Action-grounded surface geometry and volumetric shape feature representations for object affordance prediction

2016 ◽  
Author(s):  
Barry Ridge ◽  
Ales Ude
Keyword(s):  
Shape Feature ◽  
Surface Geometry ◽  
Feature Representations ◽  
Object Affordance

Perceived Glossiness: Beyond Surface Properties

2019 ◽  
Vol 2019 (1) ◽  
pp. 37-42
Author(s):  
Davit Gigilashvili ◽  
Jean-Baptiste Thomas ◽  
Marius Pedersen ◽  
Jon Yngve Hardeberg
Keyword(s):  
Surface Properties ◽  
Human Subjects ◽  
Surface Geometry ◽  
Surface Reflection ◽  
Different Color

Gloss is widely accepted as a surface- and illuminationbased property, both by definition and by means of metrology. However, mechanisms of gloss perception are yet to be fully understood. Potential cues generating gloss perception can be a product of phenomena other than surface reflection and can vary from person to person. While human observers are less likely to be capable of inverting optics, they might also fail predicting the origin of the cues. Therefore, we hypothesize that color and translucency could also impact perceived glossiness. In order to validate our hypothesis, we conducted series of psychophysical experiments asking observers to rank objects by their glossiness. The objects had the identical surface geometry and shape but different color and translucency. The experiments have demonstrated that people do not perceive objects with identical surface equally glossy. Human subjects are usually able to rank objects of identical surface by their glossiness. However, the strategy used for ranking varies across the groups of people.

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

2017 ◽  
Author(s):  
Sabrina Jaeger ◽  
Simone Fulle ◽  
Samo Turk
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Learning Approaches ◽  
Unsupervised Machine Learning ◽  
Feature Representations ◽  
Machine Learning Approach ◽  
The Individual ◽  
Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

Deep Convex Representations: Feature Representations for Bioacoustics Classification

2018 ◽  
Author(s):  
Anshul Thakur ◽  
Vinayak Abrol ◽  
Pulkit Sharma ◽  
Padmanabhan Rajan
Keyword(s):  
Feature Representations

scholarly journals Meta Learning for Few-Shot One-Class Classification

AI ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 195-208
Author(s):  
Gabriel Dahia ◽  
Maurício Pamplona Segundo
Keyword(s):  
Feature Representation ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Target Class ◽  
Feature Representations ◽  
Shot Classification ◽  
Training Stage ◽  
Comparable Performance ◽  
Meta Learning ◽  
One Class Classification

We propose a method that can perform one-class classification given only a small number of examples from the target class and none from the others. We formulate the learning of meaningful features for one-class classification as a meta-learning problem in which the meta-training stage repeatedly simulates one-class classification, using the classification loss of the chosen algorithm to learn a feature representation. To learn these representations, we require only multiclass data from similar tasks. We show how the Support Vector Data Description method can be used with our method, and also propose a simpler variant based on Prototypical Networks that obtains comparable performance, indicating that learning feature representations directly from data may be more important than which one-class algorithm we choose. We validate our approach by adapting few-shot classification datasets to the few-shot one-class classification scenario, obtaining similar results to the state-of-the-art of traditional one-class classification, and that improves upon that of one-class classification baselines employed in the few-shot setting.

scholarly journals Temporal coherency of mechanical stimuli modulates tactile form perception

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Masashi Nakatani ◽  
Yasuaki Kobayashi ◽  
Kota Ohno ◽  
Masaaki Uesaka ◽  
Sayako Mogami ◽  
...  
Keyword(s):  
Sensory Neuron ◽  
Sensory Neurons ◽  
Contact Surface ◽  
Relative Magnitude ◽  
Form Perception ◽  
Tangential Displacement ◽  
Surface Geometry ◽  
Tactile Stimuli ◽  
Surface Patterns ◽  
Temporal Coherency

AbstractThe human hand can detect both form and texture information of a contact surface. The detection of skin displacement (sustained stimulus) and changes in skin displacement (transient stimulus) are thought to be mediated in different tactile channels; however, tactile form perception may use both types of information. Here, we studied whether both the temporal frequency and the temporal coherency information of tactile stimuli encoded in sensory neurons could be used to recognize the form of contact surfaces. We used the fishbone tactile illusion (FTI), a known tactile phenomenon, as a probe for tactile form perception in humans. This illusion typically occurs with a surface geometry that has a smooth bar and coarse textures in its adjacent areas. When stroking the central bar back and forth with a fingertip, a human observer perceives a hollow surface geometry even though the bar is physically flat. We used a passive high-density pin matrix to extract only the vertical information of the contact surface, suppressing tangential displacement from surface rubbing. Participants in the psychological experiment reported indented surface geometry by tracing over the FTI textures with pin matrices of the different spatial densities (1.0 and 2.0 mm pin intervals). Human participants reported that the relative magnitude of perceived surface indentation steeply decreased when pins in the adjacent areas vibrated in synchrony. To address possible mechanisms for tactile form perception in the FTI, we developed a computational model of sensory neurons to estimate temporal patterns of action potentials from tactile receptive fields. Our computational data suggest that (1) the temporal asynchrony of sensory neuron responses is correlated with the relative magnitude of perceived surface indentation and (2) the spatiotemporal change of displacements in tactile stimuli are correlated with the asynchrony of simulated sensory neuron responses for the fishbone surface patterns. Based on these results, we propose that both the frequency and the asynchrony of temporal activity in sensory neurons could produce tactile form perception.

Channel-exchanged feature representations for person re-identification

2021 ◽  
Author(s):  
Jianchen Wang ◽  
Liming Yuan ◽  
Haixia Xu ◽  
Gengsheng Xie ◽  
Xianbin Wen
Keyword(s):  
Feature Representations
Sign in / Sign up

Export Citation Format

Share Document