{"total":19,"rows":[{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111,"area":null},{"id":"2401.17868","title":"Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model","created":"2024-01-31","cited_by_count":69,"area":null},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2404.17245","title":"Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2210.16829","title":"Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation","created":"2022-10-30","cited_by_count":12,"area":null},{"id":"2407.11321","title":"TCFormer: Visual Recognition via Token Clustering Transformer","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2311.01197","title":"AiluRus: A Scalable ViT Framework for Dense Prediction","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2309.13196","title":"ClusterFormer: Clustering As A Universal Visual Learner","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2406.04999","title":"ProMotion: Prototypes As Motion Learners","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2603.15603","title":"Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2308.03747","title":"Mask Frozen-DETR: High Quality Instance Segmentation with One GPU","created":"2023-08-07","cited_by_count":3,"area":null},{"id":"2311.15335","title":"TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2508.15057","title":"GasTwinFormer: A Hybrid Vision Transformer for Livestock Methane Emission Segmentation and Dietary Classification in Optical Gas Imaging","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2603.11917","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2305.14840","title":"Predicting Token Impact Towards Efficient Vision Transformer","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2508.05851","title":"Temporal Cluster Assignment for Efficient Real-Time Video Segmentation","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2510.01948","title":"ClustViT: Clustering-based Token Merging for Semantic Segmentation","created":"2025-10-02","cited_by_count":0,"area":null}],"next_cursor":null}