Learning Features of Intermediate Complexity for the Recognition of Biological Motion
نویسندگان
چکیده
Humans can recognize biological motion (e.g. a walker) from stimuli with impoverished information, like point-light displays (e.g. a “point-like walker”). Although the neural mechanism underlying such a robust representation remains unclear, a possible explanation is that it is based on specific motion features shared by normal and point-light stimuli. A recent study using image statistics and psychophysics has shown that these features are "opponent-motion" like, which are also congruent with neurophysiological studies. Here we use a plausible algorithm (MeT) to learn mid-level features from motion stimuli within the frame of a model for the recognition of biological motion (MRBM). Features were learnt from motion sequences containing a "walker" in two different situations: with and without cluttered background. Additionally, we use these features to solve a "walker" detection task. Our results showed that in both conditions the MeT algorithm found "opponent-motion" features, which were more present when stimuli contained no background. As we already proved with static stimuli, learning motionspecific ("walker") mid-level features increase detection performance in cluttered-background conditions.
منابع مشابه
EMG-based wrist gesture recognition using a convolutional neural network
Background: Deep learning has revolutionized artificial intelligence and has transformed many fields. It allows processing high-dimensional data (such as signals or images) without the need for feature engineering. The aim of this research is to develop a deep learning-based system to decode motor intent from electromyogram (EMG) signals. Methods: A myoelectric system based on convolutional ne...
متن کاملRecognition of Visual Events using Spatio-Temporal Information of the Video Signal
Recognition of visual events as a video analysis task has become popular in machine learning community. While the traditional approaches for detection of video events have been used for a long time, the recently evolved deep learning based methods have revolutionized this area. They have enabled event recognition systems to achieve detection rates which were not reachable by traditional approac...
متن کاملA Novel Approach to Conditional Random Field-based Named Entity Recognition using Persian Specific Features
Named Entity Recognition is an information extraction technique that identifies name entities in a text. Three popular methods have been conventionally used namely: rule-based, machine-learning-based and hybrid of them to extract named entities from a text. Machine-learning-based methods have good performance in the Persian language if they are trained with good features. To get good performanc...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملApplication of Combined Local Object Based Features and Cluster Fusion for the Behaviors Recognition and Detection of Abnormal Behaviors
In this paper, we propose a novel framework for behaviors recognition and detection of certain types of abnormal behaviors, capable of achieving high detection rates on a variety of real-life scenes. The new proposed approach here is a combination of the location based methods and the object based ones. First, a novel approach is formulated to use optical flow and binary motion video as the loc...
متن کامل