{"total":21,"rows":[{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339,"area":null},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91,"area":null},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35,"area":null},{"id":"2210.05060","title":"AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization","created":"2022-10-11","cited_by_count":28,"area":null},{"id":"2404.01751","title":"T-VSL: Text-Guided Visual Sound Source Localization in Mixtures","created":"2024-04-02","cited_by_count":19,"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":"2405.02179","title":"Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models","created":"2024-05-03","cited_by_count":8,"area":null},{"id":"2302.05940","title":"SemanticAC: Semantics-Assisted Framework for Audio Classification","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2305.19612","title":"Underwater-Art: Expanding Information Perspectives With Text Templates For Underwater Acoustic Target Recognition","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2306.01002","title":"Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2305.19602","title":"Learning Music Sequence Representation from Text Supervision","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2405.06128","title":"Enhanced Multimodal Content Moderation of Children's Videos using Audiovisual Fusion","created":"2024-05-09","cited_by_count":4,"area":null},{"id":"2211.02940","title":"Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block","created":"2022-11-05","cited_by_count":3,"area":null},{"id":"2204.07763","title":"UFRC: A Unified Framework for Reliable COVID-19 Detection on Crowdsourced Cough Audio","created":"2022-04-16","cited_by_count":1,"area":null},{"id":"2504.21375","title":"Synergy-CLIP: Extending CLIP with Multi-modal Integration for Robust Representation Learning","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2506.00903","title":"Leveraging CLIP Encoder for Multimodal Emotion Recognition","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2508.13387","title":"SPANER: Shared Prompt Aligner for Multimodal Semantic Representation","created":"2025-08-18","cited_by_count":1,"area":null},{"id":"2204.11479","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2502.18889","title":"Clip-TTS: Contrastive Text-content and Mel-spectrogram, A High-Quality Text-to-Speech Method based on Contextual Semantic Understanding","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2509.15570","title":"Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2607.15094","title":"AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning","created":"2026-07-16","cited_by_count":0,"area":null}],"next_cursor":null}