2018/11/08 by Mubariz Zaffar, Shoaib Ehsan, Zaffar, Mubariz +5
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Retrieval and Classification Techniques #Multimodal Machine Learning Applications #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.1811.03529
openalex publication_date 2018/11/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper presents a cognition-inspired agnostic framework for building a\nmap for Visual Place Recognition. This framework draws inspiration from\nhuman-memorability, utilizes the traditional image entropy concept and computes\nthe static content in an image; thereby presenting a tri-folded criterion to\nassess the 'memorability' of an image for visual place recognition. A dataset\nnamely 'ESSEX3IN1' is created, composed of highly confusing images from indoor,\noutdoor and natural scenes for analysis. When used in conjunction with\nstate-of-the-art visual place recognition methods, the proposed framework\nprovides significant performance boost to these techniques, as evidenced by\nresults on ESSEX3IN1 and other public datasets.\n