The problem of describing images through natural language has gained importance in the computer vision community. Solutions to image description have either focused on a top-down approach of generating language through combinations of object detections and language models or bottom-up propagation of keyword tags from training images to test images through probabilistic or nearest neighbor techniques. In contrast, describing videos with natural language is a less studied problem. In this paper, we combine ideas from the bottom-up and top-down approaches to image description and propose a method for video description that captures the most relevant contents of a video in a natural language description. We propose a hybrid system consisting of a low level multimodal latent topic model for initial keyword annotation, a middle level of concept detectors and a high level module to produce final lingual descriptions. We compare the results of our system to human descriptions in both short and long forms on two datasets, and demonstrate that final system output has greater agreement with the human descriptions than any single level.

Documents containing video and text are becoming more and more widespread and yet content analysis of those documents depends primarily on the text. Although automated discovery of semantically related words from text improves free text query understanding, translating videos into text summaries facilitates better video search particularly in the absence of accompanying text. In this paper, we propose a multimedia topic modeling framework suitable for providing a basis for automatically discovering and translating semantically related words obtained from textual metadata of multimedia documents to semantically related videos or frames from videos. The framework jointly models video and text and is flexible enough to handle different types of document features in their constituent domains such as discrete and real valued features from videos representing actions, objects, colors and scenes as well as discrete features from text. Our proposed models show much better fit to the multimedia data in terms of held-out data log likelihoods. For a given query video, our models translate low level vision features into bag of keyword summaries which can be further translated using simple natural language generation techniques into human readable paragraphs. We quantitatively compare the results of video to bag of words translation against a state-of-the-art baseline object recognition model from computer vision. We show that text translations from multimodal topic models vastly outperform the baseline on a multimedia dataset downloaded from the Internet.

We propose a variant of Convolutional Neural Network (CNN) models, the Attention CNN (ACNN); for large-scale categorization of millions of Japanese items into thirty-five product categories. Compared to a state-of-the-art Gradient Boosted Tree (GBT) classifier, the proposed model reduces training time from three weeks to three days while maintaining more than 96% accuracy. Additionally, our proposed model characterizes products by imputing attentive focus on word tokens in a language agnostic way. The attention words have been observed to be semantically highly correlated with the predicted categories and give us a choice of automatic feature extraction for downstream processing.

No abstract