{"total":52,"rows":[{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251,"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":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2401.01578","title":"Context-Guided Spatio-Temporal Video Grounding","created":"2024-01-03","cited_by_count":46,"area":null},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43,"area":null},{"id":"2207.13162","title":"Retrieval-Augmented Transformer for Image Captioning","created":"2022-07-26","cited_by_count":38,"area":"rag"},{"id":"2206.07173","title":"Measuring Representational Harms in Image Captioning","created":"2022-06-14","cited_by_count":36,"area":null},{"id":"2209.06997","title":"M^4I: Multi-modal Models Membership Inference","created":"2022-09-15","cited_by_count":34,"area":"safety"},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23,"area":null},{"id":"2103.16086","title":"Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking","created":"2021-03-30","cited_by_count":17,"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":"2109.02865","title":"Journalistic Guidelines Aware News Image Captioning","created":"2021-09-07","cited_by_count":14,"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":"2111.15015","title":"Neural Attention for Image Captioning: Review of Outstanding Methods","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2108.08217","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","created":"2021-08-18","cited_by_count":10,"area":null},{"id":"2104.10406","title":"Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching","created":"2021-04-21","cited_by_count":8,"area":null},{"id":"2105.08106","title":"Multi-Modal Image Captioning for the Visually Impaired","created":"2021-05-17","cited_by_count":8,"area":null},{"id":"2104.03337","title":"Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning","created":"2021-04-07","cited_by_count":7,"area":null},{"id":"2204.03938","title":"On Distinctive Image Captioning via Comparing and Reweighting","created":"2022-04-08","cited_by_count":7,"area":null},{"id":"2205.09676","title":"Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2102.11237","title":"Image Captioning using Deep Stacked LSTMs, Contextual Word Embeddings and Data Augmentation","created":"2021-02-22","cited_by_count":5,"area":null},{"id":"2109.05218","title":"Bornon: Bengali Image Captioning with Transformer-based Deep learning approach","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2210.08303","title":"Improving Radiology Summarization with Radiograph and Anatomy Prompts","created":"2022-10-15","cited_by_count":4,"area":null},{"id":"2410.18725","title":"AI Readiness in Healthcare through Storytelling XAI","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2102.11506","title":"Comparative evaluation of CNN architectures for Image Caption Generation","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2205.01813","title":"Diverse Image Captioning with Grounded Style","created":"2022-05-03","cited_by_count":3,"area":null},{"id":"2207.01733","title":"Are metrics measuring what they should? An evaluation of image captioning task metrics","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","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":"2109.08411","title":"Cross Modification Attention Based Deliberation Model for Image Captioning","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2201.09933","title":"Do Smart Glasses Dream of Sentimental Visions? Deep Emotionship Analysis for Eyewear Devices","created":"2022-01-24","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":"2512.08873","title":"Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2103.04914","title":"Analysis of Convolutional Decoder for Image Caption Generation","created":"2021-03-08","cited_by_count":0,"area":null},{"id":"2201.00969","title":"Interactive Attention AI to translate low light photos to captions for night scene understanding in women safety","created":"2022-01-04","cited_by_count":0,"area":null},{"id":"2201.09153","title":"An Integrated Approach for Video Captioning and Applications","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2204.13324","title":"Controllable Image Captioning","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2208.04522","title":"Aesthetic Attributes Assessment of Images with AMANv2 and DPC-CaptionsV2","created":"2022-08-09","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":"2211.14177","title":"Overcoming Catastrophic Forgetting by XAI","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2305.12940","title":"GEST: the Graph of Events in Space and Time as a Common Representation between Vision and Language","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2404.18062","title":"Compressed Image Captioning using CNN-based Encoder-Decoder Framework","created":"2024-04-28","cited_by_count":0,"area":null},{"id":"2411.10334","title":"Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images","created":"2024-11-15","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":"2509.01259","title":"ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization","created":"2025-09-01","cited_by_count":0,"area":null}],"next_cursor":null}