{"total":25,"rows":[{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2304.04907","title":"Improving Vision-and-Language Navigation by Generating Future-View Image Semantics","created":"2023-04-11","cited_by_count":46,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"area":null},{"id":"2305.01778","title":"SLTUNET: A Simple Unified Model for Sign Language Translation","created":"2023-05-02","cited_by_count":35,"area":null},{"id":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2402.09649","title":"ProtChatGPT: Towards Understanding Proteins with Large Language Models","created":"2024-02-15","cited_by_count":18,"area":null},{"id":"2303.12208","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2212.00986","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","created":"2022-12-02","cited_by_count":11,"area":null},{"id":"2301.05065","title":"Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks","created":"2023-01-12","cited_by_count":9,"area":null},{"id":"2305.01666","title":"BrainNPT: Pre-training of Transformer networks for brain network classification","created":"2023-05-02","cited_by_count":9,"area":null},{"id":"2301.07836","title":"Masked Autoencoding Does Not Help Natural Language Supervision at Scale","created":"2023-01-19","cited_by_count":7,"area":null},{"id":"2206.04636","title":"Spatial Entropy as an Inductive Bias for Vision Transformers","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2307.15335","title":"BARTPhoBEiT: Pre-trained Sequence-to-Sequence and Image Transformers Models for Vietnamese Visual Question Answering","created":"2023-07-28","cited_by_count":5,"area":null},{"id":"2301.12058","title":"Aerial Image Object Detection With Vision Transformer Detector (ViTDet)","created":"2023-01-28","cited_by_count":3,"area":null},{"id":"2603.29692","title":"SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2405.19226","title":"ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2407.14212","title":"Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2","created":"2024-07-19","cited_by_count":0,"area":null}],"next_cursor":null}