Exemplar-SVMs for Action Recognition
نویسندگان
چکیده
This goal of this paper is to introduce a method for action recognition that significantly reduces the labeling process. The method involves training a separate linear support vector machine (SVM) classifier for each selected exemplar and combining the scores to form mid-level features. Our approach is trained and tested on the UCF Sports Action data set. The accuracies achieved by the combined Exemplar-SVMs method approaches the best reported accuracies on the UCF Sports Action data set using a reduced amount of labeled data.
منابع مشابه
Exploiting Low-Rank Structure from Latent Domains for Domain Generalization
In this paper, we propose a new approach for domain generalization by exploiting the low-rank structure from multiple latent source domains. Motivated by the recent work on exemplar-SVMs, we aim to train a set of exemplar classifiers with each classifier learnt by using only one positive training sample and all negative training samples. While positive samples may come from multiple latent doma...
متن کاملWriter Identification Using GMM Supervectors and Exemplar-SVMs
This paper describes a method for robust offline writer identification. We propose to use RootSIFT descriptors computed densely at the script contours. GMM supervectors are used as encoding method to describe the characteristic handwriting of an individual scribe. GMM supervectors are created by adapting a background model to the distribution of local feature descriptors. Finally, we propose to...
متن کاملDynamic Selection of Exemplar-SVMs for Watch-list Screening through Domain Adaptation
Still-to-video face recognition (FR) plays an important role in video surveillance, allowing to recognize individuals of interest over a network of video cameras. Watch-list screening is a challenging video surveillance application, because faces captured during enrollment (with still camera) may differ significantly from those captured during operations (with surveillance cameras) under uncont...
متن کاملLearning discriminative trajectorylet detector sets for accurate skeleton-based action recognition
The introduction of low-cost RGB-D sensors has promoted the research in skeleton-based human action recognition. Devising a representation suitable for characterising actions on the basis of noisy skeleton sequences remains a challenge, however. We here provide two insights into this challenge. First, we show that the discriminative information of a skeleton sequence usually resides in a short ...
متن کاملEncoding CNN Activations for Writer Recognition
The encoding of local features is an essential part for writer identification and writer retrieval. While CNN activations have already been used as local features in related works, the encoding of these features has attracted little attention so far. In this work, we compare the established VLAD encoding with triangulation embedding. We further investigate generalized max pooling as an alternat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013