The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks. This prospect, however, has not been validated on convolutional networks (convnet) – one of best performing deep models – because of their supervised regime. While unsupervised alternati...

We consider the problem of clustering a given dataset into k clusters subject to an additional set of constraints on relative distance comparisons between the data items. The additional constraints are meant to reflect side-information that is not expressed in the feature vectors, directly. Relative comparisons can express structures at finer level of detail than must-link (ML) and cannot-link ...

Face detection has been well studied for many years and one of the remaining challenges is to detect small, blurred and partially occluded faces in uncontrolled environment. This paper proposes a novel context-assisted single shot face detector, named PyramidBox, to handle the hard face detection problem. Observing the importance of the context, we improve the utilization of contextual informat...

We investigate automatic detection of teacher questions from automatically segmented human-transcripts of teacher audio recordings collected in live classrooms. Using a dataset of audio recordings from 11 teachers across 37 class sessions, we automatically segment teacher speech into individual teacher utterances and code each as containing a teacher question or not. We trained supervised machi...

This paper describes the MSRA experiments for TRECVID 2008. We performed the experiments in high-level feature extraction and automatic search tasks. For high-level feature extraction, we representatively investigated the benefit of global and local low-level features by a variety of learning-based methods, including supervised and semi-supervised learning algorithms. For automatic search, we f...

Many high level natural language processing problems can be framed as determining if two given sentences are a rewriting of each other. In this paper, we propose a class of kernel functions, referred to as type-enriched string rewriting kernels, which, used in kernel-based machine learning algorithms, allow to learn sentence rewritings. Unlike previous work, this method can be fed external lexi...

Abstract. Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labelled datasets. However, for video semantic object segmentation, a domain where labels are scarce, e↵ectively exploiting the representation power of CNN with limited training data remains a challenge. Simply borrowing the existing pre-trained CNN image recog...

In this work, we investigate how to improve semi-supervised DNN for low resource languages where the initial systems may have high error rate. We propose using semi-supervised MLP features for DNN training, and we also explore using confidence to improve semi-supervised cross entropy and sequence training. The work conducted in this paper was evaluated under the IARPA Babel program for the keyw...

In recent years feedback approaches have been used in relating low-level image features with concepts to overcome the subjective nature of the human image interpretation. Generally, in these systems when the user starts with a new query, the entire prior experience of the system is lost. In this paper, we address the problem of incorporating prior experience of the retrieval system to improve t...

We propose two semi-supervised learning approaches for automatically predicting semantic characteristics of lung nodules based on low-level image features. The NIH Lung Image Database Consortium (LIDC) dataset is used for training and testing of the proposed approaches such that the nodules on which at least three radiologists agree serve as labeled data and all the other nodules serve as unlab...