{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122},{"id":"1705.02950","title":"Learning non-maximum suppression","created":"2017-05-08","cited_by_count":113},{"id":"2202.06934","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","created":"2022-02-14","cited_by_count":105},{"id":"2307.08388","title":"Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation","created":"2023-07-17","cited_by_count":84},{"id":"2004.13316","title":"SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing","created":"2020-04-28","cited_by_count":62},{"id":"2601.03236","title":"MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents","created":"2026-01-06","cited_by_count":52},{"id":"2209.13351","title":"SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery","created":"2022-09-27","cited_by_count":47},{"id":"2602.19320","title":"Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations","created":"2026-02-22","cited_by_count":21},{"id":"2312.15447","title":"Superpixel-based and Spatially-regularized Diffusion Learning for Unsupervised Hyperspectral Image Clustering","created":"2023-12-24","cited_by_count":13},{"id":"2112.11798","title":"YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles","created":"2021-12-22","cited_by_count":12},{"id":"2507.17135","title":"SADA: Stability-guided Adaptive Diffusion Acceleration","created":"2025-07-23","cited_by_count":11},{"id":"2508.01506","title":"FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models","created":"2025-08-02","cited_by_count":9},{"id":"2502.07216","title":"SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer","created":"2025-02-11","cited_by_count":7},{"id":"2106.05124","title":"PCNet: A Structure Similarity Enhancement Method for Multispectral and Multimodal Image Registration","created":"2021-06-09","cited_by_count":6},{"id":"2502.13023","title":"Detection and Geographic Localization of Natural Objects in the Wild: A Case Study on Palms","created":"2025-02-18","cited_by_count":6},{"id":"2403.03161","title":"PalmProbNet: A Probabilistic Approach to Understanding Palm Distributions in Ecuadorian Tropical Forest via Transfer Learning","created":"2024-03-05","cited_by_count":5},{"id":"2503.16963","title":"Center-guided Classifier for Semantic Segmentation of Remote Sensing Images","created":"2025-03-21","cited_by_count":5},{"id":"2602.18907","title":"DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation","created":"2026-02-21","cited_by_count":5},{"id":"2407.06614","title":"Implicit Regression in Subspace for High-Sensitivity CEST Imaging","created":"2024-07-09","cited_by_count":3},{"id":"2504.13469","title":"HMPE:HeatMap Embedding for Efficient Transformer-Based Small Object Detection","created":"2025-04-18","cited_by_count":3},{"id":"2509.12400","title":"From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization","created":"2025-09-15","cited_by_count":3},{"id":"2603.02419","title":"DINOv3 Visual Representations for Blueberry Perception Toward Robotic Harvesting","created":"2026-03-02","cited_by_count":2},{"id":"2604.20845","title":"CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation","created":"2026-02-10","cited_by_count":2},{"id":"2412.14751","title":"Query pipeline optimization for cancer patient question answering systems","created":"2024-12-19","cited_by_count":1},{"id":"2509.12442","title":"Cott-ADNet: Lightweight Real-Time Cotton Boll and Flower Detection Under Field Conditions","created":"2025-09-15","cited_by_count":1},{"id":"2511.20081","title":"Blind Adaptive Local Denoising for CEST Imaging","created":"2025-11-25","cited_by_count":1},{"id":"2604.20846","title":"ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation","created":"2026-02-10","cited_by_count":1}],"next_cursor":null}