{"total":30,"rows":[{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75,"area":null},{"id":"2505.05741","title":"Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection","created":"2025-05-09","cited_by_count":6,"area":null},{"id":"2512.09792","title":"FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2407.10655","title":"OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2603.18739","title":"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2507.04323","title":"DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2410.21822","title":"PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2506.13027","title":"DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2507.19780","title":"JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2510.24885","title":"FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2512.05663","title":"LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2603.09411","title":"RiO-DETR: DETR for Real-time Oriented Object Detection","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.07759","title":"WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2606.09367","title":"RT-SDGOD: Real-Time Single-Domain Generalized Object Detection","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2609.23431","title":"HOIBlender: Blending Lightweight Detection with Vision-Language Priors for Efficient Human-Object Interaction Detection","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2512.09309","title":"A Distributed Framework for Privacy-Enhanced Vision Transformers on the Edge","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.22454","title":"Comparing Object Detection Models for Electrical Substation Component Mapping","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.05747","title":"FlyPose: Towards Robust Human Pose Estimation From Aerial Views","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2604.03505","title":"Multimodal Urban Tree Detection from Satellite and Street-Level Imagery via Annotation-Efficient Deep Learning Strategies","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.26633","title":"SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.31834","title":"Real-Time Source-Free Object Detection","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.24981","title":"Enabling Fully Integer-Only Inference for Lightweight Detection Transformers","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.27065","title":"ScratchSim: A Procedural Synthetic Data Pipeline for Surface Scratch Detection","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.01495","title":"Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.03322","title":"LocAnyMed: Vision-Language Grounding for Multimodal Medical Images","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.15297","title":"TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformers","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.16632","title":"DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.26590","title":"GTR: Gated Token Recurrence for Efficient Dense Prediction","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.38476","title":"Curating Synthetic Data for Task-Specific Visual Perception","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}