4D ROOSTER can be applied for human cardiac C-arm CT, and potentially in other dynamic tomography areas. It can easily be adapted to other problems as regularization is decoupled from projection and back projection.
Detecting an Out-of-Domain (OOD) utterance is crucial for a robust dialog system. Most dialog systems are trained on a pool of annotated OOD data to achieve this goal. However, collecting the annotated OOD data for a given domain is an expensive process. To mitigate this issue, previous works have proposed generative adversarial networks (GAN) based models to generate OOD data for a given domain automatically. However, these proposed models do not work directly with the text. They work with the text's latent space instead, enforcing these models to include components responsible for encoding text into latent space and decoding it back, such as auto-encoder. These components increase the model complexity, making it difficult to train.We propose OodGAN, a sequential generative adversarial network (SeqGAN) based model for OOD data generation. Our proposed model works directly on the text and hence eliminates the need to include an auto-encoder. OOD data generated using OodGAN model outperforms state-of-the-art in OOD detection metrics for ROSTD (67% relative improvement in FPR 0.95) and OSQ datasets (28% relative improvement in FPR 0.95) (Zheng et al., 2020).
We present a method to segment kidneys in 3D ultrasound images. The main challenges are the high variability in kidney appearance, the frequent presence of artifacts (shadows, speckle noise, etc.) and a strong constraint on computation time for clinical acceptance (less than 10 seconds). Our algorithm leverages a database of 480 3D images through a support vector machine(SVM)-based detection algorithm followed by a model-based deformation technique. Since severe pathologies induce strong deformations of kidneys, the proposed method encompasses intuitive interaction functions allowing the user to refine the result with a few clicks. Validation has been performed by learning on 120 cases and testing on 360; a perfect segmentation was reached automatically in 50% of the cases, and in 90% of the cases in less than 3 clicks.
Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to obtain for every new domain, limiting scalability of such systems. Similarly, rule-based dialogue systems require extensive writing and maintenance of rules and do not scale either. End-to-End dialogue systems, on the other hand, do not require module-specific annotations but need a large amount of data for training. To overcome these problems, in this demo, we present Alexa Conversations 1 , a new approach for building goal-oriented dialogue systems that is scalable, extensible as well as data efficient. The components of this system are trained in a data-driven manner, but instead of collecting annotated conversations for training, we generate them using a novel dialogue simulator based on a few seed dialogues and specifications of APIs and entities provided by the developer. Our approach provides outof-the-box support for natural conversational phenomena like entity sharing across turns or users changing their mind during conversation without requiring developers to provide any such dialogue flows. We exemplify our approach using a simple pizza ordering task and showcase its value in reducing the developer burden for creating a robust experience. Finally, we evaluate our system using a typical movie ticket booking task and show that the dialogue simulator is an essential component of the system that leads to over 50% improvement in turn-level action signature prediction accuracy.
We present a method for segmenting moving transparent layers in video sequences. We assume that the images can be divided into areas containing at most two moving transparent layers. We call this configuration (which is the mostly encountered one) bi-distributed transparency. The proposed method involves three steps: initial blockmatching for two-layer transparent motion estimation, motion clustering with 3D Hough transform, and joint transparent layer segmentation and parametric motion estimation. The last step is solved by the iterative minimization of a MRF-based energy function. The segmentation is improved by a mechanism detecting areas containing one single layer. The framework is applied to various image sequences with satisfactory results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.