{"total":34,"rows":[{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2403.13042","title":"TAPTR: Tracking Any Point with Transformers as Detection","created":"2024-03-19","cited_by_count":45,"area":null},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"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":"2403.16131","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","created":"2024-03-24","cited_by_count":31,"area":null},{"id":"2312.00083","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","created":"2023-11-30","cited_by_count":29,"area":null},{"id":"2407.16291","title":"TAPTRv2: Attention-based Position Update Improves Tracking Any Point","created":"2024-07-23","cited_by_count":18,"area":null},{"id":"2305.07598","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2411.18671","title":"TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video","created":"2024-11-27","cited_by_count":8,"area":null},{"id":"2304.07527","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2404.16323","title":"LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians","created":"2024-04-25","cited_by_count":3,"area":null},{"id":"2409.17790","title":"CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2511.12410","title":"Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection","created":"2025-11-16","cited_by_count":3,"area":null},{"id":"2307.08353","title":"Box-DETR: Understanding and Boxing Conditional Spatial Queries","created":"2023-07-17","cited_by_count":2,"area":null},{"id":"2312.13735","title":"DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2410.16707","title":"DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2412.19155","title":"Referencing Where to Focus: Improving VisualGrounding with Referential Query","created":"2024-12-26","cited_by_count":2,"area":null},{"id":"2602.22595","title":"Don't let the information slip away","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2404.14657","title":"Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2405.06821","title":"Synchronized Object Detection for Autonomous Sorting, Mapping, and Quantification of Materials in Circular Healthcare","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2406.03229","title":"Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2510.15026","title":"MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2607.05177","title":"CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2311.15964","title":"Efficient Pre-training for Localized Instruction Generation of Videos","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2404.15244","title":"Image-Specific Adaptation of Transformer Encoders for Compute-Efficient Segmentation","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2410.04088","title":"Cross Resolution Encoding-Decoding For Detection Transformers","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2503.04452","title":"A lightweight model FDM-YOLO for small target improvement based on YOLOv8","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2504.07476","title":"CMEdataset Advancing China Map Detection and Standardization with Digital Image Resources","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2507.13085","title":"Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2601.02212","title":"Prior-Guided DETR for Ultrasound Nodule Detection","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2608.06674","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}