Related papers: Transformers and CNNs both Beat Humans on SBIR

Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules. To address this limitation, Linformer and Informer are proposed to reduce the quadratic…

While foundation models have revolutionised computer vision, their effectiveness for sketch understanding remains limited by the unique challenges of abstract, sparse visual inputs. Through systematic analysis, we uncover two fundamental…

Content-based image retrieval (CBIR) systems have emerged as crucial tools in the field of computer vision, allowing for image search based on visual content rather than relying solely on metadata. This survey paper presents a comprehensive…

The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so-called query image. To bridge the semantic…

One tough problem of image inpainting is to restore complex structures in the corrupted regions. It motivates interactive image inpainting which leverages additional hints, e.g., sketches, to assist the inpainting process. Sketch is simple…

In this paper, we propose a novel abstraction-aware sketch-based image retrieval framework capable of handling sketch abstraction at varied levels. Prior works had mainly focused on tackling sub-factors such as drawing style and order, we…

Understanding geometric concepts, such as distance and shape, is essential for understanding the real world and also for many vision tasks. To incorporate such information into a visual representation of a scene, we propose learning to…

We propose a new operator-sketching paradigm for designing efficient iterative data-driven reconstruction (IDR) schemes, e.g. Plug-and-Play algorithms and deep unrolling networks. These IDR schemes are currently the state-of-the-art…

Single Image Super-Resolution (SISR) reconstructs high-resolution images from low-resolution inputs, enhancing image details. While Vision Transformer (ViT)-based models improve SISR by capturing long-range dependencies, they suffer from…

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these methods with SMIRK…

Sketching is a powerful tool for creating abstract images that are sparse but meaningful. Sketch understanding poses fundamental challenges for general-purpose vision algorithms because it requires robustness to the sparsity of sketches…

With the involvement of artificial intelligence (AI), sketches can be automatically generated under certain topics. Even though breakthroughs have been made in previous studies in this area, a relatively high proportion of the generated…

Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and…

In this paper, we tackle for the first time, the problem of self-supervised representation learning for free-hand sketches. This importantly addresses a common problem faced by the sketch community -- that annotated supervisory data are…

Sketch-based 3D shape retrieval (SBSR) aims to retrieve 3D shapes that are consistent with the category of the input hand-drawn sketch. The core challenge of this task lies in two aspects: existing methods typically employ simplified…

The performance of CBIR algorithms is usually measured on an isolated workstation. In a real-world environment the algorithms would only constitute a minor component among the many interacting components. The Internet dramati-cally changes…

Proliferation of touch-based devices has made sketch-based image retrieval practical. While many methods exist for sketch-based object detection/image retrieval on small datasets, relatively less work has been done on large (web)-scale…

Contextual batched bandit (CBB) is a setting where a batch of rewards is observed from the environment at the end of each episode, but the rewards of the non-executed actions are unobserved, resulting in partial-information feedback.…

This paper, for the first time, explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR). We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap…

Resolution of the complex problem of image retrieval for diagram images has yet to be reached. Deep learning methods continue to excel in the fields of object detection and image classification applied to natural imagery. However, the…