Attribute Learning for Understanding Unstructured Social Activity
نویسندگان
چکیده
The rapid development of social video sharing platforms has created a huge demand for automatic video classification and annotation techniques, in particular for videos containing social activities of a group of people (e.g. YouTube video of a wedding reception). Recently, attribute learning has emerged as a promising paradigm for transferring learning to sparsely labelled classes in object or single-object short action classification. In contrast to existing work, this paper for the first time, tackles the problem of attribute learning for understanding group social activities with sparse labels. This problem is more challenging because of the complex multi-object nature of social activities, and the unstructured nature of the activity context. To solve this problem, we (1) contribute an unstructured social activity attribute (USAA) dataset with both visual and audio attributes, (2) introduce the concept of semi-latent attribute space and (3) propose a novel model for learning the latent attributes which alleviate the dependence of existing models on exact and exhaustive manual specification of the attribute-space. We show that our framework is able to exploit latent attributes to outperform contemporary approaches for addressing a variety of realistic multi-media sparse data learning tasks including: multi-task learning, N-shot transfer learning, learning with label noise and importantly zero-shot learning.
منابع مشابه
Relevance Topic Model for Unstructured Social Group Activity Recognition
Unstructured social group activity recognition in web videos is a challenging task due to 1) the semantic gap between class labels and low-level visual features and 2) the lack of labeled training data. To tackle this problem, we propose a “relevance topic model” for jointly learning meaningful mid-level representations upon bagof-words (BoW) video representations and a classifier with sparse w...
متن کاملExtracurricular Activities And The Development Of Social Skills In Children With Intellectual And Learning Disabilities
Numerous skill deficits interfere with the social functioning of children with intellectual (ID) and learning disabilities (LD). Due to the limited effectiveness of social skill interventions for this population, it is necessary to explore additional opportunities for social skill acquisition. Research suggests that extracurricular activity participation positively influences adolescent develop...
متن کاملMultiview Hessian regularized logistic regression for action recognition
With the rapid development of social media sharing, people often need to manage the growing volume of multimedia data such as large scale video classification and annotation, especially to organize those videos containing human activities. Recently, manifold regularized semi-supervised learning (SSL), which explores the intrinsic data probability distribution and then improves the generalizatio...
متن کاملEntity Attribute Extraction from Unstructured Text with Deep Belief Network
Entity attribute extraction is an extremely challenging research area with broad application prospects. In this paper, we propose a new approach to extract the entities’ attributes from unstructured text corpus that was gathered from Web. The proposed method is an unsupervised machine learning method that extract the entity attributes utilizing DBN. To test the proposed method, we use it to ext...
متن کاملExtracting Incomplete Planning Action Models from Unstructured Social Media Data to Support Decision Making
Despite increasing interest in leveraging the wealth of online social media data to support data-based decision making, much work in this direction has focused on tasks with straightforward “labeling” decisions. A much richer class of tasks can benefit from the power of sequential decision making. However, supporting such tasks requires learning some form of action or decision models from unstr...
متن کامل