{"total":58,"rows":[{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"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":"2401.16456","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","created":"2024-01-29","cited_by_count":56,"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":"2410.20389","title":"Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns","created":"2024-10-27","cited_by_count":21,"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":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","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":"2404.18952","title":"CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attention","created":"2024-04-27","cited_by_count":8,"area":null},{"id":"2504.17787","title":"The Fourth Monocular Depth Estimation Challenge","created":"2025-04-24","cited_by_count":8,"area":null},{"id":"2501.02990","title":"SurgRIPE challenge: Benchmark of Surgical Robot Instrument Pose Estimation","created":"2025-01-06","cited_by_count":7,"area":null},{"id":"2404.05196","title":"HSViT: Horizontally Scalable Vision Transformer","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2407.11306","title":"PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer","created":"2024-07-16","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":"2403.19882","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2406.08816","title":"ToSA: Token Selective Attention for Efficient Vision Transformers","created":"2024-06-13","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":"2405.20867","title":"Automatic Channel Pruning for Multi-Head Attention","created":"2024-05-31","cited_by_count":3,"area":null},{"id":"2406.09739","title":"Decoupling Forgery Semantics for Generalizable Deepfake Detection","created":"2024-06-14","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":"2511.00812","title":"LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2604.09127","title":"FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition","created":"2026-04-10","cited_by_count":3,"area":null},{"id":"2402.09156","title":"Crop and Couple: cardiac image segmentation using interlinked specialist networks","created":"2024-02-14","cited_by_count":2,"area":null},{"id":"2408.14177","title":"NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training","created":"2024-08-26","cited_by_count":2,"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":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2510.14962","title":"RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2305.13399","title":"Efficient Large-Scale Visual Representation Learning And Evaluation","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2312.02095","title":"Single-sample versus case-control sampling scheme for Positive Unlabeled data: the story of two scenarios","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2410.23130","title":"Compositional Segmentation of Cardiac Images Leveraging Metadata","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2503.21782","title":"Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2410.03174","title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","created":"2024-10-04","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":"2501.14535","title":"Rethinking Encoder-Decoder Flow Through Shared Structures","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2502.17206","title":"Neural Attention: A Novel Mechanism for Enhanced Expressive Power in Transformer Models","created":"2025-02-24","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":"2503.22841","title":"GmNet: Revisiting Gating Mechanisms From A Frequency View","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2506.07112","title":"EdgeSpotter: Multi-Scale Dense Text Spotting for Industrial Panel Monitoring","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2510.00882","title":"AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification","created":"2025-10-01","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":"2511.00335","title":"Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2511.23287","title":"Transformer-Driven Triple Fusion Framework for Enhanced Multimodal Author Intent Classification in Low-Resource Bangla","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.08647","title":"C-DIRA: Computationally Efficient Dynamic ROI Routing and Domain-Invariant Adversarial Learning for Lightweight Driver Behavior Recognition","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.07975","title":"An Efficient Additive Kolmogorov-Arnold Transformer for Point-Level Maize Localization in Unmanned Aerial Vehicle Imagery","created":"2026-01-12","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":"2602.05262","title":"ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.13568","title":"ZoomSpec: A Physics-Guided Coarse-to-Fine Framework for Wideband Spectrum Sensing","created":"2026-04-15","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":"2605.08592","title":"Cross-Modal RGB-D Fusion Transformer for 6D Pose Estimation of Non-Cooperative Spacecraft with Stereo-Derived Depth","created":"2026-05-09","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":"2607.03981","title":"BanglaMemeEvidence: A Multimodal Benchmark Dataset for Explanatory Evidence Detection in Bengali Memes","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.28070","title":"CF-YOLO: Context-Aware Feature Refinement for Camouflaged Industrial Micro-Defect Detection","created":"2026-08-28","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":"2609.30989","title":"PICO: Projection-Informed Consistency Optimisation for 6DoF Surgical Tool Pose Estimation","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}