Related papers: Stacked Semantic-Guided Network for Zero-Shot Sket…
Understanding and reasoning about complex 3D environments requires structured scene representations that capture not only objects but also their semantic and spatial relationships. While recent works on 3D scene graph generation have…
Training-free zero-shot composed image retrieval models are recently gaining increasing research interest due to their generalizability and flexibility in unseen multimodal retrieval. Recent LLM-based advances focus on generating the…
Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly…
Composed image retrieval is a type of image retrieval task where the user provides a reference image as a starting point and specifies a text on how to shift from the starting point to the desired target image. However, most existing…
Zero-shot Semantic Segmentation (ZSS) aims to segment categories that are not annotated during training. While fine-tuning vision-language models has achieved promising results, these models often overfit to seen categories due to the lack…
This paper proposes a novel zero-shot composed image retrieval (CIR) method considering the query-target relationship by masked image-text pairs. The objective of CIR is to retrieve the target image using a query image and a query text.…
Recognizing freehand sketches with high arbitrariness is greatly challenging. Most existing methods either ignore the geometric characteristics or treat sketches as handwritten characters with fixed structural ordering. Consequently, they…
Sketch-based 3D shape retrieval is a challenging task due to the large domain discrepancy between sketches and 3D shapes. Since existing methods are trained and evaluated on the same categories, they cannot effectively recognize the…
We present a new embedding-based framework for zero-shot learning (ZSL). Most embedding-based methods aim to learn the correspondence between an image classifier (visual representation) and its class prototype (semantic representation) for…
Recently, automatic image caption generation has been an important focus of the work on multimodal translation task. Existing approaches can be roughly categorized into two classes, i.e., top-down and bottom-up, the former transfers the…
In most recent years, zero-shot recognition (ZSR) has gained increasing attention in machine learning and image processing fields. It aims at recognizing unseen class instances with knowledge transferred from seen classes. This is typically…
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…
Content Based Image Retrieval(CBIR) is one of the important subfield in the field of Information Retrieval. The goal of a CBIR algorithm is to retrieve semantically similar images in response to a query image submitted by the end user. CBIR…
Fully supervised semantic segmentation technologies bring a paradigm shift in scene understanding. However, the burden of expensive labeling cost remains as a challenge. To solve the cost problem, recent studies proposed language model…
In this paper, we propose a novel method to learn face sketch synthesis models by using unpaired data. Our main idea is bridging the photo domain $\mathcal{X}$ and the sketch domain $Y$ by using the line-drawing domain $\mathcal{Z}$.…
Iterative sketching and sketch-and-precondition are well-established randomized algorithms for solving large-scale, over-determined linear least-squares problems. In this paper, we introduce a new perspective that interprets Iterative…
In zero-shot image retrieval (ZSIR) task, embedding learning becomes more attractive, however, many methods follow the traditional metric learning idea and omit the problems behind zero-shot settings. In this paper, we first emphasize the…
With recent advances in image-to-image translation tasks, remarkable progress has been witnessed in generating face images from sketches. However, existing methods frequently fail to generate images with details that are semantically and…
Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Existing approaches…
In Composed Image Retrieval (CIR), a user combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text…