{"total":110,"rows":[{"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,"area":"synth"},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322,"area":"mllm"},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619,"area":null},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"area":null},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668,"area":"lr"},{"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":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455,"area":"mllm"},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412,"area":null},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279,"area":"lr"},{"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":"2203.06486","title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","created":"2022-03-12","cited_by_count":169,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2109.04290","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","created":"2021-09-09","cited_by_count":116,"area":"moe"},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96,"area":null},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92,"area":"lr"},{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2106.01804","title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","created":"2021-06-03","cited_by_count":85,"area":"mllm"},{"id":"2203.04287","title":"A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation","created":"2022-03-08","cited_by_count":80,"area":null},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2111.10023","title":"UFO: A UniFied TransfOrmer for Vision-Language Representation Learning","created":"2021-11-19","cited_by_count":46,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2202.02317","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","created":"2022-02-04","cited_by_count":45,"area":null},{"id":"2107.12514","title":"Language Grounding with 3D Objects","created":"2021-07-26","cited_by_count":43,"area":null},{"id":"2111.08940","title":"Transparent Human Evaluation for Image Captioning","created":"2021-11-17","cited_by_count":40,"area":null},{"id":"2305.18171","title":"Improved Probabilistic Image-Text Representations","created":"2023-05-29","cited_by_count":40,"area":null},{"id":"2205.01850","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","created":"2022-05-04","cited_by_count":39,"area":null},{"id":"2509.09680","title":"FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark","created":"2025-09-11","cited_by_count":38,"area":"lr"},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37,"area":null},{"id":"2111.13333","title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","created":"2021-11-26","cited_by_count":34,"area":"mllm"},{"id":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32,"area":null},{"id":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32,"area":null},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30,"area":null},{"id":"2302.08268","title":"Retrieval-augmented Image Captioning","created":"2023-02-16","cited_by_count":29,"area":"rag"},{"id":"2506.01949","title":"IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layout","created":"2025-06-02","cited_by_count":28,"area":"diffusion"},{"id":"2212.09737","title":"Position-guided Text Prompt for Vision-Language Pre-training","created":"2022-12-19","cited_by_count":27,"area":"mllm"},{"id":"2303.06285","title":"DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation","created":"2023-03-11","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":"2204.13653","title":"GRIT: General Robust Image Task Benchmark","created":"2022-04-28","cited_by_count":26,"area":null},{"id":"2305.20087","title":"Too Large; Data Reduction for Vision-Language Pre-Training","created":"2023-05-31","cited_by_count":26,"area":"mllm"},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2312.14209","title":"TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusion","created":"2023-12-21","cited_by_count":26,"area":null},{"id":"2109.08029","title":"Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering","created":"2021-09-15","cited_by_count":25,"area":null},{"id":"2112.04873","title":"Nice perfume. How long did you marinate in it? Multimodal Sarcasm Explanation","created":"2021-12-09","cited_by_count":25,"area":null},{"id":"2105.15082","title":"M6-T: Exploring Sparse Expert Models and Beyond","created":"2021-05-31","cited_by_count":22,"area":"moe"},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22,"area":null},{"id":"2212.13563","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","created":"2022-12-27","cited_by_count":22,"area":null},{"id":"2302.00268","title":"Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection","created":"2023-02-01","cited_by_count":22,"area":"mllm"},{"id":"2109.02040","title":"Data Efficient Masked Language Modeling for Vision and Language","created":"2021-09-05","cited_by_count":19,"area":"mllm"},{"id":"2106.04630","title":"PAM: Understanding Product Images in Cross Product Category Attribute Extraction","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2305.04474","title":"TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection","created":"2023-05-08","cited_by_count":18,"area":null},{"id":"2301.07464","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","created":"2023-01-18","cited_by_count":16,"area":"mllm"},{"id":"2305.18842","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2107.12604","title":"Image Scene Graph Generation (SGG) Benchmark","created":"2021-07-27","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":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2403.03346","title":"Enhancing Vision-Language Pre-training with Rich Supervisions","created":"2024-03-05","cited_by_count":13,"area":"mllm"},{"id":"2409.04732","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery","created":"2024-09-07","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":"2203.14499","title":"NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge","created":"2022-03-28","cited_by_count":10,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2407.20228","title":"FlexAttention for Efficient High-Resolution Vision-Language Models","created":"2024-07-29","cited_by_count":9,"area":"mllm"},{"id":"2112.06888","title":"Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2106.05597","title":"Supervising the Transfer of Reasoning Patterns in VQA","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2108.11912","title":"Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2306.06306","title":"DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents","created":"2023-06-09","cited_by_count":7,"area":"mllm"},{"id":"2108.09479","title":"Grid-VLP: Revisiting Grid Features for Vision-Language Pre-training","created":"2021-08-21","cited_by_count":6,"area":"mllm"},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2210.05039","title":"Contrastive Video-Language Learning with Fine-grained Frame Sampling","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2310.00887","title":"GRID: A Platform for General Robot Intelligence Development","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2204.11004","title":"Training and challenging models for text-guided fashion image retrieval","created":"2022-04-23","cited_by_count":5,"area":null},{"id":"2303.05342","title":"Knowledge-augmented Few-shot Visual Relation Detection","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2307.08504","title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization","created":"2023-07-17","cited_by_count":5,"area":"mllm"},{"id":"2308.03475","title":"COPA: Efficient Vision-Language Pre-training Through Collaborative Object- and Patch-Text Alignment","created":"2023-08-07","cited_by_count":5,"area":"mllm"},{"id":"2309.16921","title":"YOLOR-Based Multi-Task Learning","created":"2023-09-29","cited_by_count":5,"area":null},{"id":"2210.08554","title":"COFAR: Commonsense and Factual Reasoning in Image Search","created":"2022-10-16","cited_by_count":4,"area":null},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4,"area":null},{"id":"2303.05068","title":"Toward Unsupervised Realistic Visual Question Answering","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2305.02265","title":"A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text","created":"2023-05-03","cited_by_count":4,"area":"lr"},{"id":"2305.10046","title":"Probing the Role of Positional Information in Vision-Language Models","created":"2023-05-17","cited_by_count":4,"area":"mllm"},{"id":"2309.03726","title":"Interpretable Visual Question Answering via Reasoning Supervision","created":"2023-09-07","cited_by_count":4,"area":null},{"id":"2312.07532","title":"Interfacing Foundation Models' Embeddings","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2510.11204","title":"Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2310.09755","title":"Beyond Segmentation: Road Network Generation with Multi-Modal LLMs","created":"2023-10-15","cited_by_count":3,"area":"mllm"},{"id":"2410.14154","title":"RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training","created":"2024-10-18","cited_by_count":3,"area":"mllm"},{"id":"2206.05912","title":"INDIGO: Intrinsic Multimodality for Domain Generalization","created":"2022-06-13","cited_by_count":2,"area":null},{"id":"2207.01733","title":"Are metrics measuring what they should? An evaluation of image captioning task metrics","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2404.00909","title":"Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning","created":"2024-04-01","cited_by_count":2,"area":"lr"},{"id":"2412.18917","title":"Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model","created":"2024-12-25","cited_by_count":2,"area":"mllm"},{"id":"2106.13033","title":"A Transformer-based Cross-modal Fusion Model with Adversarial Training for VQA Challenge 2021","created":"2021-06-24","cited_by_count":1,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null}],"next_cursor":"100"}