{"total":12,"rows":[{"id":"2409.17978","title":"HydraViT: Stacking Heads for a Scalable ViT","created":"2024-09-26","cited_by_count":11,"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":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2504.17721","title":"Conformal Segmentation in Industrial Surface Defect Detection with Statistical Guarantees","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2512.18247","title":"Towards Ancient Plant Seed Classification: A Benchmark Dataset and Baseline Model","created":"2025-12-20","cited_by_count":2,"area":null},{"id":"2411.00838","title":"Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment","created":"2024-10-29","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":"2508.01385","title":"Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2509.13210","title":"Vi-SAFE: A Spatial-Temporal Framework for Efficient Violence Detection in Public Surveillance","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.20284","title":"Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition","created":"2025-10-23","cited_by_count":0,"area":null},{"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":"2602.05262","title":"ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network","created":"2026-02-05","cited_by_count":0,"area":null}],"next_cursor":null}