Tiejian Luo

Query-biased learning to rank for real-time twitter search

By incorporating diverse sources of evidence of relevance, learning to rank has been widely applied to real-time Twitter search, where users are interested in fresh relevant messages. Such approaches usually rely on a set of training queries to learn a general ranking model, which we believe that the benefits brought by learning to rank may not have been fully exploited as the characteristics and aspects unique to the given target queries are ignored. In this paper, we propose to further improve the retrieval performance of learning to rank for real-time Twitter search, by taking the difference between queries into consideration. In particular, we learn a query-biased ranking model with a semi-supervised transductive learning algorithm so that the query-specific features, e.g. the unique expansion terms, are utilized to capture the characteristics of the target query. This query-biased ranking model is combined with the general ranking model to produce the final ranked list of tweets in response to the given target query. Extensive experiments on the standard TREC Tweets11 collection show that our proposed query-biased learning to rank approach outperforms strong baseline, namely the conventional application of the state-of-the-art learning to rank algorithms.

Unified Saliency Detection Model Using Color and Texture Features.

Saliency detection attracted attention of many researchers and had become a very active area of research. Recently, many saliency detection models have been proposed and achieved excellent performance in various fields. However, most of these models only consider low-level features. This paper proposes a novel saliency detection model using both color and texture features and incorporating higher-level priors. The SLIC superpixel algorithm is applied to form an over-segmentation of the image. Color saliency map and texture saliency map are calculated based on the region contrast method and adaptive weight. Higher-level priors including location prior and color prior are incorporated into the model to achieve a better performance and full resolution saliency map is obtained by using the up-sampling method. Experimental results on three datasets demonstrate that the proposed saliency detection model outperforms the state-of-the-art models.

A Ranked-Based Learning Approach to Automated Essay Scoring

Automated essay scoring is the computer techniques and algorithms that evaluate and score essays automatically. Compared with human rater, automated essay scoring has the advantage of fairness, less human resource cost and timely feedback. In previous work, automated essay scoring is regarded as a classification or regression problem. Machine learning techniques such as K-nearest-neighbor (KNN), multiple linear regression have been applied to solve this problem. In this paper, we regard this problem as a ranking problem and apply a new machine learning method, learning to rank, to solve this problem. We will introduce detailed steps about how to apply learning to rank to automated essay scoring, such as feature extraction, scoring. Experiments in this paper show that learning to rank outperforms other classical machine learning techniques in automated essay scoring.

Note: A manifold ranking based saliency detection method for camera

Research focused on salient object region in natural scenes has attracted a lot in computer vision and has widely been used in many applications like object detection and segmentation. However, an accurate focusing on the salient region, while taking photographs of the real-world scenery, is still a challenging task. In order to deal with the problem, this paper presents a novel approach based on human visual system, which works better with the usage of both background prior and compactness prior. In the proposed method, we eliminate the unsuitable boundary with a fixed threshold to optimize the image boundary selection which can provide more precise estimations. Then, the object detection, which is optimized with compactness prior, is obtained by ranking with background queries. Salient objects are generally grouped together into connected areas that have compact spatial distributions. The experimental results on three public datasets demonstrate that the precision and robustness of the proposed algorithm have been improved obviously.

A survey of learning to rank for real-time twitter search

Recently learning to rank has been widely used in real-time Twitter Search by integrating various of evidence of relevance and recency features into together. In real-time Twitter search, whereby the information need of a user is represented by a query at a specific time, users are interested in fresh messages. In this paper, we introduce a new ranking strategy to rerank the tweets by incorporating multiple features. Besides, an empirical study of learning to rank for real-time Twitter search is conducted by adopting the state-of-the-art learning to rank approaches. Experiments on the standard TREC Tweets11 collection show that both the listwise and pairwise learning to rank methods outperform baselines, namely the content-based retrieval models.

Selecting Training Data for Learning-Based Twitter Search

Learning to rank is widely applied as an effective weighting scheme for Twitter search. As most learning to rank approaches are based on supervised learning, their effectiveness can be affected by the inclusion of low-quality training data. In this paper, we propose a simple and effective approach that learns a query quality classifier, which automatically selects the training data on a per-query basis. Experimental results on the TREC Tweets13 collection show that our proposed approach outperforms the conventional application of learning to rank that learns the ranking model on all training queries available.

Clustering-based transduction for learning a ranking model with limited human labels

Transductive learning is a semi-supervised learning paradigm that can leverage unlabeled data by creating pseudo labels for learning a ranking model, when there is only limited or no training examples available. However, the effectiveness of transductive learning in information retrieval (IR) can be hindered by the low quality pseudo labels. To this end, we propose to incorporate a two-step k-means clustering algorithm to select the high quality training queries for generating the pseudo labels. In particular, the first step selects the high-quality queries for which the relevant documents are highly coherent as indicated by the clustering results. The second step then selects the initial training examples for the transductive learning that iteratively aggregating the pseudo examples. Finally, the learning to rank (LTR) algorithms are applied to learn the ranking model using the pseudo training examples created by the transductive learning process. Our proposed approach is particularly suitable for applications where there is only little or no human labels available as it does not necessarily involve the use of relevance assessments information or human efforts. Experimental results on the standard TREC Tweets11 collection show that our proposed approach outperforms strong baselines, namely the conventional applications of learning to rank algorithms using human labels for the training and transductive learning using all the queries available.

A Novel Illumination Compensation Method with Enhanced Retinex

Illumination compensation is a typical way for increasing the performance of image processing. Retinex algorithm compensates illumination work properly, however, it cannot deal with color constancy of images appropriately. This paper proposes a novel illumination compensation method by converting the image from RGB color space to HSI color space, and with I component enhanced by Retinex algorithm and S component adjusted adaptively in accordance with correlation coefficients. Experimental results show that our method can not only maintain the color of images when the color space conversion from HIS to RGB, but also get better image quality with enhanced brightness, contrast and information. It has the trait of upholding the color constancy.

MLPF algorithm for tracking fast moving target against light interference

In order to deal with the difficulty of tracking the fast moving aerial targets with light interference, we propose an improved particle tracking algorithm named multi-layers particle filter (MLPF). In MLPF, the particles are divided into three categories: the main particles (M-particles), the subordinate particles (S-particles) and the regenerate particles (R-particles). In the phase of resampling and state estimating, only M-particles are involved, then the R-particles are generated and considered as new S-particles in the next cycle. To a certain extent, our algorithm maintains the diversity of particles and reduces the computation time. Besides, MLPF has significant improvements on overcoming the tracing error after the sudden disappearance of the target and solving the degradation of particles. We demonstrate effectiveness of our proposed algorithm through systematic experiments. Experimental results show MLPF has better tracking effect compared to the traditional particle filter (PF) when the target is moving fast and affected by light interference. In the first experiment, the running time has been reduced from 47s to 21s while the precision increased from 64% to 96%. And for the second experiment, the running time has been reduced from 237s to 121s while precision increased from 46% to 89%.

Training query filtering for semi-supervised learning to rank with pseudo labels

Semi-supervised learning is a machine learning paradigm that can be applied to create pseudo labels from unlabeled data for learning a ranking model, when there is only limited or no training examples available. However, the effectiveness of semi-supervised learning in information retrieval (IR) can be hindered by the low quality pseudo labels, hence the need for the training query filtering that removes the low quality queries. In this paper, we assume two application scenarios with respect to the availability of human labels. First, for applications without any labeled data available, a clustering-based approach is proposed to select the high quality training queries. This approach selects the training queries following the empirical observation that the relevant documents of high quality training queries are highly coherent. Second, for applications with limited labeled data available, a classification-based approach is proposed. This approach learns a weak classifier to predict the retrieval performance gain of a given training query by making use of query features. The queries with high performance gains are selected for the following transduction process to create the pseudo labels for learning to rank algorithms. Experimental results on the standard LETOR dataset show that our proposed approaches outperform the strong baselines.