{"total":123,"rows":[{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88,"area":"diffusion"},{"id":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","cited_by_count":62,"area":null},{"id":"2412.10137","title":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments","created":"2024-12-13","cited_by_count":50,"area":null},{"id":"2312.06660","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","created":"2023-12-11","cited_by_count":41,"area":null},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2312.00343","title":"OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline","created":"2023-12-01","cited_by_count":30,"area":null},{"id":"2406.19833","title":"LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation","created":"2024-06-28","cited_by_count":28,"area":null},{"id":"2402.15761","title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","created":"2024-02-24","cited_by_count":22,"area":"ssm"},{"id":"2501.07256","title":"EdgeTAM: On-Device Track Anything Model","created":"2025-01-13","cited_by_count":21,"area":null},{"id":"2404.16484","title":"Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey","created":"2024-04-25","cited_by_count":19,"area":null},{"id":"2312.05760","title":"RepViT-SAM: Towards Real-Time Segmenting Anything","created":"2023-12-10","cited_by_count":17,"area":null},{"id":"2403.09192","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2411.17473","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","created":"2024-11-26","cited_by_count":15,"area":"ssm"},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2606.13108","title":"PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks","created":"2026-06-11","cited_by_count":14,"area":"mllm"},{"id":"2411.17261","title":"HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator","created":"2024-11-26","cited_by_count":13,"area":null},{"id":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"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":"2507.01838","title":"MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices","created":"2025-07-02","cited_by_count":12,"area":null},{"id":"2411.06786","title":"ScaleKD: Strong Vision Transformers Could Be Excellent Teachers","created":"2024-11-11","cited_by_count":11,"area":"distill"},{"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":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2412.10040","title":"RemDet: Rethinking Efficient Model Design for UAV Object Detection","created":"2024-12-13","cited_by_count":9,"area":null},{"id":"2412.20645","title":"YOLO-UniOW: Efficient Universal Open-World Object Detection","created":"2024-12-30","cited_by_count":9,"area":null},{"id":"2501.15369","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2310.05392","title":"Lightweight Full-Convolutional Siamese Tracker","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2409.18569","title":"Cross-video Identity Correlating for Person Re-identification Pre-training","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2503.07674","title":"TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation","created":"2025-03-10","cited_by_count":8,"area":null},{"id":"2411.11011","title":"CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modules","created":"2024-11-17","cited_by_count":7,"area":null},{"id":"2409.03460","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2411.16170","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2502.13693","title":"Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention","created":"2025-02-19","cited_by_count":5,"area":"ssm"},{"id":"2505.21847","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2312.01740","title":"MobileUtr: Revisiting the relationship between light-weight CNN and Transformer for efficient medical image segmentation","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2312.01741","title":"SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolution","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2405.03952","title":"HAFFormer: A Hierarchical Attention-Free Framework for Alzheimer's Disease Detection From Spontaneous Speech","created":"2024-05-07","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":"2412.05888","title":"MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Day","created":"2024-12-08","cited_by_count":4,"area":null},{"id":"2412.16085","title":"Efficient MedSAMs: Segment Anything in Medical Images on Laptop","created":"2024-12-20","cited_by_count":4,"area":null},{"id":"2509.04669","title":"VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation","created":"2025-09-04","cited_by_count":4,"area":"ssm"},{"id":"2511.15833","title":"EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3","created":"2025-11-19","cited_by_count":4,"area":null},{"id":"2412.10995","title":"RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone","created":"2024-12-14","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":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2508.09000","title":"UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2408.09248","title":"FPGA: Flexible Portrait Generation Approach","created":"2024-08-17","cited_by_count":2,"area":"diffusion"},{"id":"2409.07896","title":"MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space Models","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2503.06930","title":"Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping","created":"2025-03-10","cited_by_count":2,"area":"diffusion"},{"id":"2506.21109","title":"Pushing Trade-Off Boundaries: Compact yet Effective Remote Sensing Change Detection","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2507.01463","title":"NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2511.19301","title":"IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2310.06629","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2401.13998","title":"WAL-Net: Weakly supervised auxiliary task learning network for carotid plaques classification","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2407.12217","title":"AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2408.09240","title":"RepControlNet: ControlNet Reparameterization","created":"2024-08-17","cited_by_count":1,"area":"diffusion"},{"id":"2409.06285","title":"Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2410.21822","title":"PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2412.03055","title":"Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2502.03772","title":"A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinoma","created":"2025-02-06","cited_by_count":1,"area":"moe"},{"id":"2505.13461","title":"FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2508.15057","title":"GasTwinFormer: A Hybrid Vision Transformer for Livestock Methane Emission Segmentation and Dietary Classification in Optical Gas Imaging","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2508.15476","title":"LGMSNet: Thinning a medical image segmentation model via dual-level multiscale fusion","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2508.16884","title":"A Lightweight Convolution and Vision Transformer integrated model with Multi-scale Self-attention Mechanism","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2602.07403","title":"Surveillance Facial Image Quality Assessment: A Multi-dimensional Dataset and Lightweight Model","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.11441","title":"Detect Anything in Real Time: From Single-Prompt Segmentation to Multi-Class Detection","created":"2026-03-12","cited_by_count":1,"area":"mllm"},{"id":"2401.15942","title":"Generating Multi-Center Classifier via Conditional Gaussian Distribution","created":"2024-01-29","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":"2406.02652","title":"RepCNN: Micro-sized, Mighty Models for Wakeword Detection","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2407.00131","title":"RepAct: The Re-parameterizable Adaptive Activation Function","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2407.10419","title":"Omni-Dimensional Frequency Learner for General Time Series Analysis","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2407.17480","title":"Dynamic Universal Approximation Theory: The Basic Theory for Deep Learning-Based Computer Vision Models","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2408.12248","title":"PRG: Prompt-Based Distillation Without Annotation via Proxy Relational Graph","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2408.12974","title":"Accuracy Improvement of Cell Image Segmentation Using Feedback Former","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2412.02197","title":"Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images","created":"2024-12-03","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":"2501.01773","title":"Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Content","created":"2025-01-03","cited_by_count":0,"area":null},{"id":"2501.14535","title":"Rethinking Encoder-Decoder Flow Through Shared Structures","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2502.06189","title":"Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2502.06681","title":"CHIRLA: Comprehensive High-resolution Identification and Re-identification for Large-scale Analysis","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2503.03148","title":"Partial Convolution Meets Visual Attention","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.11995","title":"Fraesormer: Learning Adaptive Sparse Transformer for Efficient Food Recognition","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2503.14948","title":"ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-Agents","created":"2025-03-19","cited_by_count":0,"area":"agents"},{"id":"2503.22841","title":"GmNet: Revisiting Gating Mechanisms From A Frequency View","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2504.06205","title":"HER-Seg: Holistically Efficient Segmentation for High-Resolution Medical Images","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2504.14825","title":"ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2506.19330","title":"Comparative Performance of Finetuned ImageNet Pre-trained Models for Electronic Component Classification","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2507.01290","title":"Learning an Ensemble Token from Task-driven Priors in Facial Analysis","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.13569","title":"Change of Thought: Adaptive Test-Time Computation","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2508.01385","title":"Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2510.21079","title":"WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition","created":"2025-10-24","cited_by_count":0,"area":"ssm"},{"id":"2511.15645","title":"FDIO: Frequency Decomposed Inertial Odometry","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2511.19718","title":"Rethinking Vision Transformer Depth via Structural Reparameterization","created":"2025-11-24","cited_by_count":0,"area":"inference"},{"id":"2512.21984","title":"A Lightweight Multi-Scale Attention Framework for Real-Time Spinal Endoscopic Instance Segmentation","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2512.23234","title":"Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring","created":"2025-12-29","cited_by_count":0,"area":null}],"next_cursor":"100"}