{"total":135,"rows":[{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212,"area":null},{"id":"2109.03201","title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","created":"2021-09-07","cited_by_count":180,"area":null},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123,"area":null},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83,"area":null},{"id":"2203.14291","title":"Video Polyp Segmentation: A Deep Learning Perspective","created":"2022-03-27","cited_by_count":82,"area":null},{"id":"2105.08468","title":"Progressively Normalized Self-Attention Network for Video Polyp Segmentation","created":"2021-05-18","cited_by_count":75,"area":null},{"id":"2101.07172","title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","created":"2021-01-18","cited_by_count":71,"area":null},{"id":"2408.08870","title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","created":"2024-08-16","cited_by_count":64,"area":null},{"id":"2107.02368","title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","created":"2021-07-06","cited_by_count":61,"area":null},{"id":"2203.06883","title":"Accelerating DETR Convergence via Semantic-Aligned Matching","created":"2022-03-14","cited_by_count":58,"area":null},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2409.01686","title":"Frequency-Spatial Entanglement Learning for Camouflaged Object Detection","created":"2024-09-03","cited_by_count":46,"area":null},{"id":"2101.07518","title":"BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring","created":"2021-01-19","cited_by_count":45,"area":null},{"id":"2308.08924","title":"Frequency Perception Network for Camouflaged Object Detection","created":"2023-08-17","cited_by_count":37,"area":null},{"id":"2112.07380","title":"TRACER: Extreme Attention Guided Salient Object Tracing Network","created":"2021-12-14","cited_by_count":33,"area":null},{"id":"2211.04800","title":"Designing Network Design Strategies Through Gradient Path Analysis","created":"2022-11-09","cited_by_count":32,"area":null},{"id":"2301.07405","title":"HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness","created":"2023-01-18","cited_by_count":31,"area":null},{"id":"2109.14483","title":"CCTrans: Simplifying and Improving Crowd Counting with Transformer","created":"2021-09-29","cited_by_count":30,"area":null},{"id":"2203.12338","title":"Real-time Object Detection for Streaming Perception","created":"2022-03-23","cited_by_count":30,"area":null},{"id":"2106.11346","title":"GAIA: A Transfer Learning System of Object Detection that Fits Your Needs","created":"2021-06-21","cited_by_count":27,"area":null},{"id":"2405.06284","title":"Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention","created":"2024-05-10","cited_by_count":26,"area":null},{"id":"2309.06751","title":"Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances","created":"2023-09-13","cited_by_count":20,"area":null},{"id":"2306.07532","title":"Referring Camouflaged Object Detection","created":"2023-06-13","cited_by_count":19,"area":null},{"id":"2203.04313","title":"Multi-Scale Adaptive Network for Single Image Denoising","created":"2022-03-08","cited_by_count":17,"area":null},{"id":"2110.12093","title":"Circle Representation for Medical Object Detection","created":"2021-10-22","cited_by_count":15,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15,"area":null},{"id":"2207.12926","title":"A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2104.02230","title":"Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning","created":"2021-04-06","cited_by_count":12,"area":null},{"id":"2208.01762","title":"Robust RGB-D Fusion for Saliency Detection","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2108.10809","title":"Reconcile Prediction Consistency for Balanced Object Detection","created":"2021-08-24","cited_by_count":11,"area":null},{"id":"2111.10614","title":"GMSRF-Net: An improved generalizability with global multi-scale residual fusion network for polyp segmentation","created":"2021-11-20","cited_by_count":11,"area":null},{"id":"2209.02934","title":"Boundary Guided Semantic Learning for Real-time COVID-19 Lung Infection Segmentation System","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2104.12389","title":"Variational Pedestrian Detection","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2203.00129","title":"BlazeNeo: Blazing fast polyp segmentation and neoplasm detection","created":"2022-02-28","cited_by_count":10,"area":null},{"id":"2203.14341","title":"MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation","created":"2022-03-27","cited_by_count":10,"area":null},{"id":"2208.11356","title":"Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2209.02280","title":"Progressive Glass Segmentation","created":"2022-09-06","cited_by_count":10,"area":null},{"id":"2409.09588","title":"GLCONet: Learning Multi-source Perception Representation for Camouflaged Object Detection","created":"2024-09-15","cited_by_count":10,"area":null},{"id":"2201.10781","title":"ASFD: Automatic and Scalable Face Detector","created":"2022-01-26","cited_by_count":9,"area":null},{"id":"2311.18814","title":"Is Underwater Image Enhancement All Object Detectors Need?","created":"2023-11-30","cited_by_count":9,"area":null},{"id":"2110.04904","title":"Modality-Guided Subnetwork for Salient Object Detection","created":"2021-10-10","cited_by_count":8,"area":null},{"id":"2209.04639","title":"Large-Field Contextual Feature Learning for Glass Detection","created":"2022-09-10","cited_by_count":8,"area":null},{"id":"2307.12309","title":"Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network","created":"2023-07-23","cited_by_count":8,"area":null},{"id":"2104.14805","title":"Few-Shot Video Object Detection","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2207.14172","title":"Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2210.04252","title":"Precise Single-stage Detector","created":"2022-10-09","cited_by_count":7,"area":null},{"id":"2411.06703","title":"United Domain Cognition Network for Salient Object Detection in Optical Remote Sensing Images","created":"2024-11-11","cited_by_count":7,"area":null},{"id":"2106.02859","title":"Convolutional Neural Networks with Gated Recurrent Connections","created":"2021-06-05","cited_by_count":6,"area":null},{"id":"2110.15045","title":"LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2201.00767","title":"BDG-Net: Boundary Distribution Guided Network for Accurate Polyp Segmentation","created":"2022-01-03","cited_by_count":6,"area":null},{"id":"2210.15156","title":"Towards Complex Backgrounds: A Unified Difference-Aware Decoder for Binary Segmentation","created":"2022-10-27","cited_by_count":6,"area":null},{"id":"2306.00440","title":"Edge-guided Representation Learning for Underwater Object Detection","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2410.17144","title":"YOLO-TS: Real-Time Traffic Sign Detection with Enhanced Accuracy Using Optimized Receptive Fields and Anchor-Free Fusion","created":"2024-10-22","cited_by_count":6,"area":null},{"id":"2504.10979","title":"Deep Learning in Concealed Dense Prediction","created":"2025-04-15","cited_by_count":6,"area":null},{"id":"2105.01058","title":"A Dataset and System for Real-Time Gun Detection in Surveillance Video Using Deep Learning","created":"2021-05-03","cited_by_count":5,"area":null},{"id":"2203.09135","title":"Co-visual pattern augmented generative transformer learning for automobile geo-localization","created":"2022-03-17","cited_by_count":5,"area":null},{"id":"2206.01772","title":"Radar Guided Dynamic Visual Attention for Resource-Efficient RGB Object Detection","created":"2022-06-03","cited_by_count":5,"area":null},{"id":"2207.06658","title":"Universal Adaptive Data Augmentation","created":"2022-07-14","cited_by_count":5,"area":null},{"id":"2207.11889","title":"Salient Object Detection for Point Clouds","created":"2022-07-25","cited_by_count":5,"area":null},{"id":"2506.21866","title":"Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images","created":"2025-06-27","cited_by_count":5,"area":null},{"id":"2507.00659","title":"LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment","created":"2025-07-01","cited_by_count":5,"area":null},{"id":"2105.07962","title":"DFENet: A Novel Dimension Fusion Edge Guided Network for Brain MRI Segmentation","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2205.15720","title":"Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentation","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2212.05387","title":"General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments","created":"2022-12-11","cited_by_count":4,"area":null},{"id":"2306.11334","title":"Depth and DOF Cues Make A Better Defocus Blur Detector","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2307.09274","title":"Improving Text Semantic Similarity Modeling through a 3D Siamese Network","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2307.12429","title":"SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings","created":"2023-07-23","cited_by_count":4,"area":null},{"id":"2309.08365","title":"M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2403.13030","title":"Super-High-Fidelity Image Compression via Hierarchical-ROI and Adaptive Quantization","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2504.09666","title":"Uncertainty Guided Refinement for Fine-Grained Salient Object Detection","created":"2025-04-13","cited_by_count":4,"area":null},{"id":"2101.02639","title":"More Reliable AI Solution: Breast Ultrasound Diagnosis Using Multi-AI Combination","created":"2021-01-07","cited_by_count":3,"area":null},{"id":"2101.05687","title":"Towards Accurate Camouflaged Object Detection with Mixture Convolution and Interactive Fusion","created":"2021-01-14","cited_by_count":3,"area":null},{"id":"2207.03558","title":"Mirror Complementary Transformer Network for RGB-thermal Salient Object Detection","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2401.12439","title":"MAST: Video Polyp Segmentation with a Mixture-Attention Siamese Transformer","created":"2024-01-23","cited_by_count":3,"area":null},{"id":"2405.11151","title":"Multi-scale Information Sharing and Selection Network with Boundary Attention for Polyp Segmentation","created":"2024-05-18","cited_by_count":3,"area":null},{"id":"2412.19878","title":"YOLO-MST: Multiscale deep learning method for infrared small target detection based on super-resolution and YOLO","created":"2024-12-27","cited_by_count":3,"area":null},{"id":"2105.10104","title":"EMface: Detecting Hard Faces by Exploring Receptive Field Pyraminds","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2108.01527","title":"Double-Dot Network for Antipodal Grasp Detection","created":"2021-08-03","cited_by_count":2,"area":null},{"id":"2108.10503","title":"Small Object Detection Based on Modified FSSD and Model Compression","created":"2021-08-24","cited_by_count":2,"area":null},{"id":"2301.06892","title":"Cooperation Learning Enhanced Colonic Polyp Segmentation Based on Transformer-CNN Fusion","created":"2023-01-17","cited_by_count":2,"area":null},{"id":"2307.06260","title":"UGCANet: A Unified Global Context-Aware Transformer-based Network with Feature Alignment for Endoscopic Image Analysis","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2311.08745","title":"Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization","created":"2023-11-15","cited_by_count":2,"area":null},{"id":"2404.04155","title":"MarsSeg: Mars Surface Semantic Segmentation with Multi-level Extractor and Connector","created":"2024-04-05","cited_by_count":2,"area":null},{"id":"2408.12102","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2101.06438","title":"Adaptive Remote Sensing Image Attribute Learning for Active Object Detection","created":"2021-01-16","cited_by_count":1,"area":null},{"id":"2101.10226","title":"Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection","created":"2021-01-25","cited_by_count":1,"area":null},{"id":"2105.03139","title":"Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2108.11101","title":"Detecting Small Objects in Thermal Images Using Single-Shot Detector","created":"2021-08-25","cited_by_count":1,"area":null},{"id":"2110.10869","title":"LC3Net: Ladder context correlation complementary network for salient object detection","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2301.07431","title":"Sharp Eyes: A Salient Object Detector Working The Same Way as Human Visual Characteristics","created":"2023-01-18","cited_by_count":1,"area":null},{"id":"2303.04939","title":"UT-Net: Combining U-Net and Transformer for Joint Optic Disc and Cup Segmentation and Glaucoma Detection","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2307.10955","title":"Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2408.14189","title":"EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detection","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2410.10389","title":"Reverse Refinement Network for Narrow Rural Road Detection in High-Resolution Satellite Imagery","created":"2024-10-14","cited_by_count":1,"area":null},{"id":"2502.03829","title":"Frequency Domain Enhanced U-Net for Low-Frequency Information-Rich Image Segmentation in Surgical and Deep-Sea Exploration Robots","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2502.09660","title":"Towards Fine-grained Interactive Segmentation in Images and Videos","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2503.12404","title":"SAM2-ELNet: Label Enhancement and Automatic Annotation for Remote Sensing Segmentation","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2503.21187","title":"DSU-Net:An Improved U-Net Model Based on DINOv2 and SAM2 with Multi-scale Cross-model Feature Enhancement","created":"2025-03-27","cited_by_count":1,"area":null}],"next_cursor":"100"}