In the early days, content-based image retrieval (CBIR) was studied with global features.
Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively …

The explosive increase and ubiquitous accessibility of visual data on the Web have led to
the prosperity of research activity in image search or retrieval. With the ignorance of visual …

Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned
general visual representations and broad visual concepts. In principle, the well-learned …

Visual relations, such as" person ride bike" and" bike next to car", offer a comprehensive
scene understanding of an image, and have already shown their great utility in connecting …

CLIP embeddings have demonstrated remarkable performance across a wide range of
multimodal applications. However, these high-dimensional, dense vector representations …

This paper develops a novel framework for semantic image retrieval based on the notion of
a scene graph. Our scene graphs represent objects (" man"," boat"), attributes of objects (" …

We evaluate whether features extracted from the activation of a deep convolutional network
trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re …

We propose a novel framework called Semantics-Preserving Adversarial Embedding
Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their …

It has been shown that the activations invoked by an image within the top layers of a large
convolutional neural network provide a high-level descriptor of the visual content of the …

We study the problem of object recognition for categories for which we have no training
examples, a task also called zero--data or zero-shot learning. This situation has hardly been …