Content-Based Image Retrieval is a well studied problem in computer vision, with retrieval problems generally divided into two groups: category-level retrieval and instance-level retrieval. Given a query image of the Sydney Harbour bridge, for instance, category-level retrieval aims to find any bridge in a given dataset of images, whilst instance-level retrieval must find the Sydney Harbour bridge to be considered a match.
It is shown that, if the adversary can only have access to the SIFT descriptors while not their coordinates, then the modest success of reconstructing the latent image can be achieved for highly-structured images (e. g., faces) and would fail in general settings.
Despite significant progress of applying deep learning methods to the field of content-based image retrieval, there has not been a software library that covers these methods in a unified manner.
The analysis of natural disasters such as floods in a timely manner often suffers from limited data due to a coarse distribution of sensors or sensor failures.
In this paper, a new feature extraction schema including the norm of low frequency components in wavelet transformation and color features in RGB and HSV domains are proposed as representative feature vector for images in database followed by appropriate similarity measure for each feature type.
An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye.
Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images.
Ranked #3 on Image Retrieval on CARS196
We propose Information-Theoretic Active Learning (ITAL), a novel batch-mode active learning method for binary classification, and apply it for acquiring meaningful user feedback in the context of content-based image retrieval.
In this paper, we present a novel feature-augmented random forest (FARF) for image super-resolution, where the conventional gradient-based features are augmented with gradient magnitudes and different feature recipes are formulated on different stages in an RF.
Ranked #32 on Image Super-Resolution on BSD100 - 4x upscaling
In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space.
Ranked #5 on Text based Person Retrieval on CUHK-PEDES
Query images presented to content-based image retrieval systems often have various different interpretations, making it difficult to identify the search objective pursued by the user.