{"total":44,"rows":[{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280,"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":"2308.12604","title":"PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation","created":"2023-08-24","cited_by_count":95,"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":"2207.04818","title":"Cross-modal Prototype Driven Network for Radiology Report Generation","created":"2022-07-11","cited_by_count":59,"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":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2204.10688","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","created":"2022-04-22","cited_by_count":40,"area":null},{"id":"2203.15350","title":"End-to-End Transformer Based Model for Image Captioning","created":"2022-03-29","cited_by_count":38,"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":"2205.04363","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","created":"2022-05-09","cited_by_count":25,"area":null},{"id":"2211.01412","title":"CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation","created":"2022-11-02","cited_by_count":22,"area":null},{"id":"2204.07780","title":"Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks","created":"2022-04-16","cited_by_count":21,"area":null},{"id":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","cited_by_count":20,"area":null},{"id":"2208.06551","title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","created":"2022-08-13","cited_by_count":18,"area":null},{"id":"2212.01803","title":"Controllable Image Captioning via Prompting","created":"2022-12-04","cited_by_count":15,"area":null},{"id":"2305.12260","title":"Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15,"area":null},{"id":"2212.08985","title":"Efficient Image Captioning for Edge Devices","created":"2022-12-18","cited_by_count":14,"area":null},{"id":"2503.12560","title":"Multi-Granular Multimodal Clue Fusion for Meme Understanding","created":"2025-03-16","cited_by_count":14,"area":null},{"id":"2301.03160","title":"Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network","created":"2023-01-09","cited_by_count":13,"area":null},{"id":"2209.10474","title":"Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2305.16295","title":"HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning","created":"2023-05-25","cited_by_count":10,"area":null},{"id":"2201.01984","title":"Image Captioning via Compact Bidirectional Architecture","created":"2022-01-06","cited_by_count":7,"area":null},{"id":"2207.10897","title":"Efficient Modeling of Future Context for Image Captioning","created":"2022-07-22","cited_by_count":5,"area":null},{"id":"2207.05418","title":"A Baseline for Detecting Out-of-Distribution Examples in Image Captioning","created":"2022-07-12","cited_by_count":4,"area":null},{"id":"2211.09460","title":"Progressive Tree-Structured Prototype Network for End-to-End Image Captioning","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2409.11299","title":"TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation","created":"2024-09-17","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":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2305.12254","title":"A request for clarity over the End of Sequence token in the Self-Critical Sequence Training","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2308.16269","title":"Can Prompt Learning Benefit Radiology Report Generation?","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2211.10992","title":"How to Describe Images in a More Funny Way? Towards a Modular Approach to Cross-Modal Sarcasm Generation","created":"2022-11-20","cited_by_count":1,"area":null},{"id":"2212.13378","title":"Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation","created":"2022-12-27","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":"2410.15312","title":"Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2205.14458","title":"Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning","created":"2022-05-28","cited_by_count":0,"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":"2211.02321","title":"OSIC: A New One-Stage Image Captioner Coined","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2303.16293","title":"SnakeVoxFormer: Transformer-based Single Image\\\\Voxel Reconstruction with Run Length Encoding","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2504.16761","title":"Tri-FusionNet: Enhancing Image Description Generation with Transformer-based Fusion Network and Dual Attention Mechanism","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2508.01693","title":"SURE-Med: Systematic Uncertainty Reduction for Enhanced Reliability in Medical Report Generation","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2601.12926","title":"Dual-Stream Collaborative Transformer for Image Captioning","created":"2026-01-19","cited_by_count":0,"area":null}],"next_cursor":null}