{"total":99,"rows":[{"id":"2407.03653","title":"reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis","created":"2024-07-04","cited_by_count":48,"area":null},{"id":"2412.09619","title":"SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training","created":"2024-12-12","cited_by_count":27,"area":"diffusion"},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"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":"2501.15369","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2512.23562","title":"VL-RouterBench: A Benchmark for Vision-Language Model Routing","created":"2025-12-29","cited_by_count":8,"area":"mllm"},{"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":"2501.12030","title":"Advancing Earth Observation: A Survey on AI-Powered Image Processing in Satellites","created":"2025-01-21","cited_by_count":7,"area":null},{"id":"2410.05500","title":"Residual Kolmogorov-Arnold Network for Enhanced Deep Learning","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2411.18199","title":"Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges","created":"2024-11-27","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":"2501.01121","title":"PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation","created":"2025-01-02","cited_by_count":5,"area":null},{"id":"2502.21130","title":"Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2512.02965","title":"UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement","created":"2025-12-02","cited_by_count":5,"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":"2508.14486","title":"WeedSense: Multi-Task Learning for Weed Segmentation, Height Estimation, and Growth Stage Classification","created":"2025-08-20","cited_by_count":4,"area":null},{"id":"2508.18445","title":"VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2601.12798","title":"PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition","created":"2026-01-19","cited_by_count":4,"area":"moe"},{"id":"2603.16423","title":"SF-Mamba: Rethinking State Space Model for Vision","created":"2026-03-17","cited_by_count":4,"area":"ssm"},{"id":"2504.09297","title":"Cycle Training with Semi-Supervised Domain Adaptation: Bridging Accuracy and Efficiency for Real-Time Mobile Scene Detection","created":"2025-04-12","cited_by_count":3,"area":null},{"id":"2506.15835","title":"MoNetV2: Enhanced Motion Network for Freehand 3D Ultrasound Reconstruction","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2510.14770","title":"MoCom: Motion-based Inter-MAV Visual Communication Using Event Vision and Spiking Neural Networks","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2506.19955","title":"ZIP: Scalable Crowd Counting via Zero-Inflated Poisson Modeling","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.04323","title":"DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2510.11068","title":"Efficient Test-Time Adaptation through Latent Subspace Coefficients Search","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2510.13714","title":"DeDelayed: Deleting Remote Inference Delay via On-Device Correction","created":"2025-10-15","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":"2512.14052","title":"HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices","created":"2025-12-16","cited_by_count":2,"area":"lr"},{"id":"2601.05913","title":"Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces","created":"2026-01-09","cited_by_count":2,"area":"distill"},{"id":"2603.04090","title":"EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2605.17260","title":"LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs","created":"2026-05-17","cited_by_count":2,"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":"2503.07371","title":"HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detection","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2503.21208","title":"An improved EfficientNetV2 for garbage classification","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2507.07077","title":"RulerNet: Learning Perspective-Invariant Ruler Representations for Robust Image Scale Estimation","created":"2025-07-09","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":"2508.12279","title":"TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2510.15026","title":"MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2602.00852","title":"Investigating the Robustness of Subtask Distillation under Spurious Correlation","created":"2026-01-31","cited_by_count":1,"area":"distill"},{"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":"2603.11917","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.27420","title":"CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2605.06010","title":"Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models","created":"2026-05-07","cited_by_count":1,"area":"diffusion"},{"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":"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":"2412.03871","title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","created":"2024-12-05","cited_by_count":0,"area":"mllm"},{"id":"2503.00731","title":"Robust Real-Time Endoscopic Stereo Matching under Fuzzy Tissue Boundaries","created":"2025-03-02","cited_by_count":0,"area":"ssm"},{"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":"2503.10530","title":"Lightweight Models for Emotional Analysis in Video","created":"2025-03-13","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":"2505.22226","title":"Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.12542","title":"PLD: A Choice-Theoretic List-Wise Knowledge Distillation","created":"2025-06-14","cited_by_count":0,"area":"distill"},{"id":"2506.14170","title":"Progressive Multimodal Interaction Network for Reliable Quantification of Fish Feeding Intensity in Aquaculture","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2507.22101","title":"AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2507.23225","title":"YOLO-ROC: A High-Precision and Ultra-Lightweight Model for Real-Time Road Damage Detection","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.01339","title":"SBP-YOLO:A Lightweight Real-Time Model for Detecting Speed Bumps and Potholes toward Intelligent Vehicle Suspension Systems","created":"2025-08-02","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":"2508.01633","title":"Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression","created":"2025-08-03","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":"2509.07993","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2509.21696","title":"MS-YOLO: Infrared Object Detection for Edge Deployment via MobileNetV4 and SlideLoss","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.02457","title":"Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.17373","title":"Facial Expression-based Parkinson's Disease Severity Diagnosis via Feature Fusion and Adaptive Class Balancing","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.19273","title":"MobiAct: Efficient MAV Action Recognition Using MobileNetV4 with Contrastive Learning and Knowledge Distillation","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2510.22236","title":"DiffusionLane: Diffusion Model for Lane Detection","created":"2025-10-25","cited_by_count":0,"area":"diffusion"},{"id":"2511.12480","title":"MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2511.15645","title":"FDIO: Frequency Decomposed Inertial Odometry","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2512.04314","title":"DisentangleFormer: Spatial-Channel Decoupling for Multi-Channel Vision","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.08190","title":"Human-inspired Global-to-Parallel Multi-scale Encoding for Lightweight Vision Models","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.18326","title":"Cognitive Fusion of ZC Sequences and Time-Frequency Images for Out-of-Distribution Detection of Drone Signals","created":"2026-01-26","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":"2602.10818","title":"Resource-Efficient RGB-Only Action Recognition for Edge Deployment","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.02430","title":"A Unified Revisit of Temperature in Classification-Based Knowledge Distillation","created":"2026-03-02","cited_by_count":0,"area":"distill"},{"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":"2604.09648","title":"TRACE: Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.01667","title":"Deep neural networks with Fisher vector encoding for medical image classification","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.05590","title":"Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensing","created":"2026-05-07","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":"2605.11563","title":"TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.24391","title":"MX-SAFE: Versatile Inference- and Training-Proof Microscaling Format with On-the-Fly Exponent and Mantissa Bit Allocation","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.19195","title":"Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.00124","title":"Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.01984","title":"Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.16298","title":"Revisiting Shape and Texture Reliance with Category-Separability-Calibrated Suppression","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.16555","title":"Mitigating Compiler Fusion-Induced Power Bursts in Mobile NPU Inference as the Battery Depletes","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.26238","title":"Lightweight Image Classification of Raptor Species for Edge Devices: Rare-Species Dataset Expansion via Video Frame Extraction, Knowledge Distillation, and TensorRT Deployment","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.06252","title":"Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.22110","title":"How Weight Encoding Affects Language Model Placement and Performance on the Apple Neural Engine","created":"2026-08-22","cited_by_count":0,"area":"inference"},{"id":"2608.25539","title":"CropCop: An Auditable 120-Class Plant-Health Model from Benchmark Reconstruction to a Quantised Runtime Artifact","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.02689","title":"GaLe: memory-efficient Global Approximate and Local Exact features","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.03569","title":"Occlusion-Robust Multimodal Emotion Recognition in VR via Fusion of Facial Images and EMG","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07600","title":"BarkNet-Lite: A Lightweight Texture and Colour Network with the BarkBD Benchmark for Bark-Based Tree Species Recognition in Bangladesh","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.10469","title":"AgroVisNet: A lightweight Convolutional Network and the BD-PlantDX Expert-Validated Benchmark for Radish, Potato and Pointed Gourd Disease Classification","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.14247","title":"What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures with On-Device Measurements","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.21624","title":"Learned Parametric Emotion Editing: Real-Time Affective Filtering for On-Device Social Media Video","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.23017","title":"Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.34942","title":"Resolution as a First-Class Decision: Task-Conditioned Routing for Efficient Multimodal Large Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2610.04147","title":"You May Be Running the Wrong Inception Crop","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}