{"total":109,"rows":[{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2312.16886","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","created":"2023-12-28","cited_by_count":122,"area":"mllm"},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2306.02316","title":"Temporal Dynamic Quantization for Diffusion Models","created":"2023-06-04","cited_by_count":81,"area":"diffusion"},{"id":"2412.13303","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","created":"2024-12-17","cited_by_count":77,"area":"mllm"},{"id":"2401.16456","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","created":"2024-01-29","cited_by_count":56,"area":null},{"id":"2403.19967","title":"Rewrite the Stars","created":"2024-03-29","cited_by_count":55,"area":null},{"id":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21,"area":"distill"},{"id":"2301.13156","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2411.15241","title":"EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality","created":"2024-11-22","cited_by_count":17,"area":"ssm"},{"id":"2403.19963","title":"Efficient Modulation for Vision Networks","created":"2024-03-29","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":"2502.04363","title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","created":"2025-02-05","cited_by_count":15,"area":"diffusion"},{"id":"2211.06088","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","created":"2022-11-11","cited_by_count":13,"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":"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":"2409.11182","title":"Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving","created":"2024-09-16","cited_by_count":11,"area":"lr"},{"id":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2311.03747","title":"SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2401.06426","title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer","created":"2024-01-12","cited_by_count":9,"area":null},{"id":"2403.16020","title":"PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference","created":"2024-03-24","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":"2502.05800","title":"MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device","created":"2025-02-09","cited_by_count":8,"area":null},{"id":"2408.17207","title":"NanoMVG: USV-Centric Low-Power Multi-Task Visual Grounding based on Prompt-Guided Camera and 4D mmWave Radar","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2405.17081","title":"Effective Layer Pruning Through Similarity Metric Perspective","created":"2024-05-27","cited_by_count":6,"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":"2308.12494","title":"MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2309.03452","title":"Multimodal Guidance Network for Missing-Modality Inference in Content Moderation","created":"2023-09-07","cited_by_count":5,"area":"mllm"},{"id":"2405.16096","title":"MINet: Multi-scale Interactive Network for Real-time Salient Object Detection of Strip Steel Surface Defects","created":"2024-05-25","cited_by_count":5,"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":"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":"2312.08851","title":"Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2401.12736","title":"$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2402.05410","title":"SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2404.00103","title":"PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks","created":"2024-03-29","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":"2407.11224","title":"Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding","created":"2024-07-15","cited_by_count":4,"area":null},{"id":"2501.07087","title":"Video Quality Assessment for Online Processing: From Spatial to Temporal Sampling","created":"2025-01-13","cited_by_count":4,"area":null},{"id":"2502.15021","title":"Thicker and Quicker: A Jumbo Token for Fast Plain Vision Transformers","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2311.15213","title":"Leveraging Anatomical Constraints with Uncertainty for Pneumothorax Segmentation","created":"2023-11-26","cited_by_count":3,"area":null},{"id":"2402.03714","title":"Advancing Location-Invariant and Device-Agnostic Motion Activity Recognition on Wearable Devices","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2505.18636","title":"Asymmetric Duos: Sidekicks Improve Uncertainty","created":"2025-05-24","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":"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":"2511.09942","title":"AdaptViG: Adaptive Vision GNN with Exponential Decay Gating","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2607.16314","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","created":"2026-07-15","cited_by_count":2,"area":"wm"},{"id":"2309.13972","title":"Audio classification with Dilated Convolution with Learnable Spacings","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2402.14591","title":"High-Speed Detector For Low-Powered Devices In Aerial Grasping","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2403.19969","title":"Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2404.06258","title":"Robust feature knowledge distillation for enhanced performance of lightweight crack segmentation models","created":"2024-04-09","cited_by_count":1,"area":"distill"},{"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":"2408.10031","title":"Dynamic Label Injection for Imbalanced Industrial Defect Segmentation","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2409.20171","title":"Annotation-Free Curb Detection Leveraging Altitude Difference Image","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2410.11400","title":"RSSI-Assisted CSI-Based Passenger Counting with Multiple Wi-Fi Receivers","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2501.02314","title":"RadarNeXt: Real-Time and Reliable 3D Object Detector Based On 4D mmWave Imaging Radar","created":"2025-01-04","cited_by_count":1,"area":null},{"id":"2504.15991","title":"Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2508.10817","title":"Mobile-Friendly Deep Learning for Plant Disease Detection: A Lightweight CNN Benchmark Across 101 Classes of 33 Crops","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2602.00910","title":"Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2603.19567","title":"Efficiency Follows Global-Local Decoupling","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.20778","title":"PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2605.08627","title":"DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2308.10610","title":"Ear-Keeper: A Cross-Platform AI System for Rapid and Accurate Ear Disease Diagnosis","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2311.02947","title":"Multi-view learning for automatic classification of multi-wavelength auroral images","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2404.00807","title":"GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restoration","created":"2024-03-31","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":"2409.04218","title":"MpoxMamba: A Grouped Mamba-based Lightweight Hybrid Network for Mpox Detection","created":"2024-09-06","cited_by_count":0,"area":"ssm"},{"id":"2411.14345","title":"Layer Pruning with Consensus: A Triple-Win Solution","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2411.15653","title":"OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs","created":"2024-11-23","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":"2501.02040","title":"A Separable Self-attention Inspired by the State Space Model for Computer Vision","created":"2025-01-03","cited_by_count":0,"area":"ssm"},{"id":"2503.00340","title":"UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search","created":"2025-03-01","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":"2503.14757","title":"RETHINED: A New Benchmark and Baseline for Real-Time High-Resolution Image Inpainting On Edge Devices","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2503.22841","title":"GmNet: Revisiting Gating Mechanisms From A Frequency View","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2503.23796","title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","created":"2025-03-31","cited_by_count":0,"area":"diffusion"},{"id":"2505.22226","title":"Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products","created":"2025-05-28","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":"2507.10999","title":"SpaRTAN: Spatial Reinforcement Token-based Aggregation Network for Visual Recognition","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2508.02372","title":"TRUDI and TITUS: A Multi-Perspective Dataset and A Three-Stage Recognition System for Transportation Unit Identification","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.08849","title":"Adaptive High-Frequency Preprocessing for Video Coding","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2509.20688","title":"RAM-NAS: Resource-aware Multiobjective Neural Architecture Search Method for Robot Vision Tasks","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2511.00335","title":"Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2601.03431","title":"WeedRepFormer: Reparameterizable Vision Transformers for Real-Time Waterhemp Segmentation and Gender Classification","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2602.05262","title":"ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.26356","title":"From Pen to Pixel: Translating Hand-Drawn Plots into Graphical APIs via a Novel Benchmark and Efficient Adapter","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.26425","title":"CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.26551","title":"Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.26835","title":"ANVIL: Accelerator-Native Video Interpolation via Codec Motion Vector Priors","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.20291","title":"Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.23320","title":"KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition","created":"2026-04-25","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":"2606.22892","title":"IViT: A Novel Interpretable Visual Transformer for Skin Disease Detection","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":"100"}