{"total":19,"rows":[{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2210.11006","title":"SimpleClick: Interactive Image Segmentation with Simple Vision Transformers","created":"2022-10-20","cited_by_count":111,"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":"2210.10615","title":"A Unified View of Masked Image Modeling","created":"2022-10-19","cited_by_count":36,"area":null},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36,"area":null},{"id":"2308.09294","title":"Self-Calibrated Cross Attention Network for Few-Shot Segmentation","created":"2023-08-18","cited_by_count":32,"area":null},{"id":"2211.09799","title":"CAE v2: Context Autoencoder with CLIP Target","created":"2022-11-17","cited_by_count":25,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2308.10561","title":"Spatial Transform Decoupling for Oriented Object Detection","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2507.07483","title":"Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking","created":"2025-07-10","cited_by_count":9,"area":null},{"id":"2310.05393","title":"Hierarchical Side-Tuning for Vision Transformers","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2512.16635","title":"SARMAE: Masked Autoencoder for SAR Representation Learning","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2412.12423","title":"GG-SSMs: Graph-Generating State Space Models","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2211.01785","title":"Rethinking Hierarchies in Pre-trained Plain Vision Transformer","created":"2022-11-03","cited_by_count":1,"area":null},{"id":"2503.16311","title":"Structured-Noise Masked Modeling for Video, Audio and Beyond","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2506.19474","title":"HMSViT: A Hierarchical Masked Self-Supervised Vision Transformer for Corneal Nerve Segmentation and Diabetic Neuropathy Diagnosis","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2609.09801","title":"Morphological Decoupling-Based Skeletal Classification for Clinical Assessment of Malocclusion","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}