{"total":113,"rows":[{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191,"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":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"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":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25,"area":null},{"id":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25,"area":"diffusion"},{"id":"2108.05067","title":"Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning","created":"2021-08-11","cited_by_count":24,"area":null},{"id":"2305.12018","title":"BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases","created":"2023-05-19","cited_by_count":24,"area":null},{"id":"2104.11984","title":"MusCaps: Generating Captions for Music Audio","created":"2021-04-24","cited_by_count":23,"area":null},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2109.13701","title":"CIDEr-R: Robust Consensus-based Image Description Evaluation","created":"2021-09-28","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"1708.02300","title":"Reinforced Video Captioning with Entailment Rewards","created":"2017-08-07","cited_by_count":21,"area":"alignment"},{"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":"2310.05863","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","created":"2023-10-09","cited_by_count":21,"area":"mllm"},{"id":"2106.01444","title":"SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis","created":"2021-06-02","cited_by_count":18,"area":null},{"id":"2203.02838","title":"Leveraging Pre-trained BERT for Audio Captioning","created":"2022-03-06","cited_by_count":18,"area":null},{"id":"2403.13499","title":"Improved Baselines for Data-efficient Perceptual Augmentation of LLMs","created":"2024-03-20","cited_by_count":18,"area":null},{"id":"2106.15078","title":"Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation","created":"2021-06-29","cited_by_count":17,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2104.12471","title":"Contextualized Keyword Representations for Multi-modal Retinal Image Captioning","created":"2021-04-26","cited_by_count":16,"area":null},{"id":"2105.14538","title":"Longer Version for \"Deep Context-Encoding Network for Retinal Image Captioning\"","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2107.09990","title":"CL4AC: A Contrastive Loss for Audio Captioning","created":"2021-07-21","cited_by_count":16,"area":null},{"id":"2508.06125","title":"SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning","created":"2025-08-08","cited_by_count":16,"area":null},{"id":"2108.12121","title":"Reinforcement Learning-powered Semantic Communication via Semantic Similarity","created":"2021-08-27","cited_by_count":15,"area":null},{"id":"2203.15526","title":"Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning","created":"2022-03-29","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":"2406.13275","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","created":"2024-06-19","cited_by_count":14,"area":null},{"id":"2112.11739","title":"A Survey of Natural Language Generation","created":"2021-12-22","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":"2108.04692","title":"Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2210.17143","title":"Exploring Train and Test-Time Augmentations for Audio-Language Learning","created":"2022-10-31","cited_by_count":11,"area":null},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2410.09472","title":"DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning","created":"2024-10-12","cited_by_count":11,"area":"rag"},{"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":"2307.16246","title":"DRL4Route: A Deep Reinforcement Learning Framework for Pick-up and Delivery Route Prediction","created":"2023-07-30","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":"2212.08487","title":"Semantics-Empowered Communication: A Tutorial-cum-Survey","created":"2022-12-16","cited_by_count":8,"area":null},{"id":"2311.17951","title":"C3Net: Compound Conditioned ControlNet for Multimodal Content Generation","created":"2023-11-29","cited_by_count":8,"area":null},{"id":"2404.12782","title":"Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting","created":"2024-04-19","cited_by_count":8,"area":null},{"id":"2601.09385","title":"SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing","created":"2026-01-14","cited_by_count":8,"area":"mllm"},{"id":"2304.10951","title":"A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2311.16764","title":"Radiology-Aware Model-Based Evaluation Metric for Report Generation","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2501.09291","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2512.10403","title":"BRACE: A Benchmark for Robust Audio Caption Quality Evaluation","created":"2025-12-11","cited_by_count":7,"area":null},{"id":"2207.12101","title":"Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?","created":"2022-07-25","cited_by_count":6,"area":null},{"id":"2110.07410","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2201.03217","title":"Local Information Assisted Attention-free Decoder for Audio Captioning","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2202.01405","title":"Joint Speech Recognition and Audio Captioning","created":"2022-02-03","cited_by_count":5,"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":"2305.12144","title":"DiffCap: Exploring Continuous Diffusion on Image Captioning","created":"2023-05-20","cited_by_count":5,"area":null},{"id":"2408.14547","title":"Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization","created":"2024-08-26","cited_by_count":5,"area":null},{"id":"2409.12962","title":"CLAIR-A: Leveraging Large Language Models to Judge Audio Captions","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","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":"2306.14259","title":"Improving Reference-based Distinctive Image Captioning with Contrastive Rewards","created":"2023-06-25","cited_by_count":4,"area":null},{"id":"2508.03127","title":"Landsat30-AU: A Vision-Language Dataset for Australian Landsat Imagery","created":"2025-08-05","cited_by_count":4,"area":"mllm"},{"id":"2512.16145","title":"MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2001.06944","title":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","created":"2020-01-20","cited_by_count":3,"area":"offlinerl"},{"id":"2107.08028","title":"Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2210.05037","title":"Automated Audio Captioning via Fusion of Low- and High- Dimensional Features","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2210.13729","title":"Hybrid Reinforced Medical Report Generation with M-Linear Attention and Repetition Penalty","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2308.15090","title":"Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2309.11710","title":"ContextRef: Evaluating Referenceless Metrics For Image Description Generation","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2410.10913","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","created":"2024-10-14","cited_by_count":3,"area":"rag"},{"id":"2505.22045","title":"Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2506.00800","title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2510.11330","title":"Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap","created":"2025-10-13","cited_by_count":3,"area":"diffusion"},{"id":"2103.05103","title":"Image Captioning using Multiple Transformers for Self-Attention Mechanism","created":"2021-02-14","cited_by_count":2,"area":null},{"id":"2204.08409","title":"Caption Feature Space Regularization for Audio Captioning","created":"2022-04-18","cited_by_count":2,"area":null},{"id":"2207.04156","title":"Automated Audio Captioning and Language-Based Audio Retrieval","created":"2022-07-08","cited_by_count":2,"area":null},{"id":"2304.13191","title":"Towards Explainable and Safe Conversational Agents for Mental Health: A Survey","created":"2023-04-25","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":"2308.11923","title":"Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2409.09401","title":"Towards Diverse and Efficient Audio Captioning via Diffusion Models","created":"2024-09-14","cited_by_count":2,"area":"diffusion"},{"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":"2602.23649","title":"AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech","created":"2026-02-27","cited_by_count":2,"area":"mllm"},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2211.08983","title":"Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates","created":"2022-11-14","cited_by_count":1,"area":null},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"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":"2410.12028","title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2502.05435","title":"Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2601.04658","title":"LAMB: LLM-based Audio Captioning with Modality Gap Bridging via Cauchy-Schwarz Divergence","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2606.04939","title":"UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning","created":"2026-06-03","cited_by_count":1,"area":"diffusion"},{"id":"2102.11526","title":"Enhanced Modality Transition for Image Captioning","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2208.06127","title":"An investigation on selecting audio pre-trained models for audio captioning","created":"2022-08-12","cited_by_count":0,"area":null},{"id":"2402.03754","title":"Intensive Vision-guided Network for Radiology Report Generation","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2408.16827","title":"Fluent and Accurate Image Captioning with a Self-Trained Reward Model","created":"2024-08-29","cited_by_count":0,"area":"alignment"},{"id":"2409.09866","title":"S2Cap: A Benchmark and a Baseline for Singing Style Captioning","created":"2024-09-15","cited_by_count":0,"area":null}],"next_cursor":"100"}