Related papers: Pic2Word: Mapping Pictures to Words for Zero-shot …

There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a…

In order to retrieve unlabeled images by textual queries, cross-media similarity computation is a key ingredient. Although novel methods are continuously introduced, little has been done to evaluate these methods together with large-scale…

Hash coding has been widely used in approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate…

Zero-shot sketch-based image retrieval (ZS-SBIR) is a specific cross-modal retrieval task for searching natural images given free-hand sketches under the zero-shot scenario. Most existing methods solve this problem by simultaneously…

Lesion images are frequently taken in open-set settings. Because of this, the image data generated is extremely varied in nature.It is difficult for a convolutional neural network to find proper features and generalise well, as a result…

Composed Image Retrieval (CIR) is a flexible image retrieval paradigm that enables users to accurately locate the target image through a multimodal query composed of a reference image and modification text. Although this task has…

Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by transferring structural knowledge from the semantic…

Contrastive Language-Image Pre-training (CLIP) has shown powerful zero-shot learning performance. Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'. Most existing…

Referring image segmentation (RIS) aims to find a segmentation mask given a referring expression grounded to a region of the input image. Collecting labelled datasets for this task, however, is notoriously costly and labor-intensive. To…

The problem of organizing and finding images in a user's directory has become increasingly challenging due to the rapid growth in the number of images captured on personal devices. This paper presents a solution that utilizes zero shot…

The practical value of existing supervised sketch-based image retrieval (SBIR) algorithms is largely limited by the requirement for intensive data collection and labeling. In this paper, we present the first attempt at unsupervised SBIR to…

There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a…

Sketch-based image retrieval (SBIR) relies on free-hand sketches to retrieve natural photos within the same class. However, its practical application is limited by its inability to retrieve classes absent from the training set. To address…

Zero-shot image recognition (ZSIR) aims to recognize and reason in unseen domains by learning generalized knowledge from limited data in the seen domain. The gist of ZSIR is constructing a well-aligned mapping between the input visual space…

Zero-shot Image Captioning (ZIC) increasingly utilizes synthetic datasets generated by text-to-image (T2I) models to mitigate the need for costly manual annotation. However, these T2I models often produce images that exhibit semantic…

Composed Image Retrieval (CIR) retrieves target images using a reference image paired with modification text. Despite rapid advances, all existing methods and datasets operate at the image level -- a single reference image plus modification…

Multi-label classification is an essential task utilized in a wide variety of real-world applications. Multi-label zero-shot learning is a method for classifying images into multiple unseen categories for which no training data is…

This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text. We show that a strong vision-language model provides sufficient…

Contrastive losses yield state-of-the-art performance for person re-identification, face verification and few shot learning. They have recently outperformed the cross-entropy loss on classification at the ImageNet scale and outperformed all…

Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample,…