Related papers: Online Sparse Streaming Feature Selection Using Ad…

Estimating the size of the maximum matching is a canonical problem in graph algorithms, and one that has attracted extensive study over a range of different computational models. We present improved streaming algorithms for approximating…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large…

Scaling feature values is an important step in numerous machine learning tasks. Different features can have different value ranges and some form of a feature scaling is often required in order to learn an accurate classifier. However,…

Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…

Online feature selection with dynamic features has become an active research area in recent years. However, in some real-world applications such as image analysis and email spam filtering, features may arrive by groups. Existing online…

In this paper, we propose the problem of online cost-sensitive clas- sifier adaptation and the first algorithm to solve it. We assume we have a base classifier for a cost-sensitive classification problem, but it is trained with respect to a…

Federated learning (FL) scenarios inherently generate a large communication overhead by frequently transmitting neural network updates between clients and server. To minimize the communication cost, introducing sparsity in conjunction with…

We develop an online learning method for prediction, which is important in problems with large and/or streaming data sets. We formulate the learning approach using a covariance-fitting methodology, and show that the resulting predictor has…

Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the…

We propose a new matching-based framework for semi-supervised video object segmentation (VOS). Recently, state-of-the-art VOS performance has been achieved by matching-based algorithms, in which feature banks are created to store features…

This paper develops the first online algorithms for estimating the spectral density function -- a fundamental object of interest in time series analysis -- that satisfies the three core requirements of streaming inference: fixed memory,…

Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data collected by local entities. It includes local computation and synchronization steps. To reduce the communication…

As an effective data preprocessing step, feature selection has shown its effectiveness to prepare high-dimensional data for many machine learning tasks. The proliferation of high di-mension and huge volume big data, however, has brought…

As connected sensors continue to evolve, interest in low-voltage monitoring solutions is increasing. This also applies in the area of switchgear monitoring, where the detection of switch actions, their differentiation and aging are of…

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference…

While federated learning (FL) is a widely popular distributed machine learning (ML) strategy that protects data privacy, time-varying wireless network parameters and heterogeneous configurations of the wireless devices pose significant…

Online Tensor Factorization (OTF) is a fundamental tool in learning low-dimensional interpretable features from streaming multi-modal data. While various algorithmic and theoretical aspects of OTF have been investigated recently, a general…

Nonlinear models are known to provide excellent performance in real-world applications that often operate in non-ideal conditions. However, such applications often require online processing to be performed with limited computational…

A self-adaptive system can modify its own structure and behavior at runtime based on its perception of the environment, of itself and of its requirements. To develop a self-adaptive system, software developers codify knowledge about the…