English
Related papers

Related papers: Zero-shot Task Transfer for Invoice Extraction via…

200 papers

Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts. Existing approaches, such as table filling and pairwise scoring, have shown impressive performance on…

Computation and Language · Computer Science 2021-07-01 Liliang Ren , Chenkai Sun , Heng Ji , Julia Hockenmaier

In this paper, we cast Legal Judgment Prediction on European Court of Human Rights cases into an article-aware classification task, where the case outcome is classified from a combined input of case facts and convention articles. This…

Computation and Language · Computer Science 2023-02-14 T. Y. S. S Santosh , Oana Ichim , Matthias Grabmair

Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). However, current VQA benchmarks overlook scenarios with visually…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Jianing An , Luyang Jiang , Jie Luo , Wenjun Wu , Lei Huang

Motivated by the superior performance of image diffusion models, more and more researchers strive to extend these models to the text-based video editing task. Nevertheless, current video editing tasks mainly suffer from the dilemma between…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Yutao Chen , Xingning Dong , Tian Gan , Chunluan Zhou , Ming Yang , Qingpei Guo

Invoices and receipts submitted by employees are visually rich documents (VRDs) with textual, visual and layout information. To protect against the risk of fraud and abuse, it is crucial for organizations to efficiently extract desired…

Computation and Language · Computer Science 2024-11-26 Aniket Bhattacharyya , Anurag Tripathi

Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes from support set…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Xinyue Liu , Yunlong Gao , Linlin Zong , Bo Xu

Information Extraction (IE) from text refers to the task of extracting structured knowledge from unstructured text. The task typically consists of a series of sub-tasks such as Named Entity Recognition and Relation Extraction. Sourcing…

Computation and Language · Computer Science 2022-04-12 Yannis Papanikolaou , Marlene Staib , Justin Grace , Francine Bennett

Domain adaptation has been vastly investigated in computer vision but still requires access to target images at train time, which might be intractable in some uncommon conditions. In this paper, we propose the task of `Prompt-driven…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Mohammad Fahes , Tuan-Hung Vu , Andrei Bursuc , Patrick Pérez , Raoul de Charette

In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task of Scene Text Visual Question Answering (STVQA) in which…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Emanuele Vivoli , Ali Furkan Biten , Andres Mafla , Dimosthenis Karatzas , Lluis Gomez

In many documents, such as semi-structured webpages, textual semantics are augmented with additional information conveyed using visual elements including layout, font size, and color. Prior work on information extraction from…

Computation and Language · Computer Science 2020-05-15 Colin Lockard , Prashant Shiralkar , Xin Luna Dong , Hannaneh Hajishirzi

Unsupervised domain adaptation (UDA) tries to overcome the tedious work of labeling data by leveraging a labeled source dataset and transferring its knowledge to a similar but different target dataset. Meanwhile, current vision-language…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Thomas Westfechtel , Dexuan Zhang , Tatsuya Harada

Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) a fine-grained disentanglement of complex visual scene and textual context, and (ii) a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Zeyu Han , Fangrui Zhu , Qianru Lao , Huaizu Jiang

A fundamental challenge of shared autonomy is to use high-DoF robots to assist, rather than hinder, humans by first inferring user intent and then empowering the user to achieve their intent. Although successful, prior methods either rely…

Robotics · Computer Science 2025-01-16 Atharv Belsare , Zohre Karimi , Connor Mattson , Daniel S. Brown

Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems.…

Computation and Language · Computer Science 2021-01-19 A. B. Siddique , Fuad Jamour , Vagelis Hristidis

Image-to-image translation is a fundamental task in computer vision. It transforms images from one domain to images in another domain so that they have particular domain-specific characteristics. Most prior works train a generative model to…

Computer Vision and Pattern Recognition · Computer Science 2023-02-24 Sihan Xu , Zelong Jiang , Ruisi Liu , Kaikai Yang , Zhijie Huang

Foundation models have advanced computer vision by enabling strong performance across diverse tasks through large-scale pretraining and supervised fine-tuning. However, they may underperform in domains with distribution shifts and scarce…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Jesimon Barreto , Carlos Caetano , André Araujo , William Robson Schwartz

Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts. Common IE solutions, including Relation Extraction (RE) and open IE systems, can hardly handle cross-sentence tuples, and are…

Information Retrieval · Computer Science 2019-01-29 Lin Qiu , Hao Zhou , Yanru Qu , Weinan Zhang , Suoheng Li , Shu Rong , Dongyu Ru , Lihua Qian , Kewei Tu , Yong Yu

Most of the existing algorithms for zero-shot classification problems typically rely on the attribute-based semantic relations among categories to realize the classification of novel categories without observing any of their instances.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Yu-Hsuan Li , Tzu-Yin Chao , Ching-Chun Huang , Pin-Yu Chen , Wei-Chen Chiu

Visual Question Answering (VQA) is a novel problem domain where multi-modal inputs must be processed in order to solve the task given in the form of a natural language. As the solutions inherently require to combine visual and natural…

Computer Vision and Pattern Recognition · Computer Science 2018-01-31 Mikyas T. Desta , Larry Chen , Tomasz Kornuta

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…

Computation and Language · Computer Science 2023-05-23 Ping Yang , Junyu Lu , Ruyi Gan , Junjie Wang , Yuxiang Zhang , Jiaxing Zhang , Pingjian Zhang