2023/08/29 by Yun Liao, Yide Di, Liao, Yun +13 · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #FOS: Electrical engineering #Human Pose and Action Recognition #I.4.7 #Image and Video Processing (eess.IV) #Multimodal Machine Learning Applications #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2308.15144
openalex publication_date 2023/08/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Local feature matching remains a challenging task, primarily due to difficulties in matching sparse keypoints and low-texture regions. The key to solving this problem lies in effectively and accurately integrating global and local information. To achieve this goal, we introduce an innovative local feature matching method called TKwinFormer. Our approach employs a multi-stage matching strategy to optimize the efficiency of information interaction. Furthermore, we propose a novel attention mechanism called Top K Window Attention, which facilitates global information interaction through window tokens prior to patch-level matching, resulting in improved matching accuracy. Additionally, we design an attention block to enhance attention between channels. Experimental results demonstrate that TKwinFormer outperforms state-of-the-art methods on various benchmarks. Code is available at: https://github.com/LiaoYun0x0/TKwinFormer.