{"total":17,"rows":[{"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":"2505.11217","title":"Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization","created":"2025-05-16","cited_by_count":18,"area":null},{"id":"2403.19638","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","created":"2024-03-28","cited_by_count":14,"area":null},{"id":"2403.09502","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","created":"2024-03-14","cited_by_count":12,"area":null},{"id":"2312.13008","title":"No More Shortcuts: Realizing the Potential of Temporal Self-Supervision","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2409.07967","title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","created":"2024-09-12","cited_by_count":11,"area":null},{"id":"2407.03563","title":"Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2303.13193","title":"VADER: Video Alignment Differencing and Retrieval","created":"2023-03-23","cited_by_count":6,"area":null},{"id":"2412.15023","title":"FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2503.14998","title":"Tables Guide Vision: Learning to See the Heart through Tabular Data","created":"2025-03-19","cited_by_count":4,"area":null},{"id":"2407.05782","title":"Sequential Contrastive Audio-Visual Learning","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2409.01445","title":"Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2412.09126","title":"Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2508.01644","title":"DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognition","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2509.06826","title":"Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2605.12145","title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","created":"2026-05-12","cited_by_count":0,"area":null}],"next_cursor":null}