Related papers: Rerouting Connection: Hybrid Computer Vision Analy…
In this paper, we propose a new text recognition model based on measuring the visual similarity of text and predicting the content of unlabeled texts. First a Siamese convolutional network is trained with deep supervision on a labeled…
This study presents a multi-modal multi-granularity tokenizer specifically designed for analyzing ancient Chinese scripts, focusing on the Chu bamboo slip (CBS) script used during the Spring and Autumn and Warring States period (771-256…
We propose a novel architecture that learns an end-to-end mapping function to improve the spatial resolution of the input natural images. The model is unique in forming a nonlinear combination of three traditional interpolation techniques…
Inspired by the human visual system, which operates on two parallel yet interactive streams for contextual and spatial understanding, this article presents Two Interactive Streams (TwInS), a novel bio-inspired joint learning framework…
Purpose: Deformable Image Registration (DIR) can benefit from additional guidance using corresponding landmarks in the images. However, the benefits thereof are largely understudied, especially due to the lack of automatic landmark…
Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured across long-term visual domain variations, such as different…
Machine translation between many languages at once is highly challenging, since training with ground truth requires supervision between all language pairs, which is difficult to obtain. Our key insight is that, while languages may vary…
Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver…
Bibliographic coupling (BC) and co-citation (CC) are the two most common citation-based coupling measures of similarity between scientific items. One can interpret these measures as second-neighbor relations distinguished by the direction…
Dense visual correspondence plays a vital role in robotic perception. This work focuses on establishing the dense correspondence between a pair of images that captures dynamic scenes undergoing substantial transformations. We introduce…
This research investigates biases in text-to-image (TTI) models for the Indic languages widely spoken across India. It evaluates and compares the generative performance and cultural relevance of leading TTI models in these languages against…
State-of-the-art approaches for the semantic labeling of LiDAR point clouds heavily rely on the use of deep Convolutional Neural Networks (CNNs). However, transferring network architectures across different LiDAR sensor types represents a…
Tibetan is a low-resource language. In order to alleviate the shortage of parallel corpus between Tibetan and Chinese, this paper uses two monolingual corpora and a small number of seed dictionaries to learn the semi-supervised method with…
Modern media data such as 360 videos and light field (LF) images are typically captured in much higher dimensions than the observers' visual displays. To efficiently browse high-dimensional media over bandwidth-constrained networks, a…
In many medical imaging tasks, convolutional neural networks (CNNs) efficiently extract local features hierarchically. More recently, vision transformers (ViTs) have gained popularity, using self-attention mechanisms to capture global…
Archaeology has long faced fundamental issues of sampling and scalar representation. Traditionally, the local-to-regional-scale views of settlement patterns are produced through systematic pedestrian surveys. Recently, systematic manual…
This paper discusses some topics related to the latest trends in the field of evolutionary approaches to iris recognition. It presents the results of an exploratory experimental simulation whose goal was to analyze the possibility of…
Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable image searches. The mainstream Zero-Shot (ZS) CIR methods bypass the need for expensive training CIR…
The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition. For instance, measured reaction time can indicate whether a visual…
Modern feedforward convolutional neural networks (CNNs) can now solve some computer vision tasks at super-human levels. However, these networks only roughly mimic human visual perception. One difference from human vision is that they do not…