arXiv subjects

Ramesh Jain

Publications and source records attributed to Ramesh Jain.

40 records · Page 3Linked to original sources

arXiv2017

From Photo Streams to Evolving Situations

Photos are becoming spontaneous, objective, and universal sources of information. This paper develops evolving situation recognition using photo streams coming from disparate sources combined with the advances of deep learning. Using visual concepts in photos together with space and time information, we formulate the situation detection into a semi-supervised learning framework and propose new graph-based models to solve the problem. To extend the method for unknown situations, we introduce a soft label method which enables the traditional semi-supervised learning framework to accurately predict predefined labels as well as effectively form new clusters. To overcome the noisy data which degrades graph quality, leading to poor recognition results, we take advantage of two kinds of noise-robust norms which can eliminate the adverse effects of outliers in visual concepts and improve the accuracy of situation recognition. Finally, we demonstrate the idea and the effectiveness of the proposed model on Yahoo Flickr Creative Commons 100 Million.

cs.MM↗

arXiv2016

A framework for event co-occurrence detection in event streams

This paper shows that characterizing co-occurrence between events is an important but non-trivial and neglected aspect of discovering potential causal relationships in multimedia event streams. First an introduction to the notion of event co-occurrence and its relation to co-occurrence pattern detection is given. Then a finite state automaton extended with a time model and event parameterization is introduced to convert high level co-occurrence pattern definition to its corresponding pattern matching automaton. Finally a processing algorithm is applied to count the occurrence frequency of a collection of patterns with only one pass through input event streams. The method proposed in this paper can be used for detecting co-occurrences between both events of one event stream (Auto co-occurrence), and events from multiple event streams (Cross co-occurrence). Some fundamental results concerning the characterization of event co-occurrence are presented in form of a visual co- occurrence matrix. Reusable causality rules can be extracted easily from co-occurrence matrix and fed into various analysis tools, such as recommendation systems and complex event processing systems for further analysis.

cs.MM↗

arXiv2016

Habits vs Environment: What really causes asthma?

Despite considerable number of studies on risk factors for asthma onset, very little is known about their relative importance. To have a full picture of these factors, both categories, personal and environmental data, have to be taken into account simultaneously, which is missing in previous studies. We propose a framework to rank the risk factors from heterogeneous data sources of the two categories. Established on top of EventShop and Personal EventShop, this framework extracts about 400 features, and analyzes them by employing a gradient boosting tree. The features come from sources including personal profile and life-event data, and environmental data on air pollution, weather and PM2.5 emission sources. The top ranked risk factors derived from our framework agree well with the general medical consensus. Thus, our framework is a reliable approach, and the discovered rankings of relative importance of risk factors can provide insights for the prevention of asthma.

cs.CY↗

arXiv2011

Label-Specific Training Set Construction from Web Resource for Image Annotation

Recently many research efforts have been devoted to image annotation by leveraging on the associated tags/keywords of web images as training labels. A key issue to resolve is the relatively low accuracy of the tags. In this paper, we propose a novel semi-automatic framework to construct a more accurate and effective training set from these web media resources for each label that we want to learn. Experiments conducted on a real-world dataset demonstrate that the constructed training set can result in higher accuracy for image annotation.

cs.MM↗