Huan Li

Hybrid active learning for cross-domain video concept detection

Cross-domain video concept detection is a challenging task due to the distribution difference between the source domain and target domain. In order to avoid expensive labeling the target-domain data, Active Learning can be used to incrementally learn a target classifier by reusing the one in the source domain. It uses a discriminative query strategy and picks the most ambiguous samples to label, which could fail if the distribution difference is too large. In this paper, to deal with large difference in data distributions, we propose a generative query strategy which is then combined with the existing discriminative one to yield a hybrid method. This method adaptively fits the distribution differences and gives a mixture strategy that performs more robustly compared to both single strategies. Experimental results on TRECVID semantic concept detection task demonstrate superior performance of our hybrid method.

Cross-domain video concept detection: A joint discriminative and generative active learning approach

In this work, we study the problem of cross-domain video concept detection, where the distributions of the source and target domains are different. Active learning can be used to iteratively refine a source domain classifier by querying labels for a few samples in the target domain, which could reduce the labeling effort. However, traditional active learning method which often uses a discriminative query strategy that queries the most ambiguous samples to the source domain classifier for labeling would fail, when the distribution difference between two domains is too large. In this paper, we tackle this problem by proposing a joint active learning approach which combines a novel generative query strategy and the existing discriminative one. The approach adaptively fits the distribution difference and shows higher robustness than the ones using single strategy. Experimental results on two synthetic datasets and the TRECVID video concept detection task highlight the effectiveness of our joint active learning approach.

Combining motion understanding and keyframe image analysis for broadcast video information extraction

We describe a robust new approach to extract semantic concept information based on explicitly encoding static image appearance features together with motion information. For high-level semantic concept identification detection in broadcast video, we trained multi-modality classifiers which combine the traditional static image features and a new motion feature analysis method (MoSIFT). The experimental result show that the combined features have solid performance for detecting a variety of motion related concepts and provide a large improvement over static image analysis features in video.

Unsupervised Clustering Algorithm for Video Shots Using Spectral Division

A new unsupervised clustering algorithm, Spectral-division Unsupervised Shot-clustering Algorithm (SUSC), is proposed in this paper. Key-fames are picked out to represent the shots, and color feature of key-frames are extracted to describe video shots. Spherical Gaussian Model (SGM) is constructed for every shot category to form effective descriptions of them. Then Spectral Division (SD) method is employed to divide a category into two categories, and the method is iteratively used for further divisions. After each iterative shot-division, Bayesian information Criterion (BIC) is utilized to automatically judge whether to stop further division. During this processes, one category may be dissevered by mistake. In order to correct these mistakes, similar categories will be merged by calculating the similarities of every two categories. This approach is applied to three kinds of sports videos, and the experimental results show that the proposed approach is reliable and effective.

Cross-domain active learning for video concept detection

As video data from a variety of different domains (e.g., news, documentaries, entertainment) have distinctive data distributions, cross-domain video concept detection becomes an important task, in which one can reuse the labeled data of one domain to benefit the learning task in another domain with insufficient labeled data. In this paper, we approach this problem by proposing a cross-domain active learning method which iteratively queries labels of the most informative samples in the target domain. Traditional active learning assumes that the training (source domain) and test data (target domain) are from the same distribution. However, it may fail when the two domains have different distributions because querying informative samples according to a base learner that initially learned from source domain may no longer be helpful for the target domain. In our paper, we use the Gaussian random field model as the base learner which has the advantage of exploring the distributions in both domains, and adopt uncertainty sampling as the query strategy. Additionally, we present an instance weighting trick to accelerate the adaptability of the base learner, and develop an efficient model updating method which can significantly speed up the active learning process. Experimental results on TRECVID collections highlight the effectiveness.

A Web 2.0 Based Computer Knowledge Learning Platform

Traditional Web-based online learning systems usually focus on the dispatch of knowledge, and lack of ways for students to get involved. Introduction to Computer Basics (ICB) is one of the first professional courses for freshmen majored in computer science, as well as information technology. To make the learning platform of ICB more helpful, a Web 2.0 based computer knowledge learning platform is presented, which changes the focus from course content to the students¿ participation. Web 2.0 elements including personal and group spaces, wiki cyclopedia, interest mining and personalized recommendation, and RSS resource subscription are integrated. The platform has been put into use already, and got satisfaction from both teachers and students.