Proceedings ArticleDOI
How Related Exemplars Help Complex Event Detection in Web Videos
Yi Yang,Zhigang Ma,Zhongwen Xu,Shuicheng Yan,Alexander G. Hauptmann +4 more
- pp 2104-2111
TLDR
To tackle the subjectiveness of human assessment, the algorithm automatically evaluates how positive the related exemplars are for the detection of an event and uses them on an exemplar-specific basis and gains good performance for complex event detection.Citations
More filters
Proceedings ArticleDOI
A discriminative CNN video representation for event detection
TL;DR: In this paper, a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available is proposed, which leverages deep convolutional neural networks (CNNs) to advance event detection, where only frame level static descriptors can be extracted by the existing CNN toolkits.
Journal ArticleDOI
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization
TL;DR: This paper proposes a semi-supervised batch mode multi-class active learning algorithm for visual concept recognition that exploits the whole active pool to evaluate the uncertainty of the data, and proposes to make the selected data as diverse as possible.
Proceedings ArticleDOI
DevNet: A Deep Event Network for multimedia event detection and evidence recounting
TL;DR: A flexible deep CNN infrastructure, namely Deep Event Network (DevNet), is proposed that simultaneously detects pre-defined events and provides key spatial-temporal evidences, both for event detection and evidence recounting.
Journal ArticleDOI
Bi-Level Semantic Representation Analysis for Multimedia Event Detection
TL;DR: This work proposes a bi-level semantic representation analyzing method that learns weights of semantic representation attained from different multimedia archives, and restrains the negative influence of noisy or irrelevant concepts in the overall concept-level.
Journal ArticleDOI
Data Uncertainty in Face Recognition
TL;DR: This paper reduces the uncertainty of the face representation by synthesizing the virtual training samples and devise a representation approach based on the selected useful training samples to perform face recognition that can not only obtain a high face recognition accuracy, but also has a lower computational complexity than the other state-of-the-art approaches.
References
More filters
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
TL;DR: The database contains labeled face photographs spanning the range of conditions typically encountered in everyday life, and exhibits “natural” variability in factors such as pose, lighting, race, accessories, occlusions, and background.
Proceedings ArticleDOI
Learning realistic human actions from movies
TL;DR: A new method for video classification that builds upon and extends several recent ideas including local space-time features,space-time pyramids and multi-channel non-linear SVMs is presented and shown to improve state-of-the-art results on the standard KTH action dataset.
Journal ArticleDOI
One-shot learning of object categories
TL;DR: It is found that on a database of more than 100 categories, the Bayesian approach produces informative models when the number of training examples is too small for other methods to operate successfully.
Proceedings ArticleDOI
Action recognition by dense trajectories
TL;DR: This work introduces a novel descriptor based on motion boundary histograms, which is robust to camera motion and consistently outperforms other state-of-the-art descriptors, in particular in uncontrolled realistic videos.
Journal ArticleDOI
Evaluating Color Descriptors for Object and Scene Recognition
TL;DR: From the theoretical and experimental results, it can be derived that invariance to light intensity changes and light color changes affects category recognition and the usefulness of invariance is category-specific.