{"total":52,"rows":[{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2304.06488","title":"One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era","created":"2023-04-04","cited_by_count":55,"area":null},{"id":"2404.10242","title":"Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology","created":"2024-04-16","cited_by_count":52,"area":null},{"id":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45,"area":null},{"id":"2211.09120","title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","created":"2022-11-16","cited_by_count":43,"area":null},{"id":"2307.02227","title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition","created":"2023-07-05","cited_by_count":43,"area":null},{"id":"2312.10726","title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","created":"2023-12-17","cited_by_count":42,"area":null},{"id":"2211.09807","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","created":"2022-11-17","cited_by_count":31,"area":null},{"id":"2306.07713","title":"Robustness of SAM: Segment Anything Under Corruptions and Beyond","created":"2023-06-13","cited_by_count":31,"area":null},{"id":"2402.18922","title":"A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection","created":"2024-02-29","cited_by_count":23,"area":null},{"id":"2401.05446","title":"Self-supervised Learning for Electroencephalogram: A Systematic Survey","created":"2024-01-09","cited_by_count":19,"area":null},{"id":"2401.00416","title":"SVFAP: Self-supervised Video Facial Affect Perceiver","created":"2023-12-31","cited_by_count":18,"area":null},{"id":"2309.04589","title":"Motif-aware Attribute Masking for Molecular Graph Pre-training","created":"2023-09-08","cited_by_count":16,"area":null},{"id":"2309.17281","title":"Information Flow in Self-Supervised Learning","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2405.18839","title":"MEGA: Masked Generative Autoencoder for Human Mesh Recovery","created":"2024-05-29","cited_by_count":14,"area":null},{"id":"2509.25449","title":"Joint Embeddings Go Temporal","created":"2025-09-29","cited_by_count":14,"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":"2309.02028","title":"Non-Parametric Representation Learning with Kernels","created":"2023-09-05","cited_by_count":11,"area":null},{"id":"2311.11465","title":"Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape","created":"2023-06-03","cited_by_count":10,"area":null},{"id":"2404.08330","title":"Emerging Property of Masked Token for Effective Pre-training","created":"2024-04-12","cited_by_count":10,"area":null},{"id":"2304.11117","title":"A vector quantized masked autoencoder for speech emotion recognition","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2306.02094","title":"Segment Anything Meets Semantic Communication","created":"2023-06-03","cited_by_count":8,"area":null},{"id":"2306.08249","title":"Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognition","created":"2023-06-14","cited_by_count":8,"area":null},{"id":"2210.01632","title":"Backdoor Attacks in the Supply Chain of Masked Image Modeling","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2512.15729","title":"TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge","created":"2025-12-05","cited_by_count":7,"area":null},{"id":"2305.00866","title":"Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2310.12431","title":"SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2403.09809","title":"Self-Supervised Learning for Time Series: Contrastive or Generative?","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2504.16942","title":"S2Vec: Self-Supervised Geospatial Embeddings for the Built Environment","created":"2025-04-10","cited_by_count":4,"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":"2407.19889","title":"Self-Supervised Learning for Text Recognition: A Critical Survey","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2511.05619","title":"Frequency Matters: When Time Series Foundation Models Fail Under Spectral Shift","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2404.13106","title":"Automatic Cranial Defect Reconstruction with Self-Supervised Deep Deformable Masked Autoencoders","created":"2024-04-19","cited_by_count":2,"area":null},{"id":"2409.06385","title":"AMNS: Attention-Weighted Selective Mask and Noise Label Suppression for Text-to-Image Person Retrieval","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2211.00313","title":"RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images","created":"2022-11-01","cited_by_count":1,"area":null},{"id":"2212.01046","title":"Improved Representation Learning Through Tensorized Autoencoders","created":"2022-12-02","cited_by_count":1,"area":null},{"id":"2310.04461","title":"AI-based automated active learning for discovery of hidden dynamic processes: A use case in light microscopy","created":"2023-10-05","cited_by_count":1,"area":null},{"id":"2403.15876","title":"Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content","created":"2024-03-23","cited_by_count":1,"area":null},{"id":"2412.03471","title":"Cluster Specific Representation Learning","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2505.19455","title":"MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.23532","title":"GViT: Representing Images as Gaussians for Visual Recognition","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2507.01744","title":"Calibrated Self-supervised Vision Transformers Improve Intracranial Arterial Calcification Segmentation from Clinical CT Head Scans","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2308.15327","title":"Enhancing Robot Learning through Learned Human-Attention Feature Maps","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2408.15651","title":"Online pre-training with long-form videos","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2411.03365","title":"Enhanced Real-Time Threat Detection in 5G Networks: A Self-Attention RNN Autoencoder Approach for Spectral Intrusion Analysis","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2504.02536","title":"A Sensorimotor Vision Transformer","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.20347","title":"Emergent Granger Causality in Neural Networks: Can Prediction Alone Reveal Structure?","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2508.10147","title":"rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2602.17568","title":"Be Wary of Your Time Series Preprocessing","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2608.29867","title":"Partially Linear Autoencoders for Manifold Learning and Dimensionality Reduction","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}