Given a text description, Temporal Language Grounding (TLG) aims to localize temporal boundaries of the segments that contain specified semantics in an untrimmed video. TLG is inherently challenging task, as it requires comprehensive understanding both sentence and video contents. Previous works either tackle this task fully-supervised setting large amount annotations or weakly-supervised usual...

This paper presents a novel semisupervised learning algorithm called Active Deep Networks (ADN), to address the semi-supervised sentiment classification problem with active learning. First, we propose the semi-supervised learning method of ADN. ADN is constructed by Restricted Boltzmann Machines (RBM) with unsupervised learning using labeled data and abundant of unlabeled data. Then the constru...

We study semi-supervised learning when the data consists of multiple intersecting manifolds. We give a finite sample analysis to quantify the potential gain of using unlabeled data in this multi-manifold setting. We then propose a semi-supervised learning algorithm that separates different manifolds into decision sets, and performs supervised learning within each set. Our algorithm involves a n...

For many real-world application problems, the availability of data labels for supervised learning is rather limited. It is often the case that a limited number of labelled cases is accompanied by a larger number of unlabeled ones. This is the setting for semi-supervised learning, in which unsupervised approaches assist the supervised problem and viceversa. In this report, we outline some basic ...

This paper compares multilook Polarimetric SAR (PolSAR) image classification using three types of learning: a supervised, an unsupervised and a semisupervised. The multilook PolSAR pixel values are complex covariance matrices and they are described by mixtures of Wishart distributions. Tests in synthetic and real images showed that the supervised and semisupervised classifications provided the ...

We propose discriminative adversarial networks (DAN) for semi-supervised learning and loss function learning. Our DAN approach builds upon generative adversarial networks (GANs) and conditional GANs but includes the key differentiator of using two discriminators instead of a generator and a discriminator. DAN can be seen as a framework to learn loss functions for predictors that also implements...

We study Barron and Cover’s theory (BC theory) in supervised learning. The original BC theory can be applied to supervised learning only approximately and limitedly. Though Barron & Luo (2008) and Chatterjee & Barron (2014a) succeeded in removing the approximation, their idea cannot be essentially applied to supervised learning in general. By solving this issue, we propose an extension of BC th...

Sequential supervised learning problems arise in many applications. After a definition of this learning task, we give out a set of evaluation criteria to the sequential supervised learning algorithms, some leading ones of which are described in this paper and evaluated based on the given criteria. In this paper, we show how these sequential supervised learning algorithms evolve from one to anot...

Computational models of learning typically train on labeled input patterns (supervised learning), unlabeled input patterns (unsupervised learning), or a combination of the two (semi-supervised learning). In each case input patterns have a fixed number of features throughout training and testing. Human and machine learning contexts present additional opportunities for expanding incomplete knowle...