{"total":47,"rows":[{"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":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91,"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":"2106.06683","title":"Assessing Multilingual Fairness in Pre-trained Multimodal Representations","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2107.13782","title":"Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions","created":"2021-07-29","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":"2201.05307","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","created":"2022-01-14","cited_by_count":30,"area":null},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"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":"2510.09653","title":"Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition","created":"2025-10-06","cited_by_count":18,"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":"2309.12482","title":"State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding","created":"2023-09-21","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":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","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":"2112.00969","title":"Object-Centric Unsupervised Image Captioning","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":"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":"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":"2306.16649","title":"ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2401.11631","title":"Text-to-Image Cross-Modal Generation: A Systematic Review","created":"2024-01-21","cited_by_count":5,"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":"2111.05890","title":"Multimodal End-to-End Group Emotion Recognition using Cross-Modal Attention","created":"2021-11-10","cited_by_count":3,"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":"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":"2507.08610","title":"Emergent Natural Language with Communication Games for Improving Image Captioning Capabilities without Additional Data","created":"2025-07-11","cited_by_count":1,"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":"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":"2509.08225","title":"Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition","created":"2025-09-10","cited_by_count":0,"area":null}],"next_cursor":null}