{"total":33,"rows":[{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"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":"2506.00979","title":"Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection","created":"2025-06-01","cited_by_count":34,"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":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23,"area":null},{"id":"2502.11168","title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2405.11582","title":"SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization","created":"2024-05-19","cited_by_count":17,"area":null},{"id":"2502.05147","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","created":"2025-02-07","cited_by_count":8,"area":null},{"id":"2503.06683","title":"Dynamic Dictionary Learning for Remote Sensing Image Segmentation","created":"2025-03-09","cited_by_count":7,"area":null},{"id":"2402.13578","title":"TransGOP: Transformer-Based Gaze Object Prediction","created":"2024-02-21","cited_by_count":6,"area":null},{"id":"2406.15320","title":"Rethinking Remote Sensing Change Detection With A Mask View","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2507.10881","title":"Trexplorer Super: Topologically Correct Centerline Tree Tracking of Tubular Objects in CT Volumes","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2412.16553","title":"Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2503.03088","title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2505.24038","title":"Conformal Object Detection by Sequential Risk Control","created":"2025-05-29","cited_by_count":3,"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":"2408.14998","title":"FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting","created":"2024-08-27","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":"2402.14309","title":"YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2505.21868","title":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.19807","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2510.03160","title":"SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus","created":"2025-10-03","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":"2601.08728","title":"Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2503.08092","title":"SparseVoxFormer: Sparse Voxel-based Transformer for Multi-modal 3D Object Detection","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2604.26806","title":"ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.10269","title":"Increasing the Efficiency of DETR for Maritime High-Resolution Images","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.14110","title":"SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.16909","title":"TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2607.00124","title":"Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.28706","title":"Variable-Granularity Tokenization for High-Resolution Object Detection","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}