Related papers: Feature Sampling Strategies for Action Recognition
Feature selection is essential for effective visual recognition. We propose an efficient joint classifier learning and feature selection method that discovers sparse, compact representations of input features from a vast sea of candidates,…
Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…
Temporal action localization aims to localize starting and ending time with action category. Limited by GPU memory, mainstream methods pre-extract features for each video. Therefore, feature quality determines the upper bound of detection…
A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational…
Graph sampling allows mining a small representative subgraph from a big graph. Sampling algorithms deploy different strategies to replicate the properties of a given graph in the sampled graph. In this study, we provide a comprehensive…
Multi-label multi-view action recognition aims to recognize multiple concurrent or sequential actions from untrimmed videos captured by multiple cameras. Existing work has focused on multi-view action recognition in a narrow area with…
At the present time, sequential item recommendation models are compared by calculating metrics on a small item subset (target set) to speed up computation. The target set contains the relevant item and a set of negative items that are…
Accurate and computationally efficient means for classifying human activities have been the subject of extensive research efforts. Most current research focuses on extracting complex features to achieve high classification accuracy. We…
Fine-grained anomaly detection has recently been dominated by segmentation based approaches. These approaches first classify each element of the sample (e.g., image patch) as normal or anomalous and then classify the entire sample as…
Feature selection has been studied widely in the literature. However, the efficacy of the selection criteria for low sample size applications is neglected in most cases. Most of the existing feature selection criteria are based on the…
Feature selection has drawn much attention over the last decades in machine learning because it can reduce data dimensionality while maintaining the original physical meaning of features, which enables better interpretability than feature…
Recognizing human activities in a sequence is a challenging area of research in ubiquitous computing. Most approaches use a fixed size sliding window over consecutive samples to extract features---either handcrafted or learned…
Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is…
Temporal action localization has recently attracted significant interest in the Computer Vision community. However, despite the great progress, it is hard to identify which aspects of the proposed methods contribute most to the increase in…
It is a common practice to exploit pyramidal feature representation to tackle the problem of scale variation in object instances. However, most of them still predict the objects in a certain range of scales based solely or mainly on a…
Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We…
Remote sensing image classification can be performed in many different ways to extract meaningful features. One common approach is to perform edge detection. A second approach is to try and detect whole shapes, given the fact that these…
Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily…
In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing…
In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and…