Related papers: Revising FUNSD dataset for key-value detection in …

This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…

Depth perception is fundamental for robots to understand the surrounding environment. As the view of cognitive neuroscience, visual depth perception methods are divided into three categories, namely binocular, active, and pictorial. The…

Different from large-scale classification tasks, fine-grained visual classification is a challenging task due to two critical problems: 1) evident intra-class variances and subtle inter-class differences, and 2) overfitting owing to fewer…

This work explores the application of Federated Learning (FL) to Unsupervised Semantic image Segmentation (USS). Recent USS methods extract pixel-level features using frozen visual foundation models and refine them through self-supervised…

Interpretable deep learning models have received widespread attention in the field of image recognition. Due to the unique multi-instance learning of medical images and the difficulty in identifying decision-making regions, many…

Large-scale datasets have played a crucial role in the advancement of computer vision. However, they often suffer from problems such as class imbalance, noisy labels, dataset bias, or high resource costs, which can inhibit model performance…

This paper presents a neurosymbolic framework for information extraction from documents, evaluated on transactional documents. We introduce a schema-based approach that integrates symbolic validation methods to enable more effective…

Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition. SED…

Abstract--- Table detection and extraction has been studied in the context of documents like reports, where tables are clearly outlined and stand out from the document structure visually. We study this topic in a rather more challenging…

Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be…

Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for…

Extracting valuable facts or informative summaries from multi-dimensional tables, i.e. insight mining, is an important task in data analysis and business intelligence. However, ranking the importance of insights remains a challenging and…

It has long been considered a significant problem to improve the visual quality of lossy image and video compression. Recent advances in computing power together with the availability of large training data sets has increased interest in…

Intrinsic image decomposition is an important and long-standing computer vision problem. Given an input image, recovering the physical scene properties is ill-posed. Several physically motivated priors have been used to restrict the…

While there has been remarkable progress in the performance of visual recognition algorithms, the state-of-the-art models tend to be exceptionally data-hungry. Large labeled training datasets, expensive and tedious to produce, are required…

Leveraging multiple training datasets to scale up image segmentation models is beneficial for increasing robustness and semantic understanding. Individual datasets have well-defined ground truth with non-overlapping mask layouts and…

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the…

Urban facade segmentation from automatically acquired imagery, in contrast to traditional image segmentation, poses several unique challenges. 360-degree photospheres captured from vehicles are an effective way to capture a large number of…

When data is unlabelled and the target task is not known a priori, divergent search offers a strategy for learning a wide range of skills. Having such a repertoire allows a system to adapt to new, unforeseen tasks. Unlabelled image data is…

One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of…