{"total":145,"rows":[{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174,"area":null},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172,"area":null},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2206.10589","title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","created":"2022-06-21","cited_by_count":121,"area":null},{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"area":null},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2303.15446","title":"SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications","created":"2023-03-27","cited_by_count":66,"area":null},{"id":"2207.05501","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","created":"2022-07-12","cited_by_count":65,"area":null},{"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":"2307.08473","title":"EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation","created":"2023-07-17","cited_by_count":53,"area":null},{"id":"2210.01820","title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","created":"2022-10-04","cited_by_count":47,"area":null},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2209.15159","title":"MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features","created":"2022-09-30","cited_by_count":44,"area":null},{"id":"2301.01146","title":"Rethinking Mobile Block for Efficient Attention-based Models","created":"2023-01-03","cited_by_count":36,"area":null},{"id":"2402.19422","title":"PEM: Prototype-based Efficient MaskFormer for Image Segmentation","created":"2024-02-29","cited_by_count":36,"area":null},{"id":"2307.00395","title":"MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications","created":"2023-07-01","cited_by_count":35,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2306.11248","title":"Dynamic Perceiver for Efficient Visual Recognition","created":"2023-06-20","cited_by_count":33,"area":null},{"id":"2309.03979","title":"Separable Self and Mixed Attention Transformers for Efficient Object Tracking","created":"2023-09-07","cited_by_count":31,"area":null},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","cited_by_count":24,"area":null},{"id":"2405.06849","title":"GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2403.08997","title":"Caltech Aerial RGB-Thermal Dataset in the Wild","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2301.13156","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2309.07400","title":"HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2310.19252","title":"Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union","created":"2023-10-30","cited_by_count":17,"area":null},{"id":"2304.03369","title":"EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation","created":"2023-04-06","cited_by_count":16,"area":null},{"id":"2403.19963","title":"Efficient Modulation for Vision Networks","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2303.00521","title":"Quality-aware Pre-trained Models for Blind Image Quality Assessment","created":"2023-03-01","cited_by_count":15,"area":null},{"id":"2311.18237","title":"Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"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":"2409.17978","title":"HydraViT: Stacking Heads for a Scalable ViT","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2303.09730","title":"ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices","created":"2023-03-17","cited_by_count":10,"area":null},{"id":"2507.01182","title":"Rapid Salient Object Detection with Difference Convolutional Neural Networks","created":"2025-07-01","cited_by_count":10,"area":null},{"id":"2406.05850","title":"Scaling Graph Convolutions for Mobile Vision","created":"2024-06-09","cited_by_count":9,"area":null},{"id":"2407.08027","title":"Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images","created":"2024-07-10","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":"2403.18116","title":"QuakeSet: A Dataset and Low-Resource Models to Monitor Earthquakes through Sentinel-1","created":"2024-03-26","cited_by_count":8,"area":null},{"id":"2409.03901","title":"Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models","created":"2024-09-05","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":"2405.18021","title":"MULi-Ev: Maintaining Unperturbed LiDAR-Event Calibration","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2303.12557","title":"Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems","created":"2023-03-22","cited_by_count":6,"area":null},{"id":"2404.05196","title":"HSViT: Horizontally Scalable Vision Transformer","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2404.13648","title":"Data-independent Module-aware Pruning for Hierarchical Vision Transformers","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2406.06136","title":"A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis","created":"2024-06-10","cited_by_count":6,"area":null},{"id":"2409.11661","title":"Bridging the Domain Gap for Flight-Ready Spaceborne Vision","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2207.10025","title":"Learning from Synthetic Data: Facial Expression Classification based on Ensemble of Multi-task Networks","created":"2022-07-20","cited_by_count":5,"area":null},{"id":"2208.09815","title":"LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction","created":"2022-08-21","cited_by_count":5,"area":null},{"id":"2301.05785","title":"Efficient Activation Function Optimization through Surrogate Modeling","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2412.06262","title":"A Lightweight U-like Network Utilizing Neural Memory Ordinary Differential Equations for Slimming the Decoder","created":"2024-12-09","cited_by_count":5,"area":null},{"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":"2403.12562","title":"PePR: Performance Per Resource Unit as a Metric to Promote Small-Scale Deep Learning in Medical Image Analysis","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2404.12210","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","created":"2024-04-18","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":"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":"2503.16628","title":"MobilePlantViT: A Mobile-friendly Hybrid ViT for Generalized Plant Disease Image Classification","created":"2025-03-20","cited_by_count":4,"area":null},{"id":"2208.12257","title":"Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2210.15943","title":"Grafting Vision Transformers","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2305.11875","title":"FR-Net:A Light-weight FFT Residual Net For Gaze Estimation","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2305.19492","title":"CVSNet: A Computer Implementation for Central Visual System of The Brain","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2402.13537","title":"EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalization","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2410.13663","title":"DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2411.18855","title":"Improving Accuracy and Generalization for Efficient Visual Tracking","created":"2024-11-28","cited_by_count":3,"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":"2505.22769","title":"MAC-Gaze: Motion-Aware Continual Calibration for Mobile Gaze Tracking","created":"2025-05-28","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":"2211.06769","title":"Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2306.10875","title":"Vision Transformer with Attention Map Hallucination and FFN Compaction","created":"2023-06-19","cited_by_count":2,"area":null},{"id":"2307.09120","title":"Light-Weight Vision Transformer with Parallel Local and Global Self-Attention","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2311.01759","title":"TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2403.04200","title":"ACC-ViT : Atrous Convolution's Comeback in Vision Transformers","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2410.17661","title":"PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2412.12685","title":"SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2501.05880","title":"TakuNet: an Energy-Efficient CNN for Real-Time Inference on Embedded UAV systems in Emergency Response Scenarios","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2503.09903","title":"A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectives","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","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":"2512.13055","title":"Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2308.11421","title":"TurboViT: Generating Fast Vision Transformers via Generative Architecture Search","created":"2023-08-22","cited_by_count":1,"area":null},{"id":"2309.12424","title":"DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2406.13860","title":"Liveness Detection in Computer Vision: Transformer-based Self-Supervised Learning for Face Anti-Spoofing","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2406.14239","title":"LeYOLO, New Embedded Architecture for Object Detection","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2407.06673","title":"CTRL-F: Pairing Convolution with Transformer for Image Classification via Multi-Level Feature Cross-Attention and Representation Learning Fusion","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2407.18128","title":"Estimating Earthquake Magnitude in Sentinel-1 Imagery via Ranking","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2409.16999","title":"WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.14874","title":"Beyond Isolated Heads: Multi-Overlapped-Head Self-Attention for Vision Transformers","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2501.19255","title":"ContextFormer: Redefining Efficiency in Semantic Segmentation","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2505.05813","title":"BCE vs. CE in Deep Feature Learning","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2506.11093","title":"EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2507.15798","title":"Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models","created":"2025-07-21","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":"2508.12384","title":"ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2508.20375","title":"CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inference","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.13883","title":"EvHand-FPV: Efficient Event-Based 3D Hand Tracking from First-Person View","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2510.14661","title":"EuroMineNet: A Multitemporal Sentinel-2 Benchmark for Spatiotemporal Mining Footprint Analysis in the European Union (2015-2024)","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2605.23094","title":"Do Synthetic Brain MRIs Reliably Improve Tumour Classification? A StyleGAN2-ADA Class-Plane Augmentation Study on BRISC 2025","created":"2026-05-21","cited_by_count":1,"area":null}],"next_cursor":"100"}