{"total":19,"rows":[{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"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":"2310.19168","title":"BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping","created":"2023-10-29","cited_by_count":12,"area":null},{"id":"2505.20027","title":"Multi-modal brain encoding models for multi-modal stimuli","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2310.18481","title":"MOSEL: Inference Serving Using Dynamic Modality Selection","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2402.09055","title":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2306.12559","title":"Exploring the Role of Audio in Video Captioning","created":"2023-06-21","cited_by_count":3,"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":"2310.08204","title":"STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2505.23308","title":"Spoken question answering for visual queries","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2511.07988","title":"The One Where They Brain-Tune for Social Cognition: Multi-Modal Brain-Tuning on Friends","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2308.14160","title":"A Unified Transformer-based Network for multimodal Emotion Recognition","created":"2023-08-27","cited_by_count":0,"area":null},{"id":"2412.09317","title":"Multimodal Sentiment Analysis based on Video and Audio Inputs","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2511.03423","title":"Seeing What You Say: Expressive Image Generation from Speech","created":"2025-11-05","cited_by_count":0,"area":null}],"next_cursor":null}