{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1905.13545","title":"High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","created":"2019-05-28","cited_by_count":310},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"1906.08988","title":"A Fourier Perspective on Model Robustness in Computer Vision","created":"2019-06-21","cited_by_count":288},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2012.11879","title":"FcaNet: Frequency Channel Attention Networks","created":"2020-12-22","cited_by_count":179},{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110},{"id":"2007.09451","title":"Feature Pyramid Transformer","created":"2020-07-18","cited_by_count":96},{"id":"2108.11250","title":"YOLOP: You Only Look Once for Panoptic Driving Perception","created":"2021-08-25","cited_by_count":82},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81},{"id":"2203.05151","title":"Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity","created":"2022-03-10","cited_by_count":77},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62},{"id":"2008.09604","title":"Delving Deeper into Anti-aliasing in ConvNets","created":"2020-08-21","cited_by_count":60},{"id":"1911.09516","title":"Learning Spatial Fusion for Single-Shot Object Detection","created":"2019-11-21","cited_by_count":59},{"id":"2003.00872","title":"AlignSeg: Feature-Aligned Segmentation Networks","created":"2020-02-24","cited_by_count":53},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45},{"id":"2011.14288","title":"Learning Affinity-Aware Upsampling for Deep Image Matting","created":"2020-11-29","cited_by_count":37},{"id":"2007.14313","title":"Deep frequency principle towards understanding why deeper learning is faster","created":"2020-07-28","cited_by_count":31},{"id":"2408.04804","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","created":"2024-08-09","cited_by_count":29},{"id":"2108.00580","title":"GraphFPN: Graph Feature Pyramid Network for Object Detection","created":"2021-08-02","cited_by_count":25},{"id":"2210.10775","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","created":"2022-10-19","cited_by_count":25},{"id":"2012.04733","title":"CARAFE++: Unified Content-Aware ReAssembly of FEatures","created":"2020-12-07","cited_by_count":20},{"id":"2112.11798","title":"YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles","created":"2021-12-22","cited_by_count":12},{"id":"2207.04415","title":"SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow","created":"2022-07-10","cited_by_count":10},{"id":"2503.19474","title":"A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition","created":"2025-03-25","cited_by_count":10},{"id":"2505.00941","title":"FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection","created":"2025-05-02","cited_by_count":10},{"id":"2012.01733","title":"Dual Refinement Feature Pyramid Networks for Object Detection","created":"2020-12-03","cited_by_count":8},{"id":"2504.14205","title":"Dual-channel Heterophilic Message Passing for Graph Fraud Detection","created":"2025-04-19","cited_by_count":8},{"id":"2504.14204","title":"DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection","created":"2025-04-19","cited_by_count":7}],"next_cursor":null}