{"total":73,"rows":[{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68,"area":null},{"id":"2403.06258","title":"Poly Kernel Inception Network for Remote Sensing Detection","created":"2024-03-10","cited_by_count":52,"area":null},{"id":"2407.03653","title":"reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis","created":"2024-07-04","cited_by_count":48,"area":null},{"id":"2403.07589","title":"PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution","created":"2024-03-12","cited_by_count":28,"area":null},{"id":"2405.06228","title":"Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation","created":"2024-05-10","cited_by_count":25,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2411.06456","title":"Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration","created":"2024-11-10","cited_by_count":19,"area":null},{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2408.03703","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","created":"2024-08-07","cited_by_count":12,"area":null},{"id":"2304.03198","title":"RFAConv: Receptive-Field Attention Convolution for Improving Convolutional Neural Networks","created":"2023-04-06","cited_by_count":10,"area":null},{"id":"2407.05128","title":"SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2506.02197","title":"NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution","created":"2025-06-02","cited_by_count":9,"area":null},{"id":"2512.12229","title":"Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder","created":"2025-12-13","cited_by_count":7,"area":null},{"id":"2306.06365","title":"FalconNet: Factorization for the Light-weight ConvNets","created":"2023-06-10","cited_by_count":6,"area":null},{"id":"2503.14867","title":"DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2405.12721","title":"StarLKNet: Star Mixup with Large Kernel Networks for Palm Vein Identification","created":"2024-05-21","cited_by_count":5,"area":null},{"id":"2504.01954","title":"Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2405.06525","title":"SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2503.11219","title":"MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2410.06373","title":"Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2506.09724","title":"The Four Color Theorem for Cell Instance Segmentation","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2507.11893","title":"Spatial Frequency Modulation for Semantic Segmentation","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2407.17834","title":"Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2410.15279","title":"ContextDet: Temporal Action Detection with Adaptive Context Aggregation","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2505.15867","title":"SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.17963","title":"OmniESI: A unified framework for enzyme-substrate interaction prediction with progressive conditional deep learning","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2512.22664","title":"Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains","created":"2025-12-27","cited_by_count":2,"area":null},{"id":"2305.10110","title":"Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2310.16483","title":"Gramian Attention Heads are Strong yet Efficient Vision Learners","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2406.07536","title":"Towards Fundamentally Scalable Model Selection: Asymptotically Fast Update and Selection","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2408.11679","title":"BadVim: Unveiling Backdoor Threats in Visual State Space Model","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2412.00724","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2503.17110","title":"Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2504.18136","title":"MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2509.21927","title":"SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2605.17470","title":"EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2307.07265","title":"AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2311.11683","title":"SIAM: A Simple Alternating Mixer for Video Prediction","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2403.15004","title":"ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2407.14352","title":"Vision-Based Power Line Cables and Pylons Detection for Low Flying Aircraft","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2407.20843","title":"DFE-IANet: A Method for Polyp Image Classification Based on Dual-domain Feature Extraction and Interaction Attention","created":"2024-07-30","cited_by_count":0,"area":null},{"id":"2408.06633","title":"A lightweight YOLOv5-FFM model for occlusion pedestrian detection","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2410.05969","title":"Deep neural network-based detection of counterfeit products from smartphone images","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2411.19027","title":"Enhancing Neural Network Robustness Against Fault Injection Through Non-linear Weight Transformations","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2412.19628","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","created":"2024-12-27","cited_by_count":0,"area":null},{"id":"2503.08668","title":"SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2503.23947","title":"Spectral-Adaptive Modulation Networks for Visual Perception","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2504.19822","title":"Mj\\\"olnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2506.09733","title":"AtmosMJ: Revisiting Gating Mechanism for AI Weather Forecasting Beyond the Year Scale","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.17089","title":"IONext: Unlocking the Next Era of Inertial Odometry","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2508.17894","title":"Designing Practical Models for Isolated Word Visual Speech Recognition","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2509.06713","title":"MRI-Based Brain Tumor Detection through an Explainable EfficientNetV2 and MLP-Mixer-Attention Architecture","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.09242","title":"CoAtNeXt:An Attention-Enhanced ConvNeXtV2-Transformer Hybrid Model for Gastric Tissue Classification","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2510.10553","title":"MRS-YOLO Railroad Transmission Line Foreign Object Detection Based on Improved YOLO11 and Channel Pruning","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.20092","title":"Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.14515","title":"IMSE: Efficient U-Net-based Speech Enhancement using Inception Depthwise Convolution and Amplitude-Aware Linear Attention","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2604.17439","title":"Attention Is not Everything: Efficient Alternatives for Vision","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.07338","title":"ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.22677","title":"Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.02219","title":"Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolution","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.06102","title":"Step-adaptive multimodal fusion network with multi-scale cloud feature learning for ultra-short-term solar irradiance forecasting","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.06234","title":"WING: A Window-Prior-Based Generative Network with Gated Inception for Cross-Modality CT Synthesis","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.10749","title":"Water Reflection Detection Using Symmetric Attention","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.21456","title":"SPDCN: Strip-based Deformable Convolutional Network for Steel Surface Defect Segmentation","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.05258","title":"Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.16756","title":"Binarized High-Efficiency RAW Video Restoration and Beyond","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2610.03656","title":"Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03772","title":"Energy Variation in Training Modern Computer Vision Architectures","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}