{"total":59,"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":"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":"2203.14291","title":"Video Polyp Segmentation: A Deep Learning Perspective","created":"2022-03-27","cited_by_count":82,"area":null},{"id":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81,"area":null},{"id":"2105.08468","title":"Progressively Normalized Self-Attention Network for Video Polyp Segmentation","created":"2021-05-18","cited_by_count":75,"area":null},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71,"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":"2103.05284","title":"Open-book Video Captioning with Retrieve-Copy-Generate Network","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2209.00852","title":"Geometry Aligned Variational Transformer for Image-conditioned Layout Generation","created":"2022-09-02","cited_by_count":33,"area":null},{"id":"2407.07844","title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","created":"2024-07-10","cited_by_count":28,"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":"2106.04053","title":"Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding","created":"2021-06-08","cited_by_count":21,"area":null},{"id":"2103.05187","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","created":"2021-03-09","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":"2308.12383","title":"With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2307.02733","title":"MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection","created":"2023-07-06","cited_by_count":15,"area":null},{"id":"2202.10492","title":"CaMEL: Mean Teacher Learning for Image Captioning","created":"2022-02-21","cited_by_count":14,"area":null},{"id":"2108.09151","title":"Group-based Distinctive Image Captioning with Memory Attention","created":"2021-08-20","cited_by_count":13,"area":null},{"id":"2311.08223","title":"Improving Image Captioning via Predicting Structured Concepts","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2101.11911","title":"The Role of Syntactic Planning in Compositional Image Captioning","created":"2021-01-28","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":"2111.15162","title":"CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter","created":"2021-11-30","cited_by_count":11,"area":null},{"id":"2104.06806","title":"Continual learning in cross-modal retrieval","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2305.11918","title":"PASTS: Progress-Aware Spatio-Temporal Transformer Speaker For Vision-and-Language Navigation","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2309.11593","title":"Sentence Attention Blocks for Answer Grounding","created":"2023-09-20","cited_by_count":8,"area":null},{"id":"2108.11912","title":"Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2108.02180","title":"Ordered Attention for Coherent Visual Storytelling","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2106.14069","title":"Saying the Unseen: Video Descriptions via Dialog Agents","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2110.00335","title":"Geometry Attention Transformer with Position-aware LSTMs for Image Captioning","created":"2021-10-01","cited_by_count":5,"area":null},{"id":"2209.12343","title":"Paraphrasing Is All You Need for Novel Object Captioning","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2307.16399","title":"Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences","created":"2023-07-31","cited_by_count":4,"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":"2208.10491","title":"Improving Speech Emotion Recognition Through Focus and Calibration Attention Mechanisms","created":"2022-08-21","cited_by_count":3,"area":null},{"id":"2105.02391","title":"Exploring Explicit and Implicit Visual Relationships for Image Captioning","created":"2021-05-06","cited_by_count":2,"area":null},{"id":"2105.08573","title":"Dependent Multi-Task Learning with Causal Intervention for Image Captioning","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2108.01056","title":"Distributed Attention for Grounded Image Captioning","created":"2021-08-02","cited_by_count":2,"area":null},{"id":"2110.08446","title":"Self-Annotated Training for Controllable Image Captioning","created":"2021-10-16","cited_by_count":2,"area":null},{"id":"2112.14088","title":"Synchronized Audio-Visual Frames with Fractional Positional Encoding for Transformers in Video-to-Text Translation","created":"2021-12-28","cited_by_count":2,"area":null},{"id":"2205.03039","title":"Dual-Level Decoupled Transformer for Video Captioning","created":"2022-05-06","cited_by_count":2,"area":null},{"id":"2206.03803","title":"Dual Windows Are Significant: Learning from Mediastinal Window and Focusing on Lung Window","created":"2022-06-08","cited_by_count":2,"area":null},{"id":"2210.01338","title":"Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning","created":"2022-10-04","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":"2501.14828","title":"An Ensemble Model with Attention Based Mechanism for Image Captioning","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2101.09698","title":"Fast Sequence Generation with Multi-Agent Reinforcement Learning","created":"2021-01-24","cited_by_count":1,"area":null},{"id":"2307.09915","title":"Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2403.12431","title":"Geometric Constraints in Deep Learning Frameworks: A Survey","created":"2024-03-19","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":"2408.15714","title":"Pixels to Prose: Understanding the art of Image Captioning","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2506.05399","title":"Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2206.14263","title":"ZoDIAC: Zoneout Dropout Injection Attention Calculation","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2208.06117","title":"Facial Expression Recognition and Image Description Generation in Vietnamese","created":"2022-08-12","cited_by_count":0,"area":null},{"id":"2301.01955","title":"Adaptively Clustering Neighbor Elements for Image-Text Generation","created":"2023-01-05","cited_by_count":0,"area":null},{"id":"2403.06520","title":"How to Understand Named Entities: Using Common Sense for News Captioning","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2504.02496","title":"Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2604.23045","title":"A Differentiable Framework for Global Circulation Model Precipitation Bias Correction","created":"2026-04-24","cited_by_count":0,"area":null}],"next_cursor":null}