Sorry, you need to enable JavaScript to visit this website.

LDADeep+: Latent Aspect Discovery with Deep Representations

Citation Author(s):
Chieh-En Tsai, Hui-Lan Hsieh, Winston Hsu
Submitted by:
Chieh-En Tsai
Last updated:
24 March 2016 - 12:09pm
Document Type:
Presentation Slides
Document Year:
2016
Event:
Presenters Name:
Chieh-En Tsai (Andy Tsai)
Paper Code:
MMSP-L2.2

Abstract 

Abstract: 

Nowadays, with the success and fast growth of social media communities and mobile devices, people are encouraged to share their multimedia data online. Analyzing and summarizing data into useful information thus becomes increasingly important. For on- line photo sharing services like Flickr, when users are uploading a batch of daily photos at a time, the tags users provided tend to be rather vague, containing only a small amount of information. For better photo application and understanding, we attempt to automat- ically discover semantic-rich (hidden) aspects of photos merely by looking at image contents. In this paper, we propose an effective model, which is a combination of LDA model and deep learning rep- resentations, to realize the idea of automatic aspect discovery. We then discuss the properties of this aspect discovery model through experiments on event summarization task . In those experiments, we show the high diversity and high quality of aspects discovered by our proposed method. Meanwhile, we conduct an user study to evaluate the quality of the summarized results. Moreover, the pro- posed method can be further extended to human attribute discovery for a given event. We automatically discover different aspects on our Olympic Games data (e.g. football, ice skating).

up

Dataset Files

tsai_LDADeep_4_3 copy.pptx

(119)