Search

Drill tool positioning in dental implantology is a challenging task requiring 5DOF precision as the rotation around the tool axis is not influential. This work improves the quasi-static visual elements of the state-of-the-art with a novel Augmented Collimation Widget (ACW), an interactive tool of position and angle error visualization based on the gestalt reification, the human ability to group geometric elements. The user can seek in a quick, pre-attentive way the collimation of five (three positional and two rotational) error component widgets (ECWs), taking advantage of three key aspects: component separation and reification, error visual amplification, and dynamic hiding of the collimated components. We compared the ACW with the golden standard in a within-subjects (N=30) user test using 32 implant targets, measuring the time, error, and usability. ACW performed significantly better in positional (+19%) and angular (+47%) precision accuracy and with less mental demand (-6%) and frustration (-13%), but with an expected increase in task time (+59%) and physical demand (+64%). The interview indicated the ACW as the main preference and aesthetically more pleasant than GSW, candidating it as the new golden standard for implantology, but also for other applications where 5DOF positioning is key.

Mixed Reality (MR) is proven in the literature to support precise spatial dental drill positioning by superimposing 3D widgets. Despite this, the related knowledge about widget's visual design and interactive user feedback is still limited. Therefore, this study is contributed to by co-designed MR drill tool positioning widgets with two expert dentists and three MR experts. The results of co-design are two static widgets (SWs): a simple entry point, a target axis, and two dynamic widgets (DWs), variants of dynamic error visualization with and without a target axis (DWTA and DWEP). We evaluated the co-designed widgets in a virtual reality simulation supported by a realistic setup with a tracked phantom patient, a virtual magnifying loupe, and a dentist's foot pedal. The user study involved 35 dentists with various backgrounds and years of experience. The findings demonstrated significant results; DWs outperform SWs in positional and rotational precision, especially with younger generations and subjects with gaming experiences. The user preference remains for DWs (19) instead of SWs (16). However, findings indicated that the precision positively correlates with the time trade-off. The post-experience questionnaire (NASA-TLX) showed that DWs increase mental and physical demand, effort, and frustration more than SWs. Comparisons between DWEP and DWTA show that the DW's complexity level influences time, physical and mental demands. The DWs are extensible to diverse medical and industrial scenarios that demand precision.

TOTTA outlines the spatial position and rotation guidance of a real/virtual tool (TO) towards a real/virtual target (TA), which is a key task in Mixed Reality applications. The task error can have critical consequences regarding safety, performance, and quality, such as in surgical implantology or industrial maintenance scenarios. The TOTTA problem lacks a dedicated study and is scattered across different domains with isolated designs. This work contributes to a systematic review of the TOTTA visual widgets, studying 70 unique designs from 24 papers. TOTTA is commonly guided by visual overlap an intuitive, pre-attentive 'collimation' feedback of simple-shaped widgets: Box, 3D Axes, 3D Model, 2D Crosshair, Globe, Tetrahedron, Line, and Plane. Our research discovers that TO and TA are often represented with the same shape. They are distinguished by topological elements (e.g., edges, vertices, faces), colors, transparency levels, and added shapes, widget quantity, and size. Meanwhile, some designs provide continuous 'during manipulation feedback' relative to the distance between TO and TA by text, dynamic color, sonification, and amplified graphical visualization. Some approaches trigger discrete 'TA reached feedback,' such as color alteration, added sound, TA shape change, and added text. We found a lack of golden standards, including in testing procedures, as current ones are limited to partial sets with different and incomparable setups (different target configurations, avatar, background, etc.). We also found a bias in participants: right-handed, young male, non-color impaired.

Effectively using full syntactic parsing information in Neural Networks (NNs) to solve relational tasks, e.g., question similarity, is still an open problem. In this paper, we propose to inject structural representations in NNs by (i) learning an SVM model using Tree Kernels (TKs) on relatively few pairs of questions (few thousands) as gold standard (GS) training data is typically scarce, (ii) predicting labels on a very large corpus of question pairs, and (iii) pre-training NNs on such large corpus. The results on Quora and SemEval question similarity datasets show that NNs trained with our approach can learn more accurate models, especially after fine tuning on GS., Comment: ACL2018

In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-comment similarity. The latter is the main task, which can exploit the previous two for achieving better results. Our DNN is trained jointly on all the three cQA tasks and learns to encode questions and comments into a single vector representation shared across the multiple tasks. The results on the official challenge test set show that our approach produces higher accuracy and faster convergence rates than the individual neural networks. Additionally, our method, which does not use any manual feature engineering, approaches the state of the art established with methods that make heavy use of it.

This paper studies the impact of different types of features applied to learning to re-rank questions in community Question Answering. We tested our models on two datasets released in SemEval-2016 Task 3 on "Community Question Answering". Task 3 targeted real-life Web fora both in English and Arabic. Our models include bag-of-words features (BoW), syntactic tree kernels (TKs), rank features, embeddings, and machine translation evaluation features. To the best of our knowledge, structural kernels have barely been applied to the question reranking task, where they have to model paraphrase relations. In the case of the English question re-ranking task, we compare our learning to rank (L2R) algorithms against a strong baseline given by the Google-generated ranking (GR). The results show that i) the shallow structures used in our TKs are robust enough to noisy data and ii) improving GR is possible, but effective BoW features and TKs along with an accurate model of GR features in the used L2R algorithm are required. In the case of the Arabic question re-ranking task, for the first time we applied tree kernels on syntactic trees of Arabic sentences. Our approaches to both tasks obtained the second best results on SemEval-2016 subtasks B on English and D on Arabic., Comment: presented at Second WebQA workshop, SIGIR2016 (http://plg2.cs.uwaterloo.ca/~avtyurin/WebQA2016/)