{"total":33,"rows":[{"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":"2405.06849","title":"GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2504.08710","title":"Hypergraph Vision Transformers: Images are More than Nodes, More than Edges","created":"2025-04-11","cited_by_count":16,"area":null},{"id":"2406.05850","title":"Scaling Graph Convolutions for Mobile Vision","created":"2024-06-09","cited_by_count":9,"area":null},{"id":"2410.00807","title":"WiGNet: Windowed Vision Graph Neural Network","created":"2024-10-01","cited_by_count":8,"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":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2311.14775","title":"VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG","created":"2023-11-24","cited_by_count":5,"area":null},{"id":"2406.10600","title":"SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data","created":"2024-06-15","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":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","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":"2504.02440","title":"HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2505.04121","title":"Vision Graph Prompting via Semantic Low-Rank Decomposition","created":"2025-05-07","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":"2504.19682","title":"Explaining Vision GNNs: A Semantic and Visual Analysis of Graph-based Image Classification","created":"2025-04-28","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":"2509.25570","title":"AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.13740","title":"Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2403.09901","title":"Robust Subgraph Learning by Monitoring Early Training Representations","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2411.09838","title":"OneNet: A Channel-Wise 1D Convolutional U-Net","created":"2024-11-14","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":"2503.08321","title":"i-WiViG: Interpretable Window Vision GNN","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2505.22087","title":"Cognitively-Inspired Emergent Communication via Knowledge Graphs for Assisting the Visually Impaired","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2509.18840","title":"ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2512.21916","title":"Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition","created":"2025-12-26","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":"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":"2604.21290","title":"GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.22383","title":"Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2609.32362","title":"StegGNN: Learning Graphical Representation for Image Steganography","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}