{"total":38,"rows":[{"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":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99,"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":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"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":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2112.04222","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs","created":"2021-12-08","cited_by_count":23,"area":null},{"id":"2208.01834","title":"Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation","created":"2022-08-03","cited_by_count":20,"area":null},{"id":"2203.16518","title":"Collaborative Transformers for Grounded Situation Recognition","created":"2022-03-30","cited_by_count":19,"area":null},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2406.00644","title":"Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance","created":"2024-06-02","cited_by_count":17,"area":null},{"id":"2112.05375","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","created":"2021-12-10","cited_by_count":16,"area":null},{"id":"2305.11768","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","created":"2023-05-19","cited_by_count":16,"area":null},{"id":"2206.09378","title":"A Self-Guided Framework for Radiology Report Generation","created":"2022-06-19","cited_by_count":15,"area":null},{"id":"2311.08223","title":"Improving Image Captioning via Predicting Structured Concepts","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2209.08231","title":"Learning Distinct and Representative Styles for Image Captioning","created":"2022-09-17","cited_by_count":12,"area":null},{"id":"2303.06338","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","created":"2023-03-11","cited_by_count":12,"area":null},{"id":"2207.10400","title":"Correspondence Matters for Video Referring Expression Comprehension","created":"2022-07-21","cited_by_count":10,"area":null},{"id":"2207.11118","title":"Rethinking the Reference-based Distinctive Image Captioning","created":"2022-07-22","cited_by_count":8,"area":null},{"id":"2207.09625","title":"Explicit Image Caption Editing","created":"2022-07-20","cited_by_count":7,"area":null},{"id":"2210.11109","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2106.03831","title":"Counterfactual Maximum Likelihood Estimation for Training Deep Networks","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2210.14862","title":"Visual Semantic Parsing: From Images to Abstract Meaning Representation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2211.14835","title":"CLID: Controlled-Length Image Descriptions with Limited Data","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2306.14259","title":"Improving Reference-based Distinctive Image Captioning with Contrastive Rewards","created":"2023-06-25","cited_by_count":4,"area":null},{"id":"2202.13623","title":"Interactive Machine Learning for Image Captioning","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2411.19106","title":"Detailed Object Description with Controllable Dimensions","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2110.08446","title":"Self-Annotated Training for Controllable Image Captioning","created":"2021-10-16","cited_by_count":2,"area":null},{"id":"2401.15646","title":"Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning","created":"2024-01-28","cited_by_count":2,"area":null},{"id":"2407.11393","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2304.06602","title":"A-CAP: Anticipation Captioning with Commonsense Knowledge","created":"2023-04-13","cited_by_count":1,"area":null},{"id":"2305.18026","title":"Semantic Role Labeling Guided Out-of-distribution Detection","created":"2023-05-29","cited_by_count":1,"area":null},{"id":"2311.14920","title":"DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism","created":"2023-11-25","cited_by_count":1,"area":null},{"id":"2312.13330","title":"Towards Subject-Oriented Video Captioning via User-Specified Targets","created":"2023-12-20","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":"2206.03196","title":"Improving Image Captioning with Control Signal of Sentence Quality","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2506.03178","title":"LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning","created":"2025-05-29","cited_by_count":0,"area":null}],"next_cursor":null}