Large-scale distributed computing has made available the resources necessary to solve "AI-hard" problems. As a result, it becomes feasible to automate the processing of such problems, but accuracy is not very high due to the conceptual difficulty of these problems. In this paper, we integrated crowdsourcing with MapReduce to provide a scalable innovative human-machine solution to AI-hard problems, which is called CrowdMR. In CrowdMR, the majority of problem instances are automatically processed by machine while the troublesome instances are redirected to human via crowdsourcing. The results returned from crowdsourcing are validated in the form of CAPTCHA (Completely Automated Public Turing test to Tell Computers and Humans Apart) before adding to the output. An incremental scheduling method was brought forward to combine the results from machine and human in a "pay-as-you-go" way.

The Multi-Label Classification (MLC) problem has aroused wide concern in these years since the multi-labeled data appears in many applications, such as page categorization, tag recommendation, mining of semantic web data, social network analysis, and so forth. In this paper, we propose a novel MLC solution based on the random walk model, called MLRW. MLRW maps the multi-labeled instances to graphs, on which the random walk is applied. When an unlabeled data is fed, MLRW transforms the original multi-label problem to some single-label subproblems. Experimental results on several real-world data sets demonstrate that MLRW is a better solution to the MLC problems than many other existing multi-label classification methods.

Content-aware music adaption, i.e. music resizing, in temporal constraints starts drawing attention from multimedia communities because of the need of real-world scenarios, e.g. animation production and radio advertisement production. The goal of music resizing is to change the length of a music track to a user preferred length using a series of basic operations, e.g. compression, prolonging, cropping and repeating. The only existing music resizing approach so far, called LyDAR, suffers from some limitations. For example, it cannot support prolonging a music track and cannot compress music pieces with very small stretch rates. In this paper, we propose MUSIZ, a generic framework for MUsic reSIZing. Observing the diversity of quality degradation for different segments, we propose the concept of stretch-resistance to measure the degree of quality degradation after a segment is stretched. MUSIZ stretches high stretch-resistance segments intensively and relieves low stretch-resistance segments to reduce the negative impact on the stretched music piece. For short length resizing requests, we develop a contiguity-preservative cropping algorithm to remove segments before stretching, while smoothing the abrupt change at the joint between two segments. Comprehensive experimental results show that MUSIZ is superior to the existing approaches.

In many scenarios, such as TV/radio advertising production, animation production, and presentation, music pieces are constrained in the metric of time. For example, an editor wants to use a 320s song to fit a 280s animation or to accompany a 265s radio advertisement. Current music resizing approach scales the whole piece of music in a uniform manner. However, it will degrade the effect of the compressed song and make perceptual artifacts. In this paper, a novel music resizing approach, called LyDAR (LYrics Density based Approach to non-homogeneous music Resizing), is proposed, in which the resizing operation is guided by music structural analysis. Firstly, a useful concept, lyrics density, is presented, which takes advantage of lyrics to analyze the musical structure and can be used to describe the compression-resistance for different parts of a song. Secondly, two music resizing scheduling algorithms, LDF and LDGF, are developed to schedule compression over different parts of a music piece. Finally, both subjective and objective experiments are conducted to show that LyDAR can effectively and efficiently generate compressed versions of songs with good quality.