{"total":79,"rows":[{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191,"area":null},{"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":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2206.08919","title":"VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix","created":"2022-06-17","cited_by_count":45,"area":"mllm"},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2103.12989","title":"Relation-aware Instance Refinement for Weakly Supervised Visual Grounding","created":"2021-03-24","cited_by_count":35,"area":null},{"id":"2110.00428","title":"Zero-shot Natural Language Video Localization","created":"2021-08-29","cited_by_count":34,"area":null},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34,"area":null},{"id":"2203.08481","title":"Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding","created":"2022-03-16","cited_by_count":33,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2106.06509","title":"Step-Wise Hierarchical Alignment Network for Image-Text Matching","created":"2021-06-11","cited_by_count":26,"area":null},{"id":"2108.12126","title":"Automated Generation of Accurate \\& Fluent Medical X-ray Reports","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2110.11767","title":"Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioning","created":"2021-10-22","cited_by_count":23,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"area":null},{"id":"2210.12977","title":"Language-free Training for Zero-shot Video Grounding","created":"2022-10-24","cited_by_count":22,"area":null},{"id":"2305.12964","title":"Text-based Person Search without Parallel Image-Text Data","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2408.02788","title":"GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2104.13872","title":"Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning","created":"2021-04-28","cited_by_count":14,"area":null},{"id":"2211.12148","title":"Aligning Source Visual and Target Language Domains for Unpaired Video Captioning","created":"2022-11-22","cited_by_count":14,"area":null},{"id":"2312.08865","title":"Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12,"area":null},{"id":"2111.15015","title":"Neural Attention for Image Captioning: Review of Outstanding Methods","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2210.04559","title":"CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning","created":"2022-10-10","cited_by_count":11,"area":"diffusion"},{"id":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2405.00485","title":"What Makes for Good Image Captions?","created":"2024-05-01","cited_by_count":11,"area":null},{"id":"2308.04380","title":"Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination","created":"2023-08-08","cited_by_count":10,"area":null},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","cited_by_count":10,"area":null},{"id":"2107.03050","title":"Controlled Caption Generation for Images Through Adversarial Attacks","created":"2021-07-07","cited_by_count":9,"area":null},{"id":"2112.00969","title":"Object-Centric Unsupervised Image Captioning","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2112.01073","title":"Controllable Video Captioning with an Exemplar Sentence","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2407.03919","title":"MedRAT: Unpaired Medical Report Generation via Auxiliary Tasks","created":"2024-07-04","cited_by_count":9,"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":"2310.03734","title":"Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency","created":"2023-10-05","cited_by_count":8,"area":null},{"id":"2602.21655","title":"CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning","created":"2026-02-25","cited_by_count":8,"area":"alignment"},{"id":"2203.03195","title":"Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2305.18072","title":"Image Captioning with Multi-Context Synthetic Data","created":"2023-05-29","cited_by_count":7,"area":"diffusion"},{"id":"2501.00437","title":"Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning","created":"2024-12-31","cited_by_count":7,"area":"diffusion"},{"id":"2503.13385","title":"Scale Efficient Training for Large Datasets","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2106.10658","title":"Exploring Semantic Relationships for Unpaired Image Captioning","created":"2021-06-20","cited_by_count":6,"area":null},{"id":"2210.12617","title":"Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval","created":"2022-10-23","cited_by_count":6,"area":null},{"id":"2304.08178","title":"Textual Explanations for Automated Commentary Driving","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2305.01855","title":"Multimodal Data Augmentation for Image Captioning using Diffusion Models","created":"2023-05-03","cited_by_count":6,"area":"diffusion"},{"id":"2104.08384","title":"\"Wikily\" Supervised Neural Translation Tailored to Cross-Lingual Tasks","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2305.12144","title":"DiffCap: Exploring Continuous Diffusion on Image Captioning","created":"2023-05-20","cited_by_count":5,"area":null},{"id":"2509.25654","title":"DescribeEarth: Describe Anything for Remote Sensing Images","created":"2025-09-30","cited_by_count":5,"area":"mllm"},{"id":"2209.12343","title":"Paraphrasing Is All You Need for Novel Object Captioning","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2301.11174","title":"Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2303.06458","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","created":"2023-03-11","cited_by_count":4,"area":null},{"id":"2311.07414","title":"FIRST: A Million-Entry Dataset for Text-Driven Fashion Synthesis and Design","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2201.05489","title":"Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks","created":"2022-01-14","cited_by_count":3,"area":null},{"id":"2204.04977","title":"Regularization-based Pruning of Irrelevant Weights in Deep Neural Architectures","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2507.18616","title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2112.01062","title":"Syntax Customized Video Captioning by Imitating Exemplar Sentences","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2403.13444","title":"MedCycle: Unpaired Medical Report Generation via Cycle-Consistency","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2209.15000","title":"REST: REtrieve & Self-Train for generative action recognition","created":"2022-09-29","cited_by_count":1,"area":"synth"},{"id":"2310.06879","title":"The Solution for the CVPR2023 NICE Image Captioning Challenge","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2403.19193","title":"Text Data-Centric Image Captioning with Interactive Prompts","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2410.19307","title":"Semi-supervised Chinese Poem-to-Painting Generation via Cycle-consistent Adversarial Networks","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2507.03427","title":"Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2602.23088","title":"Cytoarchitecture in Words: Weakly Supervised Vision-Language Modeling for Human Brain Microscopy","created":"2026-02-26","cited_by_count":1,"area":"mllm"},{"id":"2107.13111","title":"Experimenting with Self-Supervision using Rotation Prediction for Image Captioning","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2302.03729","title":"KENGIC: KEyword-driven and N-Gram Graph based Image Captioning","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2307.14750","title":"Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation","created":"2023-07-27","cited_by_count":0,"area":"rag"},{"id":"2402.19116","title":"How to Understand \"Support\"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding","created":"2024-02-29","cited_by_count":0,"area":"mllm"},{"id":"2403.17995","title":"Semi-Supervised Image Captioning Considering Wasserstein Graph Matching","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2508.06853","title":"AGIC: Attention-Guided Image Captioning to Improve Caption Relevance","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2508.07318","title":"RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2512.23185","title":"EIR: Enhanced Image Representations for Medical Report Generation","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2603.01696","title":"Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning","created":"2026-03-02","cited_by_count":0,"area":"mllm"},{"id":"2603.18752","title":"WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.04681","title":"Batch Loss Score for Dynamic Data Pruning","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2608.21305","title":"Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2609.12965","title":"Generative Retrieval for Unsupervised Text-Based Person Search","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}