{"total":27,"rows":[{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2212.02031","title":"Prototypical Residual Networks for Anomaly Detection and Localization","created":"2022-12-05","cited_by_count":56,"area":null},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46,"area":null},{"id":"2403.18361","title":"ViTAR: Vision Transformer with Any Resolution","created":"2024-03-27","cited_by_count":25,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2310.00632","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","created":"2023-10-01","cited_by_count":12,"area":null},{"id":"2405.18240","title":"MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution","created":"2024-05-28","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2503.18931","title":"Enhancing Vision Foundation Models via Multimodal Continual Pre-Training","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2408.12396","title":"Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2407.18715","title":"BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2508.14187","title":"Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2603.00543","title":"Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark","created":"2026-02-28","cited_by_count":2,"area":null},{"id":"2311.17098","title":"DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2409.04082","title":"SDformerFlow: Spatiotemporal swin spikeformer for event-based optical flow estimation","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2411.17283","title":"BadScan: An Architectural Backdoor Attack on Visual State Space Models","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2512.05132","title":"Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2602.24222","title":"MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2403.13677","title":"Retina Vision Transformer (RetinaViT): Introducing Scaled Patches into Vision Transformers","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2509.17182","title":"PMRT: A Training Recipe for Fast, 3D High-Resolution Aerodynamic Prediction","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2510.09822","title":"Task-Aware Resolution Optimization for Visual Large Language Models","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.12660","title":"On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.16209","title":"StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2605.12168","title":"On What We Can Learn from Low-Resolution Data","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2609.03216","title":"ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04392","title":"FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}