Utilizing multiple descriptions/views of an object is often useful in image clustering tasks. Despite many works that have been proposed to effectively cluster multi-view data, there are still unaddressed problems such as the errors introduced by the traditional spectral-based clustering methods due to the two disjoint stages: 1) eigendecomposition and 2) the discretization of new representations. In this paper, we propose a unified clustering framework which jointly learns the two stages together as well as utilizing multiple descriptions of the data. More specifically, two learning methods from this framework are proposed: 1) through a graph construction from different views and 2) through combining multiple graphs. Furthermore, benefiting from the separability and local graph preserving properties of the proposed methods, a novel unsupervised automatic attribute discovery method is proposed. We validate the efficacy of our methods on five data sets, showing that the proposed joint learning clustering methods outperform the recent state-of-the-art methods. We also show that it is possible to derive a novel method to address the unsupervised automatic attribute discovery tasks.

It is our great pleasure to introduce you to the technical program of the 22 nd International Conference on Pattern Recognition (ICPR2014). The technical program has been compiled using a high-quality peer-review process. After the paper deadline, the papers were distributed to the Area Chairs by the Track Chairs. This year, since some tracks had more submissions than expected, we recruited additional Area Chairs after the deadline in order to keep the review quality high. We also recruited an additional Track Chair in order to balance work load. Area Chairs assigned each paper to at least three reviewers and made the review summary reports. The Track Chairs together with the Program Chairs made the decision of acceptance based on the Area Chairs' reports. All decisions were made on at least two reviews and a summary report, most decisions on three reviews and the summary report. Finally, the Track Chairs composed the sessions, and the Program Chairs scheduled them and assigned rooms. The papers submitted by Program Chairs and Track Chairs were handled in a special Track, without influence from these. This year we also increased the number of pages for each paper from 4 to 6 in order to further increase the scientific quality of the conference by enabling the authors to explain their research in more detail.All of this review process is the result of dedicated hard work by members of various conference committees and additional volunteers, and we would like to thank all of them for their generous efforts. Especially, we gratefully acknowledge the fundamental contribution of the Track Chairs and Area Chairs, who directly supervised the review process carried out by 89 Area Chairs and more than 1,300 reviewers, who timely delivered high-quality reviews and decision reports. This year we received a total of 1,409 paper submissions from 46 countries. 198 papers were accepted as oral presentations and 594 papers were accepted as poster presentations. We arranged 42 sessions for oral presentations and 11 poster sessions. This year, we gave the poster presenters the opportunity to submit a one-page teaser in power-point and they were broadcasted on the monitors in the conference center. We organized two prize lectures and five invited talks, including articles in the proceedings.We expect this conference to be very lively and exciting form for all of us to meet, inspire and be inspiring in many presentations and discussions. We wish you a memorable stay in Stockholm.

Demand response (DR) can provide a cost-effect approach for reducing peak loads while renewable energy sources (RES) can result in an environmental-friendly solution for solving the problem of power shortage. The increasingly integration of DR and renewable energy bring challenging issues for energy policy makers, and electricity market regulators in the main power grid. In this paper, a new two-stage stochastic game model is introduced to operate the electricity market, where Stochastic Stackelberg-Cournot-Nash (SSCN) equilibrium  is applied to characterize the optimal energy bidding strategy of the forward market and the optimal energy trading strategy of the spot market. To obtain a SSCN equilibrium, sampling average approximation (SAA) technique is harnessed to address the stochastic game model in a distributed way. By this game model, the participation ratio of demand response can be significantly increased while the unreliability of power system caused by renewable energy resources can be considerably reduced. The effectiveness of proposed model is illustrated by extensive simulations.

No abstract

Automatic video keyword generation is one of the key ingredients in reducing the burden of security officers in analyzing surveillance videos. Keywords or attributes are generally chosen manually based on expert knowledge of surveillance. Most existing works primarily aim at either supervised learning approaches relying on extensive manual labelling or hierarchical probabilistic models that assume the features are extracted using the bag-of-words approach; thus limiting the utilization of the other features. To address this, we turn our attention to automatic attribute discovery approaches. However, it is not clear which automatic discovery approach can discover the most meaningful attributes. Furthermore, little research has been done on how to compare and choose the best automatic attribute discovery methods. In this paper, we propose a novel approach, based on the shared structure exhibited amongst meaningful attributes, that enables us to compare between different automatic attribute discovery approaches. We then validate our approach by comparing various attribute discovery methods such as PiCoDeS on two attribute datasets. The evaluation shows that our approach is able to select the automatic discovery approach that discovers the most meaningful attributes. We then employ the best discovery approach to generate keywords for videos recorded from a surveillance system. This work shows it is possible to massively reduce the amount of manual work in generating video keywords without limiting ourselves to a particular video feature descriptor.

No abstract

Automatic attribute discovery methods have gained in popularity to extract sets of visual attributes from images or videos for various tasks. Despite their good performance in some classification tasks, it is difficult to evaluate whether the attributes discovered by these methods are meaningful and which methods are the most appropriate to discover attributes for visual descriptions. In its simplest form, such an evaluation can be performed by manually verifying whether there is any consistent identifiable visual concept distinguishing between positive and negative exemplars labelled by an attribute. This manual checking is tedious, expensive and labour intensive. In addition, comparisons between different methods could also be problematic as it is not clear how one could quantitatively decide which attribute is more meaningful than the others. In this paper, we propose a novel attribute meaningfulness metric to address this challenging problem. With this metric, automatic quantitative evaluation can be performed on the attribute sets; thus, reducing the enormous effort to perform manual evaluation. The proposed metric is applied to some recent automatic attribute discovery and hashing methods on four attribute-labelled datasets. To further validate the efficacy of the proposed method, we conducted a user study. In addition, we also compared our metric with a semi-supervised attribute discover method using the mixture of probabilistic PCA. In our evaluation, we gleaned several insights that could be beneficial in developing new automatic attribute discovery methods.

Electrical distribution poles are important assets in electricity supply. These poles need to be maintained in good condition to ensure they protect community safety, maintain reliability of supply, and meet legislative obligations. However, maintaining such a large volumes of assets is an expensive and challenging task. To address this, recent approaches utilise imagery data captured from helicopter and/or drone inspections. Whilst reducing the cost for manual inspection, manual analysis on each image is still required. As such, several image-based automated inspection systems have been proposed. In this paper, we target two major challenges: tiny object detection and extremely imbalanced datasets, which currently hinder the wide deployment of the automatic inspection. We propose a novel two-stage zoom-in detection method to gradually focus on the object of interest. To address the imbalanced dataset problem, we propose the resampling as well as reweighting schemes to iteratively adapt the model to the large intra-class variation of major class and balance the contributions to the loss from each class. Finally, we integrate these components together and devise a novel automatic inspection framework. Extensive experiments demonstrate that our proposed approaches are effective and can boost the performance compared to the baseline methods.