The Experts below are selected from a list of 362811 Experts worldwide ranked by ideXlab platform
Marie-francine Moens - One of the best experts on this subject based on the ideXlab platform.
-
Learning Representations Specialized in Spatial Knowledge: Leveraging Language and Vision
Transactions of the Association for Computational Linguistics, 2018Co-Authors: Guillem Collell, Marie-francine MoensAbstract:Spatial Understanding is crucial in many real-world problems, yet little progress has been made towards building representations that capture Spatial knowledge. Here, we move one step forward in th...
-
acquiring common sense Spatial knowledge through implicit Spatial templates
arXiv: Artificial Intelligence, 2017Co-Authors: Guillem Collell, Luc Van Gool, Marie-francine MoensAbstract:Spatial Understanding is a fundamental problem with wide-reaching real-world applications. The representation of Spatial knowledge is often modeled with Spatial templates, i.e., regions of acceptability of two objects under an explicit Spatial relationship (e.g., "on", "below", etc.). In contrast with prior work that restricts Spatial templates to explicit Spatial prepositions (e.g., "glass on table"), here we extend this concept to implicit Spatial language, i.e., those relationships (generally actions) for which the Spatial arrangement of the objects is only implicitly implied (e.g., "man riding horse"). In contrast with explicit relationships, predicting Spatial arrangements from implicit Spatial language requires significant common sense Spatial Understanding. Here, we introduce the task of predicting Spatial templates for two objects under a relationship, which can be seen as a Spatial question-answering task with a (2D) continuous output ("where is the man w.r.t. a horse when the man is walking the horse?"). We present two simple neural-based models that leverage annotated images and structured text to learn this task. The good performance of these models reveals that Spatial locations are to a large extent predictable from implicit Spatial language. Crucially, the models attain similar performance in a challenging generalized setting, where the object-relation-object combinations (e.g.,"man walking dog") have never been seen before. Next, we go one step further by presenting the models with unseen objects (e.g., "dog"). In this scenario, we show that leveraging word embeddings enables the models to output accurate Spatial predictions, proving that the models acquire solid common sense Spatial knowledge allowing for such generalization.
-
structured learning for Spatial information extraction from biomedical text bacteria biotopes
BMC Bioinformatics, 2015Co-Authors: Dan Roth, Parisa Kordjamshidi, Marie-francine MoensAbstract:We aim to automatically extract species names of bacteria and their locations from webpages. This task is important for exploiting the vast amount of biological knowledge which is expressed in diverse natural language texts and putting this knowledge in databases for easy access by biologists. The task is challenging and the previous results are far below an acceptable level of performance, particularly for extraction of localization relationships. Therefore, we aim to design a new system for such extractions, using the framework of structured machine learning techniques. We design a new model for joint extraction of biomedical entities and the localization relationship. Our model is based on a Spatial role labeling (SpRL) model designed for Spatial Understanding of unrestricted text. We extend SpRL to extract discourse level Spatial relations in the biomedical domain and apply it on the BioNLP-ST 2013, BB-shared task. We highlight the main differences between general Spatial language Understanding and Spatial information extraction from the scientific text which is the focus of this work. We exploit the text’s structure and discourse level global features. Our model and the designed features substantially improve on the previous systems, achieving an absolute improvement of approximately 57 percent over F1 measure of the best previous system for this task. Our experimental results indicate that a joint learning model over all entities and relationships in a document outperforms a model which extracts entities and relationships independently. Our global learning model significantly improves the state-of-the-art results on this task and has a high potential to be adopted in other natural language processing (NLP) tasks in the biomedical domain.
Eike Schwandt - One of the best experts on this subject based on the ideXlab platform.
-
aneurysm surgery with preoperative three dimensional planning in a virtual reality environment technique and outcome analysis
World Neurosurgery, 2016Co-Authors: Ralf A Kockro, Tim Killeen, Ali Ayyad, Martin Glaser, Axel Stadie, Robert Reisch, Alf Giese, Eike SchwandtAbstract:Objective Aneurysm surgery demands precise Spatial Understanding of the vascular anatomy and its surroundings. We report on a decade of experience planning clipping procedures preoperatively in a virtual reality (VR) workstation and present outcomes with respect to mortality, morbidity, and aneurysm occlusion rate. Methods Between 2006 and 2015, the clipping of 115 intracranial aneurysms in 105 patients was preoperatively planned with the Dextroscope, a stereoscopic, patient-specific VR environment. The outcome data for all cases, planned and performed in 3 institutions, were analyzed based on clinical charts and radiologic reports. Results Eighty-five incidental, unruptured aneurysms in 77 patients were electively planned and treated surgically. Mortality was 0% and morbidity (modified Rankin Scale score >2) was 2.6%. The rate of complete aneurysm obliteration on postoperative imaging was 91.8%. In addition, 30 aneurysms were treated in 28 patients with previous subarachnoid hemorrhage. Mortality in these cases was 3.6%, morbidity (modified Rankin Scale score >2) 7.1%, and the rate of complete aneurysm clipping was 90%. Conclusions Meticulous three-dimensional surgical planning in a VR environment enhances the surgeon's Spatial Understanding of the individual vascular anatomy and allows clip preselection and positioning as well as anticipation of potential difficulties and complications. VR planning was associated, in this multi-institutional series, with excellent clinical outcomes and rates of complete aneurysm closure equivalent to benchmark cohorts.
-
aneurysm surgery with preoperative three dimensional planning in a virtual reality environment technique and outcome analysis
World Neurosurgery, 2016Co-Authors: Ralf A Kockro, Tim Killeen, Ali Ayyad, Martin Glaser, Axel Stadie, Robert Reisch, Alf Giese, Eike SchwandtAbstract:Objective Aneurysm surgery demands precise Spatial Understanding of the vascular anatomy and its surroundings. We report on a decade of experience planning clipping procedures preoperatively in a virtual reality (VR) workstation and present outcomes with respect to mortality, morbidity, and aneurysm occlusion rate. Methods Between 2006 and 2015, the clipping of 115 intracranial aneurysms in 105 patients was preoperatively planned with the Dextroscope, a stereoscopic, patient-specific VR environment. The outcome data for all cases, planned and performed in 3 institutions, were analyzed based on clinical charts and radiologic reports. Results Eighty-five incidental, unruptured aneurysms in 77 patients were electively planned and treated surgically. Mortality was 0% and morbidity (modified Rankin Scale score >2) was 2.6%. The rate of complete aneurysm obliteration on postoperative imaging was 91.8%. In addition, 30 aneurysms were treated in 28 patients with previous subarachnoid hemorrhage. Mortality in these cases was 3.6%, morbidity (modified Rankin Scale score >2) 7.1%, and the rate of complete aneurysm clipping was 90%. Conclusions Meticulous three-dimensional surgical planning in a VR environment enhances the surgeon's Spatial Understanding of the individual vascular anatomy and allows clip preselection and positioning as well as anticipation of potential difficulties and complications. VR planning was associated, in this multi-institutional series, with excellent clinical outcomes and rates of complete aneurysm closure equivalent to benchmark cohorts.
Ralf A Kockro - One of the best experts on this subject based on the ideXlab platform.
-
aneurysm surgery with preoperative three dimensional planning in a virtual reality environment technique and outcome analysis
World Neurosurgery, 2016Co-Authors: Ralf A Kockro, Tim Killeen, Ali Ayyad, Martin Glaser, Axel Stadie, Robert Reisch, Alf Giese, Eike SchwandtAbstract:Objective Aneurysm surgery demands precise Spatial Understanding of the vascular anatomy and its surroundings. We report on a decade of experience planning clipping procedures preoperatively in a virtual reality (VR) workstation and present outcomes with respect to mortality, morbidity, and aneurysm occlusion rate. Methods Between 2006 and 2015, the clipping of 115 intracranial aneurysms in 105 patients was preoperatively planned with the Dextroscope, a stereoscopic, patient-specific VR environment. The outcome data for all cases, planned and performed in 3 institutions, were analyzed based on clinical charts and radiologic reports. Results Eighty-five incidental, unruptured aneurysms in 77 patients were electively planned and treated surgically. Mortality was 0% and morbidity (modified Rankin Scale score >2) was 2.6%. The rate of complete aneurysm obliteration on postoperative imaging was 91.8%. In addition, 30 aneurysms were treated in 28 patients with previous subarachnoid hemorrhage. Mortality in these cases was 3.6%, morbidity (modified Rankin Scale score >2) 7.1%, and the rate of complete aneurysm clipping was 90%. Conclusions Meticulous three-dimensional surgical planning in a VR environment enhances the surgeon's Spatial Understanding of the individual vascular anatomy and allows clip preselection and positioning as well as anticipation of potential difficulties and complications. VR planning was associated, in this multi-institutional series, with excellent clinical outcomes and rates of complete aneurysm closure equivalent to benchmark cohorts.
-
aneurysm surgery with preoperative three dimensional planning in a virtual reality environment technique and outcome analysis
World Neurosurgery, 2016Co-Authors: Ralf A Kockro, Tim Killeen, Ali Ayyad, Martin Glaser, Axel Stadie, Robert Reisch, Alf Giese, Eike SchwandtAbstract:Objective Aneurysm surgery demands precise Spatial Understanding of the vascular anatomy and its surroundings. We report on a decade of experience planning clipping procedures preoperatively in a virtual reality (VR) workstation and present outcomes with respect to mortality, morbidity, and aneurysm occlusion rate. Methods Between 2006 and 2015, the clipping of 115 intracranial aneurysms in 105 patients was preoperatively planned with the Dextroscope, a stereoscopic, patient-specific VR environment. The outcome data for all cases, planned and performed in 3 institutions, were analyzed based on clinical charts and radiologic reports. Results Eighty-five incidental, unruptured aneurysms in 77 patients were electively planned and treated surgically. Mortality was 0% and morbidity (modified Rankin Scale score >2) was 2.6%. The rate of complete aneurysm obliteration on postoperative imaging was 91.8%. In addition, 30 aneurysms were treated in 28 patients with previous subarachnoid hemorrhage. Mortality in these cases was 3.6%, morbidity (modified Rankin Scale score >2) 7.1%, and the rate of complete aneurysm clipping was 90%. Conclusions Meticulous three-dimensional surgical planning in a VR environment enhances the surgeon's Spatial Understanding of the individual vascular anatomy and allows clip preselection and positioning as well as anticipation of potential difficulties and complications. VR planning was associated, in this multi-institutional series, with excellent clinical outcomes and rates of complete aneurysm closure equivalent to benchmark cohorts.
Guillem Collell - One of the best experts on this subject based on the ideXlab platform.
-
Learning Representations Specialized in Spatial Knowledge: Leveraging Language and Vision
Transactions of the Association for Computational Linguistics, 2018Co-Authors: Guillem Collell, Marie-francine MoensAbstract:Spatial Understanding is crucial in many real-world problems, yet little progress has been made towards building representations that capture Spatial knowledge. Here, we move one step forward in th...
-
acquiring common sense Spatial knowledge through implicit Spatial templates
arXiv: Artificial Intelligence, 2017Co-Authors: Guillem Collell, Luc Van Gool, Marie-francine MoensAbstract:Spatial Understanding is a fundamental problem with wide-reaching real-world applications. The representation of Spatial knowledge is often modeled with Spatial templates, i.e., regions of acceptability of two objects under an explicit Spatial relationship (e.g., "on", "below", etc.). In contrast with prior work that restricts Spatial templates to explicit Spatial prepositions (e.g., "glass on table"), here we extend this concept to implicit Spatial language, i.e., those relationships (generally actions) for which the Spatial arrangement of the objects is only implicitly implied (e.g., "man riding horse"). In contrast with explicit relationships, predicting Spatial arrangements from implicit Spatial language requires significant common sense Spatial Understanding. Here, we introduce the task of predicting Spatial templates for two objects under a relationship, which can be seen as a Spatial question-answering task with a (2D) continuous output ("where is the man w.r.t. a horse when the man is walking the horse?"). We present two simple neural-based models that leverage annotated images and structured text to learn this task. The good performance of these models reveals that Spatial locations are to a large extent predictable from implicit Spatial language. Crucially, the models attain similar performance in a challenging generalized setting, where the object-relation-object combinations (e.g.,"man walking dog") have never been seen before. Next, we go one step further by presenting the models with unseen objects (e.g., "dog"). In this scenario, we show that leveraging word embeddings enables the models to output accurate Spatial predictions, proving that the models acquire solid common sense Spatial knowledge allowing for such generalization.
Robert Reisch - One of the best experts on this subject based on the ideXlab platform.
-
aneurysm surgery with preoperative three dimensional planning in a virtual reality environment technique and outcome analysis
World Neurosurgery, 2016Co-Authors: Ralf A Kockro, Tim Killeen, Ali Ayyad, Martin Glaser, Axel Stadie, Robert Reisch, Alf Giese, Eike SchwandtAbstract:Objective Aneurysm surgery demands precise Spatial Understanding of the vascular anatomy and its surroundings. We report on a decade of experience planning clipping procedures preoperatively in a virtual reality (VR) workstation and present outcomes with respect to mortality, morbidity, and aneurysm occlusion rate. Methods Between 2006 and 2015, the clipping of 115 intracranial aneurysms in 105 patients was preoperatively planned with the Dextroscope, a stereoscopic, patient-specific VR environment. The outcome data for all cases, planned and performed in 3 institutions, were analyzed based on clinical charts and radiologic reports. Results Eighty-five incidental, unruptured aneurysms in 77 patients were electively planned and treated surgically. Mortality was 0% and morbidity (modified Rankin Scale score >2) was 2.6%. The rate of complete aneurysm obliteration on postoperative imaging was 91.8%. In addition, 30 aneurysms were treated in 28 patients with previous subarachnoid hemorrhage. Mortality in these cases was 3.6%, morbidity (modified Rankin Scale score >2) 7.1%, and the rate of complete aneurysm clipping was 90%. Conclusions Meticulous three-dimensional surgical planning in a VR environment enhances the surgeon's Spatial Understanding of the individual vascular anatomy and allows clip preselection and positioning as well as anticipation of potential difficulties and complications. VR planning was associated, in this multi-institutional series, with excellent clinical outcomes and rates of complete aneurysm closure equivalent to benchmark cohorts.
-
aneurysm surgery with preoperative three dimensional planning in a virtual reality environment technique and outcome analysis
World Neurosurgery, 2016Co-Authors: Ralf A Kockro, Tim Killeen, Ali Ayyad, Martin Glaser, Axel Stadie, Robert Reisch, Alf Giese, Eike SchwandtAbstract:Objective Aneurysm surgery demands precise Spatial Understanding of the vascular anatomy and its surroundings. We report on a decade of experience planning clipping procedures preoperatively in a virtual reality (VR) workstation and present outcomes with respect to mortality, morbidity, and aneurysm occlusion rate. Methods Between 2006 and 2015, the clipping of 115 intracranial aneurysms in 105 patients was preoperatively planned with the Dextroscope, a stereoscopic, patient-specific VR environment. The outcome data for all cases, planned and performed in 3 institutions, were analyzed based on clinical charts and radiologic reports. Results Eighty-five incidental, unruptured aneurysms in 77 patients were electively planned and treated surgically. Mortality was 0% and morbidity (modified Rankin Scale score >2) was 2.6%. The rate of complete aneurysm obliteration on postoperative imaging was 91.8%. In addition, 30 aneurysms were treated in 28 patients with previous subarachnoid hemorrhage. Mortality in these cases was 3.6%, morbidity (modified Rankin Scale score >2) 7.1%, and the rate of complete aneurysm clipping was 90%. Conclusions Meticulous three-dimensional surgical planning in a VR environment enhances the surgeon's Spatial Understanding of the individual vascular anatomy and allows clip preselection and positioning as well as anticipation of potential difficulties and complications. VR planning was associated, in this multi-institutional series, with excellent clinical outcomes and rates of complete aneurysm closure equivalent to benchmark cohorts.