","title":"Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2410.14991","title":"ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2506.05890","title":"Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2304.07675","title":"Multimodal Representation Learning of Cardiovascular Magnetic Resonance Imaging","created":"2023-04-16","cited_by_count":4,"area":null},{"id":"2305.14268","title":"Masked Path Modeling for Vision-and-Language Navigation","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2306.14644","title":"PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas","created":"2023-06-26","cited_by_count":4,"area":null},{"id":"2307.07742","title":"SINC: Self-Supervised In-Context Learning for Vision-Language Tasks","created":"2023-07-15","cited_by_count":4,"area":null}],"next_cursor":"100"}