Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.
About 3,419 papers for “interactive annotation”
J. Vendrig, Marcel Worring · 2003
Effectively labelingthe visual content ofmovies is essentialfor annotation. Wepresent theinteractive andadaptive i-Notationsystem, whichdescribes actors’names, automaticallyprocessesmultimodalinformation sources,and deals withavailable sources’varying quality. Itprovides the basisfor intelligentinteraction anddemonstratessignificantimprovements inannotationefficiency.
Cited by 0
Miguel A. Serrano, Jesús Gracía, Miguel Á. Patricio et al. · Advances in intelligent and soft computing · 2010
Cited by 10Open access
David G. Lebow, Dale W. Liek, Hope J. Hartman · Inquiry Critical Thinking Across the Disciplines · 2003
Cited by 0
Trung-Nghia Le, Tam Nguyen, Quoc-Cuong Tran et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2021
In this paper, we introduce a practical system for interactive video object mask annotation, which can support multiple back-end methods. To demonstrate the generalization of our system, we introduce a novel approach for video object annotation. Our proposed system takes scribbles at a chosen key-frame from the end-users via a user-friendly interface and produces masks of corresponding objects at the key-frame via the Control-Point-based Scribbles-to-Mask (CPSM) module. The object masks at the key-frame are then propagated to other frames and refined through the Multi-Referenced Guided Segmentation (MRGS) module. Last but not least, the user can correct wrong segmentation at some frames, and the corrected mask is continuously propagated to other frames in the video via the MRGS to produce the object masks at all video frames.
Cited by 3Open access
Fabian Sperrle, Rita Sevastjanova, Rebecca Kehlbeck et al. · arXiv (Cornell University) · 2019
Argumentation Mining addresses the challenging tasks of identifying boundaries of argumentative text fragments and extracting their relationships. Fully automated solutions do not reach satisfactory accuracy due to their insufficient incorporation of semantics and domain knowledge. Therefore, experts currently rely on time-consuming manual annotations. In this paper, we present a visual analytics system that augments the manual annotation process by automatically suggesting which text fragments to annotate next. The accuracy of those suggestions is improved over time by incorporating linguistic knowledge and language modeling to learn a measure of argument similarity from user interactions. Based on a long-term collaboration with domain experts, we identify and model five high-level analysis tasks. We enable close reading and note-taking, annotation of arguments, argument reconstruction, extraction of argument relations, and exploration of argument graphs. To avoid context switches, we transition between all views through seamless morphing, visually anchoring all text- and graph-based layers. We evaluate our system with a two-stage expert user study based on a corpus of presidential debates. The results show that experts prefer our system over existing solutions due to the speedup provided by the automatic suggestions and the tight integration between text and graph views.
Cited by 2Open access
Daniel Kaneider, Thomas Seifried, Michael Haller · 2013
Situation maps play an important role in planning and decision making in emergency response centers. Important information such as operating units or hazards is usually shown on these maps. Arranging the huge amount of in-formation can be challenging for operators, as this information should always be visible while not occluding im-portant regions of the underlying geographic map. As large interactive whiteboards are increasingly replacing tradition-al analog maps, new ways to assist with arranging information can be provided. In this paper, we present a new approach for placing annotations automatically on top of a map. For finding the optimal placement, our metrics are based on geographic features, on the users' sketched input, and on the annotations geometry itself. Moreover, we also added additional features to minimize occlusions for multiple annotations. First results were highly promising and showed that our approach improves input performance while keeping an optimal view of the map.
Cited by 5
Ryuichiro Higashinaka, Katashi Nagao · 2002
We propose a method "Interactive Paraphrasing" which enables users to interactively paraphrase words in a document by their definitions, making use of syntactic annotation and word sense annotation. Syntactic annotation is used for managing smooth integration of word sense definitions into the original document, and word sense annotation for retrieving the correct word sense definition for a word in a document. In this way, documents can be paraphrased so that they fit into the original context, preserving the semantics and improving the readability at the same time. No extra layer (window) is necessary for showing the word sense definition as in conventional methods, and other natural language processing techniques such as summarization, translation, and voice synthesis can be easily applied to the results.
Cited by 3Open access
Effectively Labeling, Jeroen Vendrig · 2010
the visual content of movies is essential for annotation. We present the interactive and adaptive i-Notation system, which describes actors’ names, automatically processes multimodal information sources, and deals with available sources’ varying quality. It provides the basis for intelligent interaction and demonstrates significant improvements in annotation efficiency.
Cited by 0
Zdravko Marinov · Repository KITopen (Karlsruhe Institute of Technology) · 2026
Die medizinische Bildsegmentierung hat sich in den letzten Jahren rasant weiterentwickelt, und viele Modelle erreichen inzwischen eine dem Menschen vergleichbare Leistungsfähigkeit auf zahlreichen Benchmarks. Dennoch bleibt die Expertise von Fachpersonen unverzichtbar, da unvollständige oder fehlerhafte Vorhersagen unmittelbaren Einfluss auf Diagnose und Therapie haben können. Interaktive Segmentierung begegnet dieser Herausforderung, indem sie menschliches Feedback in Modelle integriert und es Nutzerinnen ermöglicht, Vorhersagen iterativ über menschliche Interaktionen wie Klicks zu verfeinern. So können Expertinnen Modelle gezielt zu präzisen Ergebnissen leiten und komplexe Daten – etwa 3D-Volumina – mit wenigen Interaktionen statt durch aufwendige voxelweise Annotationen effizient annotieren. Trotz dieses Potenzials ist das Forschungsfeld fragmentiert: Es fehlen klare Definitionen, standardisierte Evaluationsverfahren, realistische Interaktionssimulationen und einheitliche Benchmarks. Diese Dissertation widmet sich diesen zentralen Herausforderungen und liefert sowohl praktische Lösungen als auch theoretische Grundlagen, die bisher weitgehend gefehlt haben. Im ersten Teil der Dissertation untersuchen wir drei zentrale Komponenten interaktiver Modelle und formulieren Best Practices, die für jedes Modell anwendbar sind: (1) die Repräsentation menschlicher Interaktionen; (2) die realistische Simulation der Interaktionen medizinischer Annotator*innen; (3) sowie die Effizienz interaktiver Modelle. Wir geben formale Definitionen für die Interaktionsrepräsentation („guidance signal“) und die Interaktionssimulation („robot user“) und entwickeln einen theoretischen Rahmen, um interaktive Modelle systematisch mit unserer Terminologie zu beschreiben. Aufbauend auf diesen theoretischen Grundlagen führen wir im zweiten Teil der Dissertation eine systematische Analyse von 121 existierenden Methoden der interaktiven Segmentierung durch und entwickeln eine Taxonomie, die die Methoden in klar abgegrenzte Kategorien einordnet. Mithilfe dieser Taxonomie geben wir praktische Empfehlungen zur Modellauswahl für spezifische Anwendungen und formulieren Best Practices für jede Kategorie. Unsere Analyse zeigt außerdem wesentliche Lücken im Forschungsfeld auf, darunter das Fehlen standardisierter Evaluationen, Datensätze, Baselines und Protokolle zur Interaktionssimulation. Diese Defizite haben dazu geführt, dass viele frühere Modelle isoliert evaluiert wurden – ohne Vergleich zu bestehender Arbeit. Um das Fehlen gemeinsamer Standards zu adressieren, etablieren wir eine globale Community für interaktive Segmentierung, indem wir vier internationale Wettbewerbe an mehreren Standorten mitorganisieren, die über 200 Einreichungen anziehen. Diese Initiativen ermöglichen eine gemeinschaftsweite Diskussion zentraler Forschungslücken und schaffen die Grundlage für faire und standardisierte Vergleiche interaktiver Ansätze. Zudem erstellen wir ein groß angelegtes, multimodales Datenset aus 166 offenen Datensätzen über neun Bildgebungsmodalitäten, ergänzt durch standardisierte Protokolle für Interaktionssimulation und Evaluation, sodass transparente und reproduzierbare Benchmarks in jedem Bereich der medizinischen Bildgebung möglich werden. Diese Dissertation definiert die Grundlagen der interaktiven medizinischen Bildsegmentierung neu – basierend auf drei Säulen: theoretischen Beiträgen, praktischen Empfehlungen und Community-getriebenen Benchmarks. Diese Grundlagen schaffen die notwendige Struktur für Fortschritt und zeigen, dass Weiterentwicklung von Zusammenarbeit, der Etablierung von Best Practices und der Identifikation zentraler Forschungslücken abhängt, um das Feld in Richtung klinisch verlässlicher und annotierungseffizienter interaktiver Modelle voranzubringen.
Cited by 0Open access
Jan Wijffels · 2021
Annotate text with entities and the relations between them. Annotate areas of interest in images with your labels. Providing 'htmlwidgets' bindings to the 'recogito' <<a href="https://github.com/recogito/recogito-js" target="_top">https://github.com/recogito/recogito-js</a>> and 'annotorious' <<a href="https://github.com/recogito/annotorious" target="_top">https://github.com/recogito/annotorious</a>> libraries.
Cited by 0Open access
Association for Computational Linguistics 2024, Huang, Chen, Ilievski, Ilija et al. · Underline Science Inc. · 2024
Human annotation is a time-consuming task that requires a significant amount of effort. To address this issue, interactive data annotation utilizes an annotation model to provide suggestions for humans to approve or correct. However, annotation models trained with limited labeled data are prone to generating incorrect suggestions, leading to extra human correction effort. To tackle this challenge, we propose Araida, an analogical reasoning-based approach that enhances automatic annotation accuracy in the interactive data annotation setting and reduces the need for human corrections. Araida involves an error-aware integration strategy that dynamically coordinates an annotation model and a k-nearest neighbors (KNN) model, giving more importance to KNN's predictions when predictions from the annotation model are deemed inaccurate. Empirical studies demonstrate that Araida is adaptable to different annotation tasks and models. On average, it reduces human correction labor by 11.02% compared to vanilla interactive data annotation methods.
Cited by 0Open access
Heather Richter Lipford, Tyler Thomas, Bill Chu et al. · 2014
Security vulnerabilities are commonly caused by security bugs introduced by developers during code construction. Static analysis tools can detect such vulnerabilities, yet are often not utilized by developers, leaving them out of the security loop. We are investigating interactive static analysis, to assist developers in detecting and mitigating security vulnerabilities during code construction. We propose interactive code annotation as a technique to gather security-related decisions from developers to aid in vulnerability detection. In this paper, we discuss the lessons we have learned in a technical and user evaluation of our current prototype, and the resulting design of our code annotation interface. The design decisions we present can help to inform the design of other annotation and security tools.
Cited by 4
Timo Götzelmann, Katrin Hartmann, Thomas Strothotte · 2006
Cited by 1
Matteo Antico, Danilo Avola, Paolo Bottoni et al. · 2016
Annotation of Web content is becoming a widespread activity by which users appropriate and enrich information available on the Net. MADCOW (Multimedia Annotation of Digital Content Over the Web) is a system for annotating HTML pages that provides a uniform interactive paradigm to make annotations on text, images and video. MADCOW has also recently included novel features for groups and group annotations with reference to ontological domains, but interaction with the MADCOW client is currently limited to the use of common input devices (e.g., keyboard, mouse), requiring a precise selection of the portions to be annotated. In this paper we present a sketch-based interface, which can be used to annotate not only content but also aspects relative to the presentation of the information. While interacting with a standard Web browser, users can draw free-hand geometrical shapes (e.g., circles, rectangles, closed paths) for selecting specific parts of the Web pages to be annotated. The interaction mode depends on the adopted input device. For example, users interacting with touch-screen devices (e.g., smartphones, tablets) can draw shapes with their fingers, but in principle any device able to detect sketching gestures can be supported (e.g., graphic tablets, optical pens). The paper discusses interaction aspects together with an overview of the system architecture. Finally, preliminary experimental tests and some considerations on the usability are also reported.
Cited by 3Open access
Euxhen Hasanaj, Jingtao Wang, Arjun Sarathi et al. · bioRxiv (Cold Spring Harbor Laboratory) · 2021
Abstract Several recent technologies and platforms enable the profiling of various molecular signals at the single-cell level. A key question for all studies using such data is the assignment of cell types. To improve the ability to correctly assign cell types in single and multi-omics sequencing and imaging single-cell studies, we developed Cellar. This interactive software tool supports all steps in the analysis and assignment process. We demonstrate the advantages of Cellar by using it to annotate several HuBMAP datasets from multi-omics single-cell sequencing and spatial proteomics studies. Cellar is freely available and includes several annotated reference HuBMAP datasets. Availability https://data.test.hubmapconsortium.org/app/cellar
Cited by 3Open access
Shilpa Arora, Eric Nyberg · 2009
We demonstrate that a supervised annotation learning approach using structured features derived from tokens and prior annotations performs better than a bag of words approach. We present a general graph representation for automatically deriving these features from labeled data. Automatic feature selection based on class association scores requires a large amount of labeled data and direct voting can be difficult and error-prone for structured features, even for language specialists. We show that highlighted rationales from the user can be used for indirect feature voting and same performance can be achieved with less labeled data. We present our results on two annotation learning tasks for opinion mining from product and movie reviews.
Cited by 13Open access
Tobias Isenberg, Petra Neumann, Sheelagh Carpendale et al. · 2006
We provide the capabilities to interactively create annotations for high-resolution information displays using low-resolution input. These types of annotations are important during collaborative information exploration to externalize parts of the exploration process for the collaborators. We provide the possibility of using direct touch-input with pen or finger at a low resolution to write or draw annotations. These are made available as Sticky Notes that can then be used without major costs in rendering time and screen-real-estate on a high-resolution display.
Cited by 0
Santos, André Jerónimo Martins dos · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · 2016
O aumento acelerado da literatura biomédica levou ao desenvolvimento de vários esforços para extrair e armazenar, de forma estruturada, a informação relativa aos conceitos e relações presentes nesses textos, oferecendo aos investigadores e clínicos um acesso rápido e fácil à informação. No entanto, este processo de "curadoria de conhecimento" é uma tarefa extremamente exaustiva, sendo cada vez mais comum o uso de ferramentas de anotação automática, fazendo uso de técnicas de mineração de texto. Apesar de já existirem sistemas de anotação bastante completos e que apresentam um alto desempenho, estes não são largamente usados pela comunidade biomédica, principalmente por serem complexos e apresentarem limitações ao nível de usabilidade. Por outro lado, o PDF tornou-se nos últimos anos num dos formatos mais populares para publicar e partilhar documentos visto poder ser apresentado exatamente da mesma maneira independentemente do sistema ou plataforma em que é acedido. A maioria das ferramentas de anotação foram principalmente desenhadas para extrair informação de texto livre, contudo hoje em dia uma grande parte da literatura biomédica é publicada e distribuída em PDF, e portanto a extração de informação de documentos PDF deve ser um ponto de foco para a comunidade de mineração de texto biomédico. O objetivo do trabalho descrito nesta dissertação foi a extensão da framework Neji, permitindo o processamento de documentos em formato PDF, e a integração dessas funcionalidades na plataforma Egas, permitindo que um utilizador possa visualizar e anotar, simultaneamente, o artigo original no formato PDF e o texto extraído deste. Os sistemas desenvolvidos apresentam bons resultados de desempenho, tanto em termos de velocidade de processamento como de representação da informação, o que também contribui para uma melhor experiência de utilizador. Além disso, apresentam várias vantagens para a comunidade de mineração de texto e curadores, permitindo a anotação direta de artigos no formato PDF e simplificando o uso e configuração destes sistemas de anotação por parte de investigadores.
Cited by 0Open access
Pick, Sebastian · RWTH Publications (RWTH Aachen) · 2019
Virtual Reality (VR) offers the unique possibility to explore data sets in a highly immersive and interactive fashion. A key aspect of this exploration process is the acquisition of insights and findings concerning the involved data. In this context, it becomes the task of so-called annotation systems to enable users to preserve said findings and review them at a later time. Even though the design of VR-based annotation systems has been a research topic for many years, crucial challenges remain unresolved. Many interaction solutions focus on isolated issues and are rather limited in scope. Additionally, they usually forgo holistic workflow designs that are vital for covering all relevant annotation operations in a consistent fashion. Similarly, available annotation presentation techniques are usually inappropriate for use within immersive virtual environments (IVEs) or they perform sub-optimally. Lastly, the design of annotation systems is usually further complicated if they are to be reused in context of other usage scenarios that impose a different and varying set of requirements on them. In this thesis, I set out to address the aforementioned issues. To this end, I present an annotation framework that was specifically designed to be configurable and extensible in accordance to the changing requirements of different application scenarios. It is grounded in a specialized data model that facilitates the integration not only of required data types, which are used to describe annotations, but also techniques to capture and present them. I employ this model to develop a flexible solution to the design of holistic interaction workflows. My design approach covers all essential operations, including the creation, modification, and review of arbitrary types of annotations from within IVEs. To provide a set of ready-to-use interaction techniques to acquire annotation contents, I identify the most relevant data types and devise appropriate interaction concepts. Similarly, I present a generalized two-tier presentation strategy that facilitates the access to and review of arbitrary annotation contents. While the tier one representation provides basic access to a selection of contents in a customizable form, the tier two representation allows for access to all contents in a generalized manner. I furthermore introduce a novel automated annotation layout approach that prevents occlusions of and by annotations to maintain visual access to them and the original data. In order to determine the viability of my approaches, I cover a series of technical analyses and user studies. They are rounded off by a presentation of concrete application examples that utilize varying subsets of techniques to demonstrate the usefulness and flexibility of my framework.
Cited by 0Open access
Chen Huang, Yiping Jin, Ilija Ilievski et al. · 2024
Human annotation is a time-consuming task that requires a significant amount of effort.To address this issue, interactive data annotation utilizes an annotation model to provide suggestions for humans to approve or correct.However, annotation models trained with limited labeled data are prone to generating incorrect suggestions, leading to extra human correction effort.To tackle this challenge, we propose ARAIDA, an analogical reasoning-based approach that enhances automatic annotation accuracy in the interactive data annotation setting and reduces the need for human corrections.ARAIDA involves an error-aware integration strategy that dynamically coordinates an annotation model and a k-nearest neighbors (KNN) model, giving more importance to KNN's predictions when predictions from the annotation model are deemed inaccurate.Empirical studies demonstrate that ARAIDA is adaptable to different annotation tasks and models.On average, it reduces human correction labor by 11.02% compared to vanilla interactive data annotation methods.
Cited by 0Open access