Action Representation Using Classifier Decision Boundaries

نویسندگان

  • Jue Wang
  • Anoop Cherian
  • Fatih Murat Porikli
  • Stephen Gould
چکیده

Most popular deep learning based models for action recognition are designed to generate separate predictions within their short temporal windows, which are often aggregated by heuristic means to assign an action label to the full video segment. Given that not all frames from a video characterize the underlying action, pooling schemes that impose equal importance to all frames might be unfavorable. In an attempt towards tackling this challenge, we propose a novel pooling scheme, dubbed SVM pooling, based on the notion that among the bag of features generated by a CNN on all temporal windows, there is at least one feature that characterizes the action. To this end, we learn a decision hyperplane that separates this unknown yet useful feature from the rest. Applying multiple instance learning in an SVM setup, we use the parameters of this separating hyperplane as a descriptor for the video. Since these parameters are directly related to the support vectors in a max-margin framework, they serve as robust representations for pooling of the CNN features. We devise a joint optimization objective and an efficient solver that learns these hyperplanes per video and the corresponding action classifiers over the hyperplanes. Showcased experiments on the standard HMDB and UCF101 datasets demonstrate state-of-the-art performance.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Hybrid Classifier for Characterizing Motor Unit Action Potentials in Diagnosing Neuromuscular Disorders

Background: The time and frequency features of motor unit action potentials (MUAPs) extracted from electromyographic (EMG) signal provide discriminative information for diagnosis and treatment of neuromuscular disorders. However, the results of conventional automatic diagnosis methods using MUAP features is not convincing yet.Objective: The main goal in designing a MUAP characterization system ...

متن کامل

A Novel Bayesian Classifier using Copula Functions

A useful method for representing Bayesian classifiers is through discriminant functions. Here, using copula functions, we propose a new model for discriminants. This model provides a rich and generalized class of decision boundaries. These decision boundaries significantly boost the classification accuracy especially for high dimensional feature spaces. We strengthen our analysis through simula...

متن کامل

A variance-based Bayesian framework for improving Land-Cover classification through wide-area learning from large geographic regions

Common to much work on land-cover classification in multispectral imagery is the use of single satellite images for training the classifiers for the different land types. Unfortunately, more often than not, decision boundaries derived in this manner do not extrapolate well from one image to another. This happens for several reasons, most having to do with the fact that different satellite image...

متن کامل

Learning classifier systems for decision making in continuous-valued domains

This thesis investigates Learning Classifier System architectures for decision making in continuous-valued domains. The information contained in continuous-valued domains is not always conveniently expressed using the ternary representation typically used by Learning Classifier Systems and an interval-based representation is a natural choice. Two intervalbased representations recently proposed ...

متن کامل

Relationship Between Decision Boundaries and Recognition Error Rates in Pattern Recognition with Supplementary Information

Pattern recognition with supplementary information which differs from the conventional pattern recognition has been proposed. This framework decreases misrecognition rates by using not only a pattern itself but also supplementary information that assists recognition. In the framework, a classifier suitable for the conventional pattern recognition has simply been used, and thus there is room for...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1704.01716  شماره 

صفحات  -

تاریخ انتشار 2017