{"total":50,"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":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2306.07257","title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","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":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"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":"2401.13478","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","created":"2024-01-24","cited_by_count":23,"area":null},{"id":"2204.08058","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","created":"2022-04-17","cited_by_count":20,"area":null},{"id":"2310.11612","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","created":"2023-10-17","cited_by_count":20,"area":null},{"id":"2408.13608","title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description","created":"2024-08-24","cited_by_count":20,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"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":"2312.10144","title":"Data-Efficient Multimodal Fusion on a Single GPU","created":"2023-12-15","cited_by_count":11,"area":null},{"id":"2505.03054","title":"BLAB: Brutally Long Audio Bench","created":"2025-05-05","cited_by_count":11,"area":null},{"id":"2405.10084","title":"Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2508.12149","title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","created":"2025-08-16","cited_by_count":6,"area":null},{"id":"2311.01615","title":"FLAP: Fast Language-Audio Pre-training","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2307.16371","title":"MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2310.13276","title":"InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2410.16505","title":"Do Audio-Language Models Understand Linguistic Variations?","created":"2024-10-21","cited_by_count":4,"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":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2410.08324","title":"The language of sound search: Examining User Queries in Audio Search Engines","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2411.10513","title":"Any2Any: Incomplete Multimodal Retrieval with Conformal Prediction","created":"2024-11-15","cited_by_count":3,"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":"2405.07202","title":"Unified Video-Language Pre-training with Synchronized Audio","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2406.15897","title":"Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval","created":"2024-06-22","cited_by_count":2,"area":null},{"id":"2408.11641","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2207.09732","title":"Introducing Auxiliary Text Query-modifier to Content-based Audio Retrieval","created":"2022-07-20","cited_by_count":1,"area":null},{"id":"2302.12258","title":"Data leakage in cross-modal retrieval training: A case study","created":"2023-02-23","cited_by_count":1,"area":null},{"id":"2408.09269","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2509.04086","title":"TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2509.16649","title":"AISTAT lab system for DCASE2025 Task6: Language-based audio retrieval","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2605.26641","title":"OmniRetriever: Any-to-Any Audio-Video-Text Retrieval via Fusion-as-Teacher Distillation","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2310.13267","title":"On the Language Encoder of Contrastive Cross-modal Models","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2405.00367","title":"Distance Sampling-based Paraphraser Leveraging ChatGPT for Text Data Manipulation","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2405.11093","title":"AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2604.20267","title":"ATIR: Towards Audio-Text Interleaved Contextual Retrieval","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.19101","title":"Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2609.16875","title":"Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}