Related papers: Visual Information Extraction in the Wild: Practic…
The inherent ambiguity in defining visual concepts poses significant challenges for modern generative models, such as the diffusion-based Text-to-Image (T2I) models, in accurately learning concepts from a single image. Existing methods lack…
The goal of a classification model is to assign the correct labels to data. In most cases, this data is not fully described by the given set of labels. Often a rich set of meaningful concepts exist in the domain that can much more precisely…
We introduce RealKIE, a benchmark of five challenging datasets aimed at advancing key information extraction methods, with an emphasis on enterprise applications. The datasets include a diverse range of documents including SEC S1 Filings,…
Variational Convertor-Encoder (VCE) converts an image to various styles; we present this novel architecture for the problem of one-shot generalization and its transfer to new tasks not seen before without additional training. We also…
This paper presents variable bitrate lossy image compression using a VAE-based neural network. An adaptable image quality adjustment strategy is proposed. The key innovation involves adeptly adjusting the input scale exclusively during the…
This paper revisits visual representation in knowledge-based visual question answering (VQA) and demonstrates that using regional information in a better way can significantly improve the performance. While visual representation is…
Monocular novel-view synthesis has long required multi-view image pairs for supervision, limiting training data scale and diversity. We argue it is not necessary: one view is enough. We present OVIE, trained entirely on unpaired internet…
Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain…
Estimating eye-gaze from images alone is a challenging task, in large parts due to un-observable person-specific factors. Achieving high accuracy typically requires labeled data from test users which may not be attainable in real…
Open Information Extraction (OpenIE) aims to extract structured relational tuples (subject, relation, object) from sentences and plays critical roles for many downstream NLP applications. Existing solutions perform extraction at sentence…
Visually Rich Document Understanding (VRDU) has emerged as a critical field in document intelligence, enabling automated extraction of key information from complex documents across domains such as medical, financial, and educational…
In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) methods primarily rely on Optical Character Recognition (OCR),…
Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as…
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general…
Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on the data they are fed with and can…
Information extraction (IE) aims to produce structured information from an input text, e.g., Named Entity Recognition and Relation Extraction. Various attempts have been proposed for IE via feature engineering or deep learning. However,…
The task of Composed Image Retrieval (CoIR) involves queries that combine image and text modalities, allowing users to express their intent more effectively. However, current CoIR datasets are orders of magnitude smaller compared to other…
Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the semantics of the visual world and natural language. Supervised methods working for vision-language…
Legal practitioners often face a vast amount of documents. Lawyers, for instance, search for appropriate precedents favorable to their clients, while the number of legal precedents is ever-growing. Although legal search engines can assist…
In real-world traffic surveillance, vehicle images captured under adverse weather, poor lighting, or high-speed motion often suffer from severe noise and blur. Such degradations significantly reduce the accuracy of license plate recognition…