392,262 Hits in 3.5 sec

Automatically learning shape specifications

He Zhu, Gustavo Petri, Suresh Jagannathan
2016 SIGPLAN notices  
Experimental results indicate that our implementation is both efficient and effective, capable of automatically synthesizing sophisticated shape specifications over a range of complex data types, going  ...  language using a lightweight data-driven learning procedure.  ...  Devise a data-driven learning technique to perform automatic inference and synthesis of function specifications using these predicates.  ... 
doi:10.1145/2980983.2908125 fatcat:pkr2zib775burhalokplvgevke

Cross Modality Deformable Segmentation Using Hierarchical Clustering and Learning [chapter]

Yiqiang Zhan, Maneesh Dewan, Xiang Sean Zhou
2009 Lecture Notes in Computer Science  
Although many automatic segmentation methods have been designed to segment specific anatomical objects in a given imaging modality, a more generic solution that is directly applicable to different imaging  ...  The appearance characteristics of each learned anatomical primitive are then captured through a cascaded boosting learning method. (2) To effectively incorporate non-Gaussian shape priors, we cluster the  ...  Introduction In recent decades, automatic/semi-automatic algorithms for the delineation of anatomical structures has become more and more important in assisting and automating specific radiological tasks  ... 
doi:10.1007/978-3-642-04271-3_125 fatcat:amewe5l2ijfdpcscuwgngojxd4

From Controlled to Automatic Processes and Back Again: The Role of Contextual Features

Rosa Angela Fabio, Tindara Caprì, Martina Romano
2019 Europe's Journal of Psychology  
An automatic sequence task (with and without contextual features) was used to test flexibility in automatic processing.  ...  Results showed that the use of contextual cues can increase flexibility in automatic processes. The results are discussed in light of new theories on softened automaticity.  ...  In conclusion, the present study highlights two key points: the first concerns the possibility that context-specific features can affect the learned task and can implement flexibility in automatic processing  ... 
doi:10.5964/ejop.v15i4.1746 pmid:33680159 pmcid:PMC7909205 fatcat:zn7qcuz7yjgqfpscw23sxfz4rq

Creating a Computable Cognitive Model of Visual Aesthetics for Automatic Aesthetics Evaluation of Robotic Dance Poses

Hua Peng, Jing Li, Huosheng Hu, Keli Hu, Chao Tang, Yulong Ding
2019 Symmetry  
After applying machine learning methods in different feature combinations, machine aesthetics models are built for automatic evaluation of robotic dance poses.  ...  Specifically, a computable cognitive model of visual aesthetics is developed using the two important aesthetic cognitive neural models of the human brain, which is then applied in the automatic aesthetics  ...  Each stage will be implemented by some specific algorithms from computer vision or machine-learning technology.  ... 
doi:10.3390/sym12010023 fatcat:xacncilbg5bzrirr2ndx6xep3u

Pose Normalization via Learned 2D Warping for Fully Automatic Face Recognition

Akshay Asthana, Michael Jones, Tim Marks, Kinh Tieu, Roland Goecke
2011 Procedings of the British Machine Vision Conference 2011  
Our method uses multi dimensional Gaussian process regression to learn a nonlinear mapping function from the 2D shapes of faces at any non-frontal pose to the corresponding 2D frontal face shapes.  ...  Our method uses multidimensional Gaussian process regression to learn a nonlinear mapping function from the 2D shapes of faces at any non-frontal pose to the corresponding 2D frontal face shapes.  ...  To compare that regression method with ours, we employ it in reverse, learning a mapping from face shapes in a specific nonfrontal pose to the corresponding frontal face shapes.  ... 
doi:10.5244/c.25.127 dblp:conf/bmvc/AsthanaJMTG11 fatcat:rpidxiceorhvhjxsane2wt46gu

Multiple Visual Feature Integration Based Automatic Aesthetics Evaluation of Robotic Dance Motions

Hua Peng, Jinghao Hu, Haitao Wang, Hui Ren, Cong Sun, Huosheng Hu, Jing Li
2021 Information  
Inspired by the above facts, this paper proposes a novel mechanism of automatic aesthetics evaluation of robotic dance motions based on multiple visual feature integration.  ...  Meanwhile, in the visual aesthetics cognition of human brains, space and shape are two important visual elements perceived from motions.  ...  In this paper, ensemble learning is used in the stage of automatic aesthetics evaluation.  ... 
doi:10.3390/info12030095 fatcat:5rvkp57dqjej3bzeqogkg62hzu

Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets [article]

Clara Fernandez-Labrador, Ajad Chhatkuli, Danda Pani Paudel, Jose J. Guerrero, Cédric Demonceaux, Luc Van Gool
2021 arXiv   pre-print
Automatic discovery of category-specific 3D keypoints from a collection of objects of some category is a challenging problem.  ...  We define keypoints to be category-specific, if they meaningfully represent objects' shape and their correspondences can be simply established order-wise across all objects.  ...  Automatic discovery of category-specific 3D keypoints from a collection of objects of some category is a challenging problem.  ... 
arXiv:2003.07619v3 fatcat:sukmkgxk4jeynh6a4zhtjp7wxe

Category-Specific Object Reconstruction from a Single Image [article]

Abhishek Kar, Shubham Tulsiani, João Carreira, Jitendra Malik
2015 arXiv   pre-print
At the core of our approach are deformable 3D models that can be learned from 2D annotations available in existing object detection datasets, that can be driven by noisy automatic object segmentations  ...  and which we complement with a bottom-up module for recovering high-frequency shape details.  ...  Learning Deformable 3D Models We are interested in 3D shape models that can be robustly aligned to noisy object segmentations by incorporating top-down class-specific knowledge of how shapes from the class  ... 
arXiv:1411.6069v2 fatcat:g4f5xqheprh67p5gqvn7rlfi4u

Free-sketch recognition

Tracy Hammond, Brian Eoff, Brandon Paulson, Aaron Wolin, Katie Dahmen, Joshua Johnston, Pankaj Rajan
2008 Proceeding of the twenty-sixth annual CHI conference extended abstracts on Human factors in computing systems - CHI '08  
Gesture-based techniques, such as those used by the Palm Pilot's Graffiti, can provide highaccuracy, but require the user to learn a particular drawing style in order for shapes to be recognized.  ...  Free-sketch recognition allows users to draw shapes as they would naturally, but most current techniques have low accuracies or require significant domain-level tweaking to make them usable.  ...  We thank Randall Davis for helping to shape our ideas, as well as other previous members of the MIT Design Rationale Group -specifically including Christine Alvarado, Metin Sezgin, Michael Oltmans, Aaron  ... 
doi:10.1145/1358628.1358802 dblp:conf/chi/HammondEPWDJR08 fatcat:nkbod6exkjfafmukv4edainbgm

Orthophoto Map Feature Extraction Based on Neural Networks

Zdenek Horak, Milos Kudelka, Václav Snásel, Vit Vozenilek
2011 Databases, Texts, Specifications, Objects  
These features describe the segment from the viewpoint of general image analysis (color, tint, etc.) as well as from the viewpoint of the shapes in the segment.  ...  As the learning method we use supervised learning, where the network is presented repeatedly with specific samples, which are propagated towards the network output.  ...  These features are detected by a set of specific algorithms. We use a neural network for tuning these algorithms. The features are then detected automatically.  ... 
dblp:conf/dateso/HorakKSV11 fatcat:ogamlnvy5bewrbwbt2c472mffm

A Data-Driven Automatic Design Method for Electric Machines Based on Reinforcement Learning and Evolutionary Optimization

Takahiro Sato, Masafumi Fujita
2021 IEEE Access  
The overview of the machine shape is shown in Fig. 5 . The specification, the fundamental and shape variables are summarized in Table I , II, respectively.  ...  Conclusion For the automatic design of electric machines considering all the fundamental and shape variables, an automatic design method named DeSearTAM has been proposed.  ...  The circuit constants of the equivalent circuit are derived from the geometric shape of the machine. The other features of the machine are also computed from the machine shape analytically.  ... 
doi:10.1109/access.2021.3078668 fatcat:py3tqs4e35cmxlspscevysbkye

Whose DAM account? Attentional learning explains Booth and Waxman

Linda B. Smith, Susan S. Jones, Hanako Yoshida, Eliana Colunga
2003 Cognition  
Although the objects were clearly artifactual, the stories included many descriptors and verbs specific to animate kinds.  ...  In this linguistic context, rich in animacy cues, the children generalized the names as if the novel artifacts were animate things -that is, by similarities in shape and texture rather than by shape alone  ...  In a similar way, we have suggested that naming automatically takes children's attention to specific perceptible object properties because of well-learned associations.  ... 
doi:10.1016/s0010-0277(02)00236-6 pmid:12684200 fatcat:sls2xs6fargdrokqq7xbp7kimy


Y. Li, M. Sakamoto, T. Shinohara, T. Satoh
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Hence, we propose a novel approach for automatic label placement of area-feature based on deep learning.  ...  Then a key-point detection model, which simultaneously detect and localize specific key-points from an image, is applied to the binary image to estimate the candidate positions of labels.  ...  In this study, we focused on deep learning, which is a specific kind of machine learning. Compared to the rule-based approach, deep learning does not require the human design of rules and features.  ... 
doi:10.5194/isprs-archives-xliii-b4-2020-117-2020 fatcat:wuswojda7zbhjnrydrax7yuip4

Alternative face models for 3D face registration

Albert Ali Salah, Neşe Alyüz, Lale Akarun, Longin Jan Latecki, David M. Mount, Angela Y. Wu
2007 Vision Geometry XV  
Finally, we perform simulations with multiple AFMs that correspond to different clusters in the face shape space and compare these with gender and morphology based groupings.  ...  Drawing on cognitive justifications, we propose to employ category-specific alternative average face models for registration, which is shown to increase the accuracy of the subsequent recognition.  ...  The beneficial effect from specific AFMs is evident in TPS methods that use either automatic or manual landmarks.  ... 
doi:10.1117/12.705860 fatcat:a3muhvowhjgoxn3saziozwmlwm

Automatic Extraction of Appendix from Ultrasonography with Self-Organizing Map and Shape-Brightness Pattern Learning

Kwang Baek Kim, Doo Heon Song, Hyun Jun Park
2016 BioMed Research International  
In this paper, we propose a fully automatic appendix extractor from ultrasonography by applying a series of image processing algorithms and an unsupervised neural learning algorithm, self-organizing map  ...  From the suggestions of clinical practitioners, we define four shape patterns of appendix and self-organizing map learns those patterns in pixel clustering phase.  ...  Conclusion In this paper, we propose a method to extract appendix automatically by using a series of image processing algorithms and self-organizing map that learns typical shape patterns of appendix from  ... 
doi:10.1155/2016/5206268 pmid:27190991 pmcid:PMC4844865 fatcat:dw2vk2fj3netzkopok5w5kc6py
« Previous Showing results 1 — 15 out of 392,262 results