{"total":879,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433,"area":"mllm"},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717,"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":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405,"area":null},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359,"area":null},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305,"area":"offlinerl"},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290,"area":"mllm"},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287,"area":null},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2410.23262","title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","created":"2024-10-30","cited_by_count":231,"area":"driving"},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2402.11411","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","created":"2024-02-18","cited_by_count":198,"area":"alignment"},{"id":"2204.13258","title":"Cross-modal Memory Networks for Radiology Report Generation","created":"2022-04-28","cited_by_count":185,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177,"area":null},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168,"area":null},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162,"area":null},{"id":"2305.14761","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","created":"2023-05-24","cited_by_count":160,"area":"mllm"},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159,"area":"mllm"},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122,"area":"lr"},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120,"area":null},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120,"area":"lr"},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"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":"2309.09812","title":"R2GenGPT: Radiology Report Generation with Frozen LLMs","created":"2023-09-18","cited_by_count":114,"area":null},{"id":"2307.05356","title":"VisText: A Benchmark for Semantically Rich Chart Captioning","created":"2023-06-28","cited_by_count":112,"area":null},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111,"area":"mllm"},{"id":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109,"area":null},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108,"area":null},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105,"area":null},{"id":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2304.02211","title":"METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens","created":"2023-04-05","cited_by_count":101,"area":null},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99,"area":null},{"id":"2203.01017","title":"TableFormer: Table Structure Understanding with Transformers","created":"2022-03-02","cited_by_count":94,"area":null},{"id":"2403.13600","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","created":"2024-03-20","cited_by_count":93,"area":"mllm"},{"id":"2108.00316","title":"Chest ImaGenome Dataset for Clinical Reasoning","created":"2021-07-31","cited_by_count":90,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2302.08888","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","created":"2023-02-17","cited_by_count":86,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2112.02889","title":"Joint Learning of Localized Representations from Medical Images and Reports","created":"2021-12-06","cited_by_count":81,"area":null},{"id":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79,"area":"mllm"},{"id":"2401.02384","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","created":"2024-01-04","cited_by_count":79,"area":"mllm"},{"id":"2303.12112","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","created":"2023-03-21","cited_by_count":78,"area":null},{"id":"2110.01705","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","created":"2021-10-04","cited_by_count":76,"area":null},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76,"area":null},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75,"area":"safety"},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2112.15011","title":"Radiology Report Generation with a Learned Knowledge Base and Multi-modal Alignment","created":"2021-12-30","cited_by_count":73,"area":null},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71,"area":null},{"id":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71,"area":null},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70,"area":"distill"},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69,"area":null},{"id":"2112.15009","title":"Knowledge Matters: Radiology Report Generation with General and Specific Knowledge","created":"2021-12-30","cited_by_count":68,"area":null},{"id":"2203.10095","title":"AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation","created":"2022-03-18","cited_by_count":65,"area":null},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2309.06597","title":"Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning","created":"2023-09-12","cited_by_count":63,"area":null},{"id":"2306.11345","title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","created":"2023-06-20","cited_by_count":62,"area":null},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2207.09666","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","created":"2022-07-20","cited_by_count":56,"area":null},{"id":"2101.10804","title":"CPTR: Full Transformer Network for Image Captioning","created":"2021-01-26","cited_by_count":55,"area":null},{"id":"2301.13741","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","created":"2023-01-31","cited_by_count":54,"area":null},{"id":"2405.10004","title":"ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset","created":"2024-05-16","cited_by_count":54,"area":null},{"id":"2207.14381","title":"Pro-tuning: Unified Prompt Tuning for Vision Tasks","created":"2022-07-28","cited_by_count":53,"area":null},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2112.01551","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","created":"2021-12-02","cited_by_count":52,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2304.02828","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","created":"2023-04-06","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2203.15859","title":"NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models","created":"2022-03-29","cited_by_count":50,"area":null},{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49,"area":null},{"id":"2307.15042","title":"TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis","created":"2023-07-27","cited_by_count":49,"area":"diffusion"},{"id":"2406.18844","title":"Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift","created":"2024-06-27","cited_by_count":49,"area":"mllm"},{"id":"2108.11945","title":"SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments","created":"2021-08-26","cited_by_count":48,"area":null},{"id":"2103.14146","title":"Describing and Localizing Multiple Changes with Transformers","created":"2021-03-25","cited_by_count":47,"area":null},{"id":"2104.08211","title":"Robust Open-Vocabulary Translation from Visual Text Representations","created":"2021-04-16","cited_by_count":47,"area":null},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47,"area":null},{"id":"2401.13649","title":"VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks","created":"2024-01-24","cited_by_count":47,"area":"agents"},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null}],"next_cursor":"100"}