Air pollution is becoming a serious issue that threatens everyone's daily life. Accordingly how to measure the local air quality easily and quickly becomes an urgent problem. Sensor-based methods are relatively expensive, and image based air quality measurement is a promising direction as it is often less cost. Meanwhile web service of precise air quality measurement is of great importance as it allows to timely monitor the air pollution and can provide recommendations for decision makers. This paper devises an effective web service to address this challenging problem. Specifically we offer a service letting mobile device users to upload photos taken outdoor with meta information. Once the background web service computation is finished, we return the air quality level at their location to the users. In our service system, it includes three basic modules: 1) using GPS location information to get the basic air quality value from the nearest official air quality station, 2) using photo by our air quality assessment based on dictionary learning for image representation to compute air quality. In this method we add ℓ21norm to the target function to promote the nonzero coefficients of the words aggregate within similar quality level, 3) using photo uploaded by user by our CNN based photo air pollution estimation method to obtain the air quality estimation. Finally we combine the above three estimations to reach the final estimation to the end users. Empirical experiments are conducted on the real-world dataset that collaborates the efficacy of our method.

Air quality has become a major global concern for human beings involving all social stratums, for both developing and developed countries. Web service of precise and early air pollution forecasting is of great importance as it allows people to pro-actively take preventative and protective measurements. As an endeavor on the course of machine learning based air quality forecasting, this paper presents an initiative and its technological details in solving this challenging problem. Specifically, this work involves three major highlights regarding with both algorithmic innovation and deployment with its impact: 1) We propose a multi-channel ensemble learning framework, 2) We propose a new supervised feature learning and extraction method, i.e. sufficient statistics feature mapping based on Deep Boltzman Machine, which serves as a building block for our learning system, 3) We target our air pollution prediction method to the city of Beijing, China as it is at the forefront for battling against air pollution, which is embodied as a web service for prediction. Extensive experiments of real time air pollution forecasting on the real-world data demonstrates the effectiveness of the proposed method and value of the deployed web service system.

Air pollution has raised people's intensive concerns especially in developing countries such as China and India. Different from using expensive or unreliable methods like sensor-based or social network based one, photo based air pollution estimation is a promising direction, while little work has been done up to now. Focusing on this immediate problem, this paper devises an effective convolutional neural network to estimate air's quality based on photos. Our method is comprised of two ingredients: first a negative log-log ordinal classifier is devised in the last layer of the network, which can improve the ordinal discriminative ability of the model. Second, as a variant of the Rectified Linear Units (ReLU), a modified activation function is developed for photo based air pollution estimation. This function has been shown it can alleviate the vanishing gradient issue effectively. We collect a set of outdoor photos and associate the pollution levels from official agency as the ground truth. Empirical experiments are conducted on this real-world dataset which shows the capability of our method.

Distance metric learning (DML) is successful in discovering intrinsic relations in data. However, most algorithms are computationally demanding when the problem size becomes large. In this paper, we propose a discriminative metric learning algorithm, develop a distributed scheme learning metrics on moderate-sized subsets of data, and aggregate the results into a global solution. The technique leverages the power of parallel computation. The algorithm of the aggregated DML (ADML) scales well with the data size and can be controlled by the partition. We theoretically analyze and provide bounds for the error induced by the distributed treatment. We have conducted experimental evaluation of the ADML, both on specially designed tests and on practical image annotation tasks. Those tests have shown that the ADML achieves the state-of-the-art performance at only a fraction of the cost incurred by most existing methods.

Automatic annotation of digital pictures is a key technology for managing and retrieving images from large image collections. Typical algorithms only deal with the problem of monolingual image annotation. In this paper, we propose a framework to deal with the problem of multilingual image annotation, which can annotate images in multiple languages. The framework can not only benefit users with different native languages, but also provide more accurate annotations. In this framework, image annotation is performed in two stages, including parallel monolingual image annotation and the fusion of annotation results in multiple languages. In the first stage, candidate annotations for each language are extracted by leveraging multilingual large scale Web image database. Due to the incompleteness and inaccuracy problem of candidate annotations, we proposed a multilingual annotation fusion algorithm (MAF). By modeling candidate annotations for each language as an n-partite graph, MAF algorithm can improve and re-rank multilingual annotations. Finally, annotations with the highest ranking values in each language are selected and translated as the result. Experimental results for English-Chinese image annotations demonstrate the effectiveness of the proposed framework.

In image annotation refinement, word correlations among candidate annotations are used to reserve high relevant words and remove irrelevant words. Existing methods build word correlations on textual annotations of images. In this paper, visual contents of images are utilized to explore better word correlations by using multi-graph similarity reinforcement method. Firstly, image visual similarity graph and word correlations graph are built respectively. Secondly, the two graphs are iteratively reinforced by each other through image-word transfer matrix. Once the two graphs converge to steady states, the new word correlations graph is used to refine the candidate annotations. The experiments show that our method performs better than method not considering visual content of images.

In this paper, we proposed an image ranking model called SocialRank for web image search engine, which leverages rich metadata and structures of virtual communities in online photo-sharing sites in Web 2.0. In SocialRank, three levels of static rankings for sites, users and images are computed, respectively. To achieve combined image rankings in a site, a graph model is proposed to integrate social relations between users and images to reinforce their static rankings. To obtain the unified image rankings of different sites, image rankings are normalized and combined by considering duplicate images and static site rankings. The diversity of search results is also an important factor of image search engines. So we proposed an offline static diversity ranking of images. The experimental results show that the proposed SocialRank performs comparably with Google Image Search.

Web image annotation is a very important method to effectively index and search images on the internet. Many web image annotation approaches utilized not only the visual information but also the texts emerged with web image. However, they failed to utilize the whole relations among annotations, which reflect the specific semantic content of images. In this paper we propose a novel Multi-Progressive Model (MPM) for web image annotation that leverages word correlations between available texts of web images and an automatic-built vocabulary. The proposed approach treat the available text of web images as initial annotations, and extend them by using a pre-defined lexicon to include more words which are potentially relevant to the target image. It then rank initial and extended annotations by taking advantage of whole words relations without bringing huge computation. The multi-progressive model can be viewed as a greedy optimization algorithm that approximately optimizes the joint annotation probability in a progressive way. Experimental results on web images demonstrate the effectiveness of the proposed model.

Automatic image annotation is an effective way for managing and retrieving abundant images on the internet. In this paper, we propose a novel search-based method for web image annotation. Firstly, surrounding text and other textual information in the hosting web pages are used as the candidate annotations. As the candidates are very noisy, two measures are defined to re-rank them and only top-ranked ones are reserved as the final annotations. One measure is based on the visual consistence between the given image and the image search results when the candidate annotation is submitted as a query. The other measure is based on the textual consistence between one candidate and others, which is calculated from the pairwise co-occurrence using image search engines. Finally, Dempster-Shafer multiple evidence combination approach is used to combine the visual and textual measures for the final ranking. Experimental results on web images demonstrate the effectiveness of the proposed method.

Automatic image annotation is an effective way for managing and retrieving abundant images on the internet. In this paper, a bipartite graph reinforcement model (BGRM) is proposed for web image annotation. Given a web image, a set of candidate annotations is extracted from its surrounding text and other textual information in the hosting web page. As this set is often incomplete, it is extended to include more potentially relevant annotations by searching and mining a large-scale image database. All candidates are modeled as a bipartite graph. Then a reinforcement algorithm is performed on the bipartite graph to re-rank the candidates. Only those with the highest ranking scores are reserved as the final annotations. Experimental results on real web images demonstrate the effectiveness of the proposed model.