Light field (LF) cameras record both intensity and directions of light rays in a scene with a single exposure. Due to the trade-off between spatial and angular dimensions, the spatial resolution of LF images is limited, so super-resolution is widely studied. Pixels follow linear coordinate projection across views in LF images. Hence, auxiliary views nearer to the target view are generally more effective for use in super-resolution. In this paper, an LF-pyramid is proposed based on an angular-distance constraint for discriminatively exploiting auxiliary views. From views of different layers in an LF-pyramid, complementary features of different effectiveness can be extracted. However, shapes of LF-pyramids change for target views with different angular positions. To fully exploit an LF-pyramid, we introduce a pyramid-angular-constraint network for LF super-resolution (LF-PACNet). Specifically, to handle an arbitrary number of views in each layer, an intra-pyramid-layer feature extraction module is designed, which treats all views in the same layer equally in complementary information extraction. Then, to deal with an arbitrary number of layers, a recurrent cross-pyramid-layer feature complementation module is constructed, which discriminatively complements the target view with high-frequency details. Extensive experiments on public datasets demonstrate state-of-the-art performance for our method, both visually and numerically, especially for datasets with large disparities.

Automated breast ultrasound (ABUS) has emerged as a promising tool for breast lesion detection, but most existing deep learning models for ABUS lack transparency and fail to align with clinical reasoning processes. This limits their interpretability and hinders clinical adoption. Therefore, we propose 3D-IRMM-Net, a radiologist-mimicking 3D multimodal network. It integrates visual, textual, and semantic cues to emulate hierarchical diagnostic reasoning. At its core, the network integrates two novel components: the 3D Scale-Expert Convolution (3D-SEC) block, which enables parameter-efficient, topology-aware feature routing via a shared graph convolutional layer; and the Adaptive Spatial-Gaussian (ASG) block, which enhances lesion localization in ABUS by modeling spatial dependencies through multi-scale Gaussian attention. In addition, we propose LLM-Vision activator, a natural-language-driven mechanism that uses language to guide 3D visual attention activation and enables 3D spatial-perceptual feature learning via a pretrained 2D VLM, boosting training efficiency. By aligning AI inference with clinical workflows, 3D-IRMM-Net enhances both detection rates and interpretability. Extensive experiments on ABUS2025, TDSC-ABUS2023, and FPHXD-ABUS datasets confirm its state-of-the-art performance across multiple metrics. At an FPPI of 0.5, our method achieved a patient-level detection rates of 89.7±1.1% (internal) and 85.1±2.0% (external); at an FPPI of 4, they rose to 96.1±1.6% and 91.5 ±1.9%, respectively. Furthermore, the model provides principled uncertainty quantification, improving trustworthiness in real-world deployment. These results confirm the effectiveness of 3D-IRMM-Net in bridging the gap between AI-driven detection and clinical practice.

Breast cancer significantly affects women's health, making early and accurate diagnosis through ultrasound examination essential. However, automated breast ultrasound(ABUS) lesion detection models encounter challenges, including uncertain noise and difficulties in locating small lesions. This paper proposes SUA-MT, a multi-video object detection network using uncertainty-aware transformers and temporal-spatial mamba. To address the performance degradation caused by low-quality frames and noise interference in input data, we propose the uncertainty-gated transformer decoder (UGTD), which dynamically adjusts attention weights to focus on high-confidence regions while suppressing attention to redundant areas. The spatialtemporal(ST) mamba module is designed to model the long-term dependencies and 3D spatial features of different plane video frames, making full use of temporal and spatial information. In general, SUA-MT not only supports dynamic video length input, but also combines multidimensional video modeling of lesions (transverse, sagittal and coronal plane), making full use of the complementarity of multi-view information and spatiotemporal information to enhance the ability to locate small lesions. Experimental results on a combined set of internal and publicly datasets demonstrate that the SUA-MT method achieves state-of-the-art performance compared to existing video detection approaches. Specifically, SUA-MT attains a mean precision of 80.1 % and mean recall of 84.2 %, providing an efficient and robust solution for lesion detection in ABUS.

The task of detecting three-dimensional objects using only RGB images presents a considerable challenge within the domain of computer vision. The core issue lies in accurately performing epipolar geometry matching between multiple views to obtain latent geometric priors. Existing methods establish correspondences along epipolar line features in voxel space through various layers of convolution. However, this step often occurs in the later stages of the network, which limits overall performance. To address this challenge, we introduce a novel framework, ImVoxelENet, that integrates a geometric epipolar constraint. We start from the back-projection of pixel-wise features and design an attention mechanism that captures the relationship between forward and backward features along the ray for multiple views. This approach enables the early establishment of geometric correspondences and structural connections between epipolar lines. Using ScanNetV2 as a benchmark, extensive comparative and ablation experiments demonstrate that our proposed network achieves a 1.1% improvement in mAP, highlighting its effectiveness in enhancing 3D object detection performance. Our code is available at https://github.com/xug-coder/ImVoxelENet.

Collaborative filtering (CF) is an essential technique in recommender systems that provides personalized recommendations by only leveraging user-item interactions. However, most CF methods represent users and items as fixed points in the latent space, lacking the ability to capture uncertainty. While probabilistic embedding is proposed to intergrate uncertainty, they suffer from several limitations when introduced to graph-based recommender systems. Graph convolutional network framework would confuse the semantic of uncertainty in the nodes, and similarity measured by Kullback–Leibler (KL) divergence suffers from degradation problem and demands an exponential number of samples. To address these challenges, we propose a novel approach, called the Wasserstein dependent Graph ATtention network (W-GAT), for collaborative filtering with uncertainty. We utilize GAT and Wasserstein distance to learn Gaussian embedding for each user and item. Additionally, our method incorporates Wasserstein-dependent mutual information further to increase the similarity between positive pairs. Experimental results on three benchmark datasets show the superiority of W-GAT compared to several representative baselines. Extensive experimental analysis validates the effectiveness of W-GAT in capturing uncertainty by modeling the range of user preferences and categories associated with items.

Collaborative Filtering (CF) models based on Graph Contrastive Learning (GCL) have effectively improved the performance of long-tail recommendation. However, the popularity bias still presents a challenge in further enhancing their effectiveness. Some studies suggest that achieving better recommendations, particularly for the long-tail, requires learning representations with a more uniform distribution to implicitly mitigate popularity bias. Nevertheless, our analysis of various CF models reveals that different models exhibit varying abilities in capturing popularity and those with superior performance might encode more popularity information in item representations. This raises a question: Does encoding popularity always lead to harmful bias? We speculate that superior recommendations may emerge from leveraging the encoded popularity information to optimize the representations of users and items rather than eliminating its existence in representations. This motivates a data augmentation approach, wherein we generate augmented samples by mixing representations of items with different popularity levels and explicitly debias using the encoded popularity information which is often neglected. Additionally, we propose an adaptive contrastive loss, leveraging structural information and unifying the recommendation and contrastive learning objectives, which adaptively re-weights positive samples and ensures the capture of item popularity. Our proposed framework remains scalable without requiring multiple forward computations throughout the entire graph. Extensive experiments demonstrate improvements in both overall and long-tail recommendation performance.

Stereo vision is widely studied for depth information extraction. However, occlusion and noise pose significant challenges to traditional methods due to failure in photo consistency. In this paper, an occlusion and noise-aware stereo framework named ONAF is proposed to get a robust depth estimation by integrating the advantages of correspondence cues and refocusing cues from light field(LF). ONAF consists of two special depth cue extractors: correspondence depth cue extractor (CCE) and refocusing depth cue extractor (RCE). CCE extracts accurate correspondence depth cues in occlusion areas based on multi-direction Ray-Epipolar Plane Images(Ray-EPIs) from LF, which are more robust than traditional multi-direction EPIs. RCE generates accurate refocusing depth cues in noise areas, benefitting from the many-to-one integration strategy and the directional perception of texture and occlusion based on multi-direction focal stacks from LF. Attention mechanism is introduced to complementarily fuse CCE and RCE to generate optimum depth maps. The experimental results prove the effectiveness of ONAF, which outperforms state-of-the-art disparity estimation methods, especially in occlusion and noise areas.

Explanations play an essential role in helping users evaluate results from recommender systems. Various natural language generation methods have been proposed to generate explanations for the recommendation. However, they usually suffer from two problems. First, since user-provided review text contains noisy data, the generated explanations may be irrelevant to the recommended items. Second, as lacking some supervision signals, most of the generated sentences are similar, which cannot meet the diversity and personalized needs of users. To tackle these problems, we propose a multimodal contrastive transformer (MMCT) model for an explainable recommendation, which incorporates multimodal information into the learning process, including sentiment features, item features, item images, and refined user reviews. Meanwhile, we propose a dynamic fusion mechanism during the decoding stage, which generates supervision signals to guide the explanation generation. Additionally, we develop a contrastive objective to generate diverse explainable texts. Comprehensive experiments on two real-world datasets show that the proposed model outperforms comparable explainable recommendation baselines in terms of explanation performance and recommendation performance. Efficiency analysis and robustness analysis verify the advantages of the proposed model. While ablation analysis establishes the relative contributions of the respective components and various modalities, the case study shows the working of our model from an intuitive sense.

Recommender systems usually learn user interests from various user behaviors, including clicks and postclick behaviors (e.g., like and favorite, which reflects the true interests of users). However, these behaviors inevitably exhibit popularity bias, leading to some unfairness issues: 1) for items with similar quality, more popular ones get more exposure; and 2) even worse the popular items with lower popularity might receive more exposure. Existing work on mitigating popularity bias blindly eliminates the bias and usually ignores the effect of item quality. We argue that the relationships between different user behaviors (e.g., conversion rate) actually reflect the item quality. Therefore, to handle the unfairness issues, we propose to mitigate the popularity bias by considering multiple user behaviors. In this work, we examine causal relationships behind the interaction generation procedure in multibehavior recommendation. Specifically, we find that: 1) item popularity is a confounder between the exposed items and users’ postclick interactions, leading to the exposure unfairness; and 2) some hidden confounders (e.g., the reputation of item producers) affect both item popularity and quality, resulting in the quality unfairness. To alleviate these confounding issues, we propose a causal framework to estimate the causal effect, which leveragesbackdoor adjustmentto block the backdoor paths caused by the confounders. In the inference stage, we remove the negative effect of popularity and utilize the good effect of quality for recommendation. Experiments on two real-world datasets validate the effectiveness of our proposed framework, which enhances fairness without sacrificing recommendation accuracy on postclick behavior.

Collaborative filtering (CF) is the basic method for recommendation with implicit feedback. Recently, various state-of-the-art CF integrates graph neural networks. However, they often suffer from popularity bias, causing recommendations to deviate from users' genuine preferences. Additionally, several contrastive learning methods based on the in-batch sample strategy have been proposed to train the CF model effectively, but they are prone to suffering from sample bias. To address this problem, debiased contrastive loss has been employed in the recommendation, but instead of personalized debiasing, it treats each user equally. In this paper, we propose a popularity-aware debiased contrastive loss for CF, which can adaptively correct the positive and negative scores based on the popularity of users and items. Our approach aims to reduce the negative impact of popularity and sample bias simultaneously. We theoretically analyze the effectiveness of the proposed method and reveal the relationship between popularity and gradient, which justifies the correction strategy. We extensively evaluate our method on three public benchmarks over balanced and imbalanced settings. The results demonstrate its superiority over the existing debiased strategies, not only on the entire datasets but also when segmenting the datasets based on item popularity.

Self-attention, which allows transformers to capture deep bidirectional contexts, plays a vital role in BERT-like pre-trained language models. However, the maximum likelihood pre-training objective of BERT may produce an anisotropic word embedding space, which leads to biased attention scores for high-frequency tokens, as they are very close to each other in representation space and thus have higher similarities. This bias may ultimately affect the encoding of global contextual information. To address this issue, we propose TOCOL, a TOken-Level COntrastive Learning framework for improving the contextual representation of pre-trained language models, which integrates a novel self-supervised objective to the attention mechanism to reshape the word representation space and encourages PLM to capture the global semantics of sentences. Results on the GLUE Benchmark show that TOCOL brings considerable improvement over the original BERT. Furthermore, we conduct a detailed analysis and demonstrate the robustness of our approach for low-resource scenarios.

Solving math word problems (MWPs) is a challenging task. Some existing solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions, and vice versa. Therefore, this work investigates the logical consistency among different problems and proposes a novel framework to solve math word problems following logically consistent templates. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method does learn the logical similarity between Questions and plays a crucial role in our model's nerformance.

Drug-target interaction (DTI) is an important task in drug discovery and drug repurposing. Currently, most methods utilizing drug-based and protein-based similarity values to predict DTIs achieve promising results. However, calculating similarities for each pair of nodes is time-consuming, especially for relatively large datasets. In this research, we propose a novel subgraph-oriented heterogeneous DTI identification method that transforms the DTI task from a link prediction task to a subgraph classification task. For each link, a local subgraph around this link is extracted. Then, a subgraph labeling process distinguishes different topologies of subgraphs. A random walk-based node representation generation is also integrated with the model. Finally, we apply a graph neural network for the subgraph classification. Our method avoids incorporating human-made similarity values by extracting more meaningful local subgraph topological information. Experimental studies for known DTI predictions on two DTI datasets show promising results for DTI prediction. Empirical results for new DTI predictions on two external public databases show the generalization ability of the proposed method.

Light field (LF) cameras record multiple perspectives by a sparse sampling of real scenes, and these perspectives provide complementary information. This information is beneficial to LF super-resolution (LFSR). Compared with traditional single-image super-resolution, LF can exploit parallax structure and perspective correlation among different LF views. Furthermore, the performance of existing methods are limited as they fail to deeply explore the complementary information across LF views. In this paper, we propose a novel network, called the light field complementary-view feature attention network (LF-CFANet), to improve LFSR by dynamically learning the complementary information in LF views. Specifically, we design a residual complementary-view spatial and channel attention module (RCSCAM) to effectively interact with complementary information between complementary views. Moreover, RCSCAM captures the relationships between different channels, and it is able to generate informative features for reconstructing LF images while ignoring redundant information. Then, a maximum-difference information supplementary branch (MDISB) is used to supplement information from the maximum-difference angular positions based on the geometric structure of LF images. This branch also can guide the process of reconstruction. Experimental results on both synthetic and real-world datasets demonstrate the superiority of our method. The proposed LF-CFANet has a more advanced reconstruction performance that displays faithful details with higher SR accuracy than state-of-the-art methods.

Abstract Person image generation aims to synthesize realistic person images that follow the same distribution as the given dataset. Previous attempts can be generally categorized into two classes: conditional GAN and unconditional GAN. The former usually uses pose information as condition to make pose transfer using GAN. The generated person have the same identity as the source person. The latter generates person images from scratch, and the real person images are only used as references for the discriminator. While conditional GAN is widely studied, unconditional GAN is also worth exploring because it can synthesize person image with new identity, which is a useful manner of data augmentation. These two types of generating methods have their different advantages and disadvantages, and sometimes they are complementary. This paper proposes a CoGAN to cooperatively train two types of GANs in an end‐to‐end framework. The two GANs serve different purposes, and can learn from each other during the cooperative learning procedure. The experimental results on public datasets show that the proposed CoGAN improves the performance of both baseline methods, and achieves competitive results compared with state‐of‐the‐art methods.

For an intelligent transportation system, multiple object tracking (MOT) is more challenging from the traditional static surveillance camera to mobile devices of the Internet of Things (IoT). To cope with this problem, previous works always rely on additional information from multivision, various sensors, or precalibration. Only based on a monocular camera, we propose a hybrid motion model to improve the tracking accuracy in mobile devices. First, the model evaluates camera motion hypotheses by measuring optical flow similarity and transition smoothness to perform robust camera trajectory estimation. Second, along the camera trajectory, smooth dynamic projection is used to map objects from image to world coordinate. Third, to deal with trajectory motion inconsistency, which is caused by occlusion and interaction of long time interval, tracklet motion is described by the multimode motion filter for adaptive modeling. Fourth, in tracklets association, we propose a spatiotemporal evaluation mechanism, which achieves higher discriminability in motion measurement. Experiments on MOT15, MOT17, and KITTI benchmarks show that our proposed method improves the trajectory accuracy, especially in mobile devices and our method achieves competitive results over other state-of-the-art methods.

Due to the lack of natural delimiters, most Chinese Named Entity Recognition (NER) approaches are character-based and utilize an external lexicon to leverage the word-level information. Although they have achieved promising results, the latent words they introduced are still non-contextualized. In this paper, we investigate three relations, i.e., adjacent relation between characters, character co-occurrence relation between latent words, and dependency relation among tokens, to address this issue. Specifically, we first establish the local context for latent words and then propose a masked self-attention mechanism to incorporate such local contextual information. Besides, since introducing external knowledge such as lexicon and dependency relation inevitably brings in some noises, we propose a gated information controller to handle this problem. Extensive experimental results show that the proposed approach surpasses most similar methods on public datasets and demonstrates its promising potential.

Retrieval Question Answering (ReQA) is an essential mechanism of information sharing which aims to find the answer to a posed question from large-scale candidates. Currently, the most efficient solution is Dual-Encoder which has shown great potential in the general domain, while it still lacks research on biomedical ReQA. Obtaining a robust Dual-Encoder from biomedical datasets is challenging, as scarce annotated data are not enough to sufficiently train the model which results in over-fitting problems. In this work, we first build ReQA BioASQ datasets for retrieving answers to biomedical questions, which can facilitate the corresponding research. On that basis, we propose a framework to solve the over-fitting issue for robust biomedical answer retrieval. Under the proposed framework, we first pre-train Dual-Encoder on natural language inference (NLI) task before the training on biomedical ReQA, where we appropriately change the pre-training objective of NLI to improve the consistency between NLI and biomedical ReQA, which significantly improve the transferability. Moreover, to eliminate the feature redundancies of Dual-Encoder, consistent post-whitening is proposed to conduct decorrelation on the training and trained sentence embeddings. With extensive experiments, the proposed framework achieves promising results and exhibits significant improvement compared with various competitive methods.

Biomedical factoid question answering is an essential application for biomedical information sharing. Recently, neural network based approaches have shown remarkable performance for this task. However, due to the scarcity of annotated data which requires intensive knowledge of expertise, training a robust model on limited-scale biomedical datasets remains a challenge. Previous works solve this problem by introducing useful knowledge. It is found that the interaction between question and answer (QA-interaction) is also a kind of knowledge which could help extract answer accurately. This research develops a knowledge distillation framework for biomedical factoid question answering, in which a teacher model as the knowledge source of QA-interaction is designed to enhance the student model. In addition, to further alleviate the problem of limited-scale dataset, a novel adversarial knowledge distillation technique is proposed to robustly distill the knowledge from teacher model to student model by constructing perturbed examples as additional training data. By forcing the student model to mimic the predicted distributions of teacher model on both original examples and perturbed examples, the knowledge of QA-interaction can be learned by student model. We evaluate the proposed framework on the widely used BioASQ datasets, and experimental results have shown the proposed method's promising potential.

Question answering (QA) plays a vital role in biomedical natural language processing. Among question answering tasks, the retrieval question answering (ReQA) aims to directly retrieve the correct answer from candidates and has attracted much attention in the community for its efficiency. Recently, researchers have introduced ReQA into the biomedical domain as BioReQA. Typically BioReQA models rely on the dual-encoder to gain semantic representation and are trained following the settings of dense retrieval. However, they normally utilize easy in-batch negative samples in training process to avoid the extra forwarding cost and GPU memory required by encoding additional negative samples. However, hard negative samples have been proved more important with regard to the overall performance of BioReQA tasks. Therefore in this research, we focus on effectively constructing hard in-batch negative samples. Inspired by the classic linear assignment problem, we propose an Iterative Linear Assignment Grouping (ILAG) algorithm to construct hard in-batch negative samples. To further enhance performance for given hard batches in a low-resource scenario, we also employ adversarial training to augment the difficulty of batches. Extensive experiments have shown our proposed method's promising potential in the area of biomedical retrieval question answering.

Recording activities of zebrafish is a fundamental task in biological research that aims to accurately track individuals and recover their real-world movement trajectories from multiple viewpoint videos. In this paper, we propose a novel online tracking solution based on a holistic perspective that leverages the correlation of appearance and location across views. It first reconstructs the 3D coordinates of targets frame by frame and then tracks them directly in 3D space instead of a 2D image plane. However, it is not trivial to implement such a solution which requires the association of targets across views and neighboring frames under occlusion and parallax distortion. To cope with that, we propose the view-invariant feature representation and the Kalman filter-based 3D state estimation, and combine the advantages of both to generate robust 3D trajectories. Extensive experiments on public datasets verify the efficiency and effectiveness of the approach.

Master tutors are important guides in the academic career of postgraduate students, so find and choose a suitable tutor is very important. However, the existing master tutor selection mode has many problems such as information asymmetry, which makes it difficult for students to make the most appropriate choice. With the construction of smart campus, more and more educational data are recorded, which makes it possible to conduct Educational Data Mining. In this paper, master tutors and students were respectively modeled, a master tutor recommendation method based on machine learning algorithms, such as TF-IDF, kNN and SVDCF was introduced. A real data set of our university was built and preprocessed. Specific recommendation algorithms were then designed. Experiments were conducted and acceptable Top-N hit rate results were achieved. The experimental results show that based on the modeling of students and master tutors, a lightweight combination of machine learning algorithms can achieve good practical results.

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing.However, the study of MoE components mostly focused on the feedforward layer in Transformer architecture.This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism.MoA includes a set of attention heads that each has its own set of parameters.Given an input, a router dynamically selects a subset of k attention heads per token.This conditional computation schema allows MoA to achieve stronger performance than the standard multi-head attention layer.Furthermore, the sparsely gated MoA can easily scale up the number of attention heads and the number of parameters while preserving computational efficiency.In addition to the performance improvements, MoA also automatically differentiates heads' utilities, providing a new perspective to discuss the model's interpretability.We conducted experiments on several important tasks, including Machine Translation and Masked Language Modeling.Experiments have shown promising results on several tasks against strong baselines that involve large and very deep models 1 .

The Knowledge Base Question Generation (KBQG) is an essential natural language processing task. Taking knowledge graph and answer entities as input, KBQG aims to generate corresponding natural language question. Recently Graph2Seq has been proposed to encode the knowledge graph and achieved remarkable results, while one important challenge still remains, i.e., the graph encoding lacks the interaction with the target question. To deal with the above challenge, we propose a graph and question interaction enhanced Graph2Seq model, in which we design an encoder-decoder parallel enhancement mechanism and apply the knowledge distillation for both inter-mediate representation and prediction distribution to employ the knowledge of the target question into the graph representation. Experiments have been conducted on KBQG benchmark dataset and experimental results have shown the promising potential of proposed method.

Personalized recommendation plays a central role in various online applications. To provide quality recommendation service, it is of crucial importance to consider multi-modal information associated with users and items, e.g., review text, description text, and images. However, many existing approaches do not fully explore and fuse multiple modalities. To address this problem, we propose a multi-modal contrastive pre-training model for recommendation. We first construct a homogeneous item graph and a user graph based on the relationship of co-interaction. For users, we propose intra-modal aggregation and inter-modal aggregation to fuse review texts and the structural information of the user graph. For items, we consider three modalities: description text, images, and item graph. Moreover, the description text and image complement each other for the same item. One of them can be used as promising supervision for the other. Therefore, to capture this signal and better exploit the potential correlation of intra-modalities, we propose a self-supervised contrastive inter-modal alignment task to make the textual and visual modalities as similar as possible. Then, we apply inter-modal aggregation to obtain the multi-modal representation of items. Next, we employ a binary cross-entropy loss function to capture the potential correlation between users and items. Finally, we fine-tune the pre-trained multi-modal representations using an existing recommendation model. We have performed extensive experiments on three real-world datasets. Experimental results verify the rationality and effectiveness of the proposed method.

Biomedical factoid question answering is an important task in biomedical question answering applications. It has attracted much attention because of its reliability. In question answering systems, better representation of words is of great importance, and proper word embedding can significantly improve the performance of the system. With the success of pretrained models in general natural language processing tasks, pretrained models have been widely used in biomedical areas, and many pretrained model-based approaches have been proven effective in biomedical question-answering tasks. In addition to proper word embedding, name entities also provide important information for biomedical question answering. Inspired by the concept of transfer learning, in this study, we developed a mechanism to fine-tune BioBERT with a named entity dataset to improve the question answering performance. Furthermore, we applied BiLSTM to encode the question text to obtain sentence-level information. To better combine the question level and token level information, we use bagging to further improve the overall performance. The proposed framework was evaluated on BioASQ 6b and 7b datasets, and the results have shown that our proposed framework can outperform all baselines.

Proper understanding of paragraph is essential for question generation task since the semantic interaction is complicated among sentences. How to integrate long text paragraph information into question generation is still a challenge. In this research, we proposed a multi-perspective paragraph context modeling mechanism, which firstly encodes the contextualized representation of input paragraph, and then utilize multi-head self-attention and Rezero network to further enhance paragraph-level feature extraction and context modeling. Finally, attention-based decoder with copy mechanism generates question according to encoded hidden states. Experimental study on widely used SQuAD dataset has shown the proposed method’s potential.

Generating on-topic responses and understanding the background information of context are both significant for dialogue generation. However, few works simultaneously concentrate on these two issues. For this purpose, we propose an open-domain topic-aware dialogue generation model via joint learning. We first design two-hop based static graph attention mechanism to enhance the semantic representations of context, and then two auxiliary sub-tasks are introduced. Topic Predictor module is designed to focus on the most pertinent topics and Language Modeling module further facilitates learning richer information from context. Experimental study has shown the proposed model’s promising potential. In particular, our model predicts the most topics that best match the query per response. Besides, further analysis proves that our model can generate more diversified and informative responses.

Recent progress in multi-object tracking (MOT) has shown great significance of a robust scoring mechanism for potential tracks. However, the lack of available data in MOT makes it difficult to learn a general scoring mechanism. Multiple cues including appearance, motion and etc., are limitedly utilized in current manual scoring functions. In this paper, we propose a Multiple Nodes Tracking (MNT) framework that adapts to most trackers. Based on this framework, a Recurrent Tracking Unit (RTU) is designed to score potential tracks through long-term information. In addition, we present a method of generating simulated tracking data without real data to overcome the defect of limited available data in MOT. The experiments demonstrate that our simulated tracking data is effective for training RTU and achieves state-of-the-art performance on both MOT17 and MOT16 benchmarks. Meanwhile, RTU can be flexibly plugged into classic trackers such as DeepSORT and MHT, and makes remarkable improvements as well.

Vehicle re-identification aims to associate images or videos of the same vehicle collected from different cameras. Many existing methods address the vehicle re-identification problem by explicitly learning distinguishable global features. However, vehicle attributes, i.e., logo category and orientation, play an indispensable role in identifying vehicles. In this paper, we first propose deep models to recognize vehicle attributes. Then, based on these attributes, we adopt a High Confidence Attribute Network (HCANet) to extract weighted global features. A comprehensive evaluation on the VehicleID dataset shows that our approach achieves competitive results.

BACKGROUND: Biomedical question answering (QA) is a sub-task of natural language processing in a specific domain, which aims to answer a question in the biomedical field based on one or more related passages and can provide people with accurate healthcare-related information. Recently, a lot of approaches based on the neural network and large scale pre-trained language model have largely improved its performance. However, considering the lexical characteristics of biomedical corpus and its small scale dataset, there is still much improvement room for biomedical QA tasks. RESULTS: Inspired by the importance of syntactic and lexical features in the biomedical corpus, we proposed a new framework to extract external features, such as part-of-speech and named-entity recognition, and fused them with the original text representation encoded by pre-trained language model, to enhance the biomedical question answering performance. Our model achieves an overall improvement of all three metrics on BioASQ 6b, 7b, and 8b factoid question answering tasks. CONCLUSIONS: The experiments on BioASQ question answering dataset demonstrated the effectiveness of our external feature-enriched framework. It is proven by the experiments conducted that external lexical and syntactic features can improve Pre-trained Language Model's performance in biomedical domain question answering task.

Vehicle reidentification, aiming at identifying vehicles across images, has drawn a lot of attention and has made significant achievements in recent years. However, vehicle reidentification remains a challenging task caused by severe appearance changes due to different orientations. In practice, the result of reidentification is greatly influenced by the pose of vehicles, and we call this influence as a pose barrier problem. One way to address the pose barrier problem is to train a feature representation that is invariant for various vehicle poses. To this end, we present pose robust features (PRFs) that contains two components: 1) pose-invariant features (PIFs) and 2) pose discriminative features (PDFs). On the one hand, PIF is the expert in exploring the overall characteristic of vehicles. When training PIF, we adopt an identity classifier as well as an orientation classifier. In addition, an adversarial loss is deployed in the PIF network. On the other hand, we design a PDF network, which has a similar architecture to the PIF network but can distinguish the difference between local details. The difference between PDF and PIF is that the network of training PDF does not apply the adversarial loss. Finally, by combining PIF and PDF, PRF has the advantages of the two features and can alleviate the influence of the pose barrier problem. Experiments are conducted on the VeRi-776 and VehicleID data sets. We show that PIF and PDF are complementary and that PRF produces competitive performance compared with state-of-the-art approaches.

Multiobject tracking is a basic task in video analysis. Due to the strict requirements on efficiency and resource consumption, most of the applications on edge devices are online or near-online methods. Besides motion modeling, appearance information is also widely used for tracking. However, the influence of occlusion is usually ignored. In this article, spatial-temporal co-occurrence constraints (STCCs) features are introduced to resist occlusions by exploring the rich spatial and temporal information of tracklets. In addition, a novel blockchain-based near-online framework called co-occurrence constraints tracklet tracker (CoCTs) is proposed for cross-camera tracking. It inherits the advantages of the blockchain technology in sharing information. Based on blockchain, an efficient association mechanism and a reliable information sharing method are introduced. Experimental results show that CoCT performs high computational efficiency and low resource consumption. In the edge computing environment, it achieves real-time performance on cross-camera tracking. On the MOT17 benchmark, our method shows the state-of-the-art results compared with other online trackers.

We consider the task of driver gaze prediction: estimating where the location of the focus of a driver should be, based on a raw video of the outside environment. In practice, we output a probability map that gives the normalized probability of each point in a given scene being the object of the driver attention. Most existing methods (i.e.,Coarse-to-FineandMulti-branch) take an image or a video as input and directly output the fixation map. While successful, these methods can often produce highly scattered predictions, rendering them unreliable for real-world usage. Motivated by this observation, we propose the reinforced attention (RA) model as a regulatory mechanism to increase prediction density. Our method is built directly on top of existing methods, making it complementary to current approaches. Specifically, we first useMulti-branchto obtain an initial fixation map. Then, RA is trained using deep reinforcement learning to learn a location prediction policy, producing a reinforced attention. Finally, in order to obtain the final gaze prediction result, we combine the fixation map and the reinforced attention by a mask-guided multiplication. Experimental results show that our framework improves the accuracy of gaze prediction, and provides state-of-the-art performance on the DR(eye)VE dataset.

Teaching machine to answer arbitrary questions is a long-term goal of natural language processing. In real dialogue corpus, informative words like named entities can often be infrequent and hard to model, and one primary challenge of dialogue system is how to promote the model's capability of generating high-quality responses with those informative words. In order to address this problem, we propose a novel pre-training based encoder-decoder model, which can enhance the multiturn dialogue response generation by incorporating external textual knowledge. We adopt BERT as encoder to merge external knowledge into dialogue history modeling, and a multi-head attention based decoder is designed to incorporate the semantic information from both knowledge and dialogue hidden representations into decoding process to generate informative and proper dialogue responses. Experiments on two response generation tasks indicate our model to be superior over competitive baselines on both automatic and human evaluations.

Person reidentification (ReID) is an important application of Internet of Things (IoT). ReID recognizes pedestrians across camera views at different locations and time, which is usually treated as a ranking task. An essential part of this task is the hard sample mining. Technically, two strategies could be employed, i.e., global hard mining and local hard mining. For the former, hard samples are mined within the entire training set, while for the latter, it is done in mini-batches. In literature, most existing methods operate locally. Examples include batch-hard sample mining and semihard sample mining. The reason for the rare use of global hard mining is the high computational complexity. In this article, we argue that global mining helps to find harder samples that benefit model training. To this end, this article introduces a new system to: 1) efficiently mine hard samples (positive and negative) from the entire training set and 2) effectively use them in training. Specifically, a ranking list network coupled with a multiplet loss is proposed. On the one hand, the multiplet loss makes the ranking list progressively created to avoid the time-consuming initialization. On the other hand, the multiplet loss aims to make effective use of the hard and easy samples during training. In addition, the ranking list makes it possible to globally and effectively mine hard positive and negative samples. In the experiments, we explore the performance of the global and local sample mining methods, and the effects of the semihard, the hardest, and the randomly selected samples. Finally, we demonstrate the validity of our theories using various public data sets and achieve competitive results via a quantitative evaluation.

In recent years, the demand for intelligent devices related to the Internet of Things (IoT) is rapidly increasing. In the field of computer vision, many algorithms have been preinstalled in IoT devices to achieve higher efficiency, such as face recognition, area detection, target tracking, etc. Tracking is an important but complex task that needs high efficiency solutions in real applications. There is a common assumption that detection can only represent one pedestrian to describe nonoverlapping in physical space. In fact, the pixels of the image do not exactly correspond to the positions in the real world. In order to overcome the limitation of this assumption, we remove this unreasonable assumption and present a novel idea that each detector response can have multiple labels to describe different targets at the same time. Therefore, we propose a graph-based method for near-online tracking in this article. We introduce a detection multiplexing method for tracking in the monocular image and propose a multiplex labeling graph (MLG) model. Each node in MLG has the ability to represent multiple targets. In addition, we improve the shortage of graph-based trackers in using temporal features. We construct long short-term memory networks to model motion and appearance features for MLG optimization. On the public multiobject tracking challenge benchmark, our near-online method gains satisfactory efficiency and achieves state-of-the-art results without additional private detection as well.

Biomedical event extraction plays an important role in the extraction of biological information from large-scale scientific publications. However, most state-of-the-art systems separate this task into several steps, which leads to cascading errors. In addition, it is complicated to generate features from syntactic and dependency analysis separately. Therefore, in this paper, we propose an end-to-end model based on long short-term memory (LSTM) to optimize biomedical event extraction. Experimental results demonstrate that our approach improves the performance of biomedical event extraction. We achieve average F1-scores of 59.68, 58.23, and 57.39 percent on the BioNLP09, BioNLP11, and BioNLP13's Genia event datasets, respectively. The experimental study has shown our proposed model's potential in biomedical event extraction.

Data association is one of the key research in tracking-by-detection framework. Due to frequent interactions among targets, there are various relationships among trajectories in crowded scenes which leads to problems in data association, such as association ambiguity, association omission, etc. To handle these problems, we propose hypothesis-testing based tracking (HTBT) framework to build potential associations between target by constructing and testing hypotheses. In addition, a spatio-temporal interaction graph (STIG) model is introduced to describe the basic interaction patterns of trajectories and test the potential hypotheses. Based on network flow optimization, we formulate offline tracking as a MAP problem. Experimental results show that our tracking framework improves the robustness of tracklet association when detection failure occurs during tracking. On the public MOT16, MOT17 and MOT20 benchmark, our method achieves competitive results compared with other state-of-the-art methods.

In this paper, we focus on the problem of novel view synthesis for vehicles. Some previous works solve the problem of novel view synthesis in a controlled 3D environment by exploiting additional 3D details (i.e., camera viewpoints and underlying 3D models). However, in real scenarios, the 3D details are difficult to obtain. In this case, we find that introducing vehicle pose to represent the views of vehicles is an alternative paradigm to solve the lack of 3D details. In novel view synthesis, preserving local details is one of the most challenging problems. To address this problem, we propose a perspective-aware generative model (PAGM). We are motivated by the prior that vehicles are made of quadrilateral planes. Preserving these rigid planes during image generation ensures that image details are kept. To this end, a classic image transformation method is leveraged,i.e., perspective transformation. In our GAN-based system, the perspective transformation is applied to the encoder feature maps, and the resulting maps are regarded as new conditions for the decoder. This strategy preserves the quadrilateral planes all the way through the network, thus shuttling the texture details from the input image to the generated image. In the experiments, we show that PAGM can generate high-quality vehicle images with fine details. Quantitatively, our method is superior to several competing approaches employing either GAN or the perspective transformation. Code is available at:https://github.com/ilvkai/view-synthesis-for-vehicles

Recently, most multiple object tracking (MOT) algorithms adopt the idea of tracking-by-detection. Relevant research shows that the performance of the detector obviously affects the tracker, while the improvement of detector is gradually slowing down in recent years. Therefore, trackers using tracklet (short trajectory) are proposed to generate more complete trajectories. Although there are various tracklet generation algorithms, the fragmentation problem still often occurs in crowded scenes. In this paper, we introduce an iterative clustering method that generates more tracklets while maintaining high confidence. Our method shows robust performance on avoiding internal identity switch. Then we propose a deep association method for tracklet association. In terms of motion and appearance, we construct motion evaluation network (MEN) and appearance evaluation network (AEN) to learn long-term features of tracklets for association. In order to explore more robust features of tracklets, a tracklet-based training mechanism is also introduced. Tracklet groups are used as the input of the networks instead of discrete detections. Experimental results show that our training method enhances the performance of the networks. In addition, our tracking framework generates more complete trajectories while maintaining the unique identity of each target as the same time. On the latest MOT 2017 benchmark, we achieve state-of-the-art results.

Recent years have witnessed the world-wide emergence of mega-metropolises with incredibly huge populations. Understanding residents mobility patterns, or urban dynamics, thus becomes crucial for building modern smart cities. In this paper, we propose a Neighbor-Regularized and context-aware Non-negative Tensor Factorization model (NR-cNTF) to discover interpretable urban dynamics from urban heterogeneous data. Different from many existing studies concerned with prediction tasks via tensor completion, NR-cNTF focuses on gaining urban managerial insights from spatial, temporal, and spatio-temporal patterns. This is enabled by high-quality Tucker factorizations regularized by both POI-based urban contexts and geographically neighboring relations. NR-cNTF is also capable of unveiling long-term evolutions of urban dynamics via a pipeline initialization approach. We apply NR-cNTF to a real-life data set containing rich taxi GPS trajectories and POI records of Beijing. The results indicate: 1) NR-cNTF accurately captures four kinds of city rhythms and seventeen spatial communities; 2) the rapid development of Beijing, epitomized by the CBD area, indeed intensifies the job-housing imbalance; 3) the southern areas with recent government investments have shown more healthy development tendency. Finally, NR-cNTF is compared with some baselines on traffic prediction, which further justifies the importance of urban contexts awareness and neighboring regulations.

Shiyuan Xiao, Yuanxin Ouyang, Wenge Rong, Jianxin Yang, Zhang Xiong. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Answer selection is an important method to achieve better user experience in question answering (QA) systems and it is essential in ensuring better QA matching performance. Improving mutual information between QA pairs is a useful way to obtain the matching degree improvement and question rewriting has been proven a helpful way in utilizing mutual interaction between questions and answers. In this research, we focus on syntax tree aware question rewriting inspired by the thought of integrating syntactic information into question answering. Besides, to improve the quality of rewriting, we employ the generative adversarial network for rewriting optimization, which consists of a syntax tree aware rewriting model and a discriminator. The quality information given by the discriminator guides the optimizing of the rewriting model in the training phase. The experimental study has shown the effectiveness of syntax tree aware question rewriting and utilizing the generative adversarial network for rewriting.

Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT). Despite great research efforts devoted to leveraging deep learning (DL) methods for building better QT strategies, existing studies still face serious challenges especially from the side of finance, such as the balance of risk and return, the resistance to extreme loss, and the interpretability of strategies, which limit the application of DL-based strategies in real-life financial markets. In this work, we propose AlphaStock, a novel reinforcement learning (RL) based investment strategy enhanced by interpretable deep attention networks, to address the above challenges. Our main contributions are summarized as follows: i) We integrate deep attention networks with a Sharpe ratio-oriented reinforcement learning framework to achieve a risk-return balanced investment strategy; ii) We suggest modeling interrelationships among assets to avoid selection bias and develop a cross-asset attention mechanism; iii) To our best knowledge, this work is among the first to offer an interpretable investment strategy using deep reinforcement learning models. The experiments on long-periodic U.S. and Chinese markets demonstrate the effectiveness and robustness of AlphaStock over diverse market states. It turns out that AlphaStock tends to select the stocks as winners with high long-term growth, low volatility, high intrinsic value, and being undervalued recently.

This paper proposes a novel iterative maximum weighted independent set (MWIS) algorithm for multiple hypothesis tracking (MHT) in a tracking-by-detection framework. MHT converts the tracking problem into a series of MWIS problems across the tracking time. Previous works solve these NP-hard MWIS problems independently without the use of any prior information from each frame, and they ignore the relevance between adjacent frames. In this paper, we iteratively solve the MWIS problems by using the MWIS solution from the previous frame rather than solving the problem from scratch each time. First, we define five hypothesis categories and a hypothesis transfer model, which explicitly describes the hypothesis relationship between adjacent frames. We also propose a polynomial-time approximation algorithm for the MWIS problem in MHT. In addition to that, we present a confident short tracklet generation method and incorporate tracklet-level association into MHT, which further improves the computational efficiency. Our experiments on both MOT16 and MOT17 benchmarks show that our tracker outperforms all the previously published tracking algorithms on both MOT16 and MOT17 benchmarks. Finally, we demonstrate that the polynomial-time approximate tracker reaches nearly the same tracking performance.

Tracking-by-detection is one of the most popular approaches to tracking multiple objects in which the detector plays an important role. Sometimes, detector failures caused by occlusions or various poses are unavoidable and lead to tracking failure. To cope with this problem, we construct a heterogeneous association graph that fuses high-level detections and low-level image evidence for target association. Compared with other methods using low-level information, our proposed heterogeneous association fusion (HAF) tracker is less sensitive to particular parameters and is easier to extend and implement. We use the fused association graph to build track trees for HAF and solve them by the multiple hypotheses tracking framework, which has been proven to be competitive by introducing efficient pruning strategies. In addition, the novel idea of adaptive weights is proposed to analyze the contribution between motion and appearance. We also evaluated our results on the MOT challenge benchmarks and achieved state-of-the-art results on the MOT Challenge 2017.

Text matching is a core issue for question answering (QA), information retrieval (IR) and many other fields. We propose to reformulate the original text, i.e., generating a new text that is semantically equivalent to original text, to improve text matching degree. Intuitively, the generated text improves mutual information between two text sequences. We employ the generative adversarial network as the reformulation model where there is a discriminator to guide the text generating process. In this work, we focus on matching question and answers. The task is to rank answers based on QA matching degree. We first reformulate the original question without changing the asker's intent, then compute a relevance score for each answer. To evaluate the method, we collected questions and answers from Zhihu. In addition, we also conduct substantial experiments on public data such as SemEval and WikiQA to compare our method with existing methods. Experimental results demonstrate that after adding the reformulated question, the ranking performance across different matching models can be improved consistently, indicating that the reformulated question has enhanced mutual information and effectively bridged the semantic gap between QA.

Driven by the wave of urbanization in recent decades, the research topic about migrant behavior analysis draws great attention from both academia and the government. Nevertheless, subject to the cost of data collection and the lack of modeling methods, most of existing studies use only questionnaire surveys with sparse samples and non-individual level statistical data to achieve coarse-grained studies of migrant behaviors. In this paper, a partially supervised cross-domain deep learning model named CD-CNN is proposed for migrant/native recognition using mobile phone signaling data as behavioral features and questionnaire survey data as incomplete labels. Specifically, CD-CNN features in decomposing the mobile data into location domain and communication domain, and adopts a joint learning framework that combines two convolutional neural networks with a feature balancing scheme. Moreover, CD-CNN employs a three-step algorithm for training, in which the co-training step is of great value to partially supervised cross-domain learning. Comparative experiments on the city Wuxi demonstrate the high predictive power of CD-CNN. Two interesting applications further highlight the ability of CD-CNN for in-depth migrant behavioral analysis.

The information literacy that the teenagers should have is widely concerned nowadays. We have been teaching a course entitled Introduction to Computer Science and computer Ethics that is taken by freshmen from computer science, electronic engineering and software engineering. There were more than 400 students in our course annually. The students were divided into groups to participate the in-class discussion. We used to focus on computer professional code of practice in last years. While in the fall semester 2017, we paid more attention on what computer and internet have bring us, and what should we do when we are facing the situations nobody had met before. There were 4 sessions, respectively great changes in society made by computer technology and internet, influences in our traditional culture, responsibility of enterprise in information age, and the artificial intelligent ethics problems. Most topics include new technology or idea. We got over 300 questionnaires after the course finished. From which we found that, compare with the former students, more moral topics have been closely followed. Nowadays, all society members are the contributors of the internet, whatever their major are. Our approach can be spread to similar information entrance course easily.

Multiple object tracking is a research hotspot in the artificial intelligent field, and tracking-by-detection is one of the most popular paradigms in recent years. Among these methods, the network flow based tracker is quite popular due to its computational efficiency and optimality, but it still has one main drawback: Object detection is the processing unit, so high-order information is hard to be taken into consideration directly, and it is usually processed hierarchically, which leads to error propagation. To address this problem, we propose community evolution model for network flow based trackers. We introduce a novel community, which maintains detections and tracklets dynamically. The community allows modeling the connectivities of detections and tracklets jointly, which adaptively incorporates all-level correlations among detections and tracklets, including low-level optical flow, mid-level color histogram, and high-level ranking model. We demonstrate the validity of our method on PETS09 dataset and the MOT17 benchmark, and our method achieves competitive results. Our results on the MOT17 benchmark are available on the website.

Biological Event Extraction is an important task towards the goal of extracting biomedical knowledge from the scientific publications by capturing biomedical entities and their complex relations from the texts. As a crucial step in event extraction, event trigger identification, assigning words with suitable trigger category, has recently attracted substantial attention. As triggers are scattered in large corpus, traditional linguistic parsers are hard to generate syntactic features from them. Thereby, trigger sparsity problem restricts the model's learning process and becomes one of the main hinder in trigger identification. In this paper, we employ Noise Contrastive Estimation with Multi-Layer Perceptron model for solving triggers' sparsity problem. Meanwhile, in the light of recent advance in word distributed representation, word-embedding feature generated by language model is utilized for semantic and syntactic information extraction. Finally, experimental study on commonly used MLEE dataset against baseline methods has demonstrated its promising result.

Since a light-field camera is able to capture more information than a traditional camera, a lot of methods, such as depth estimation, image super-resolution, and view synthesis, are explored for recovering scene information. In this paper, we propose a novel framework for scene recovery based on lenslet-based light-field camera images. Instead of using traditional matching terms, we design a new micro-lens-based matching term to calculate structure information and recover several kinds of scene information simultaneously. On the one hand, inherent information in micro-lens images is selected to complement details in sub-aperture images. On the other hand, sub-aperture images are used to expand micro-lens images and synthesize new view images. A new micro-lens-based consistency metric is introduced for the matching term to handle occlusions in depth estimation and image reconstruction. The newly appeared and newly occluded areas in synthesized views are analyzed and recovered based on information from surrounding points. Experimental results show that the proposed depth estimation method outperforms state-of-the-art methods on both synthetic and lenslet-based light-field images, especially in low-texture and occlusion regions. Furthermore, the super-resolution and view synthesis methods are able to acquire view images with more details and less aliasing artifacts.

Supervised dimensionality reduction (DR) plays an important role in learning systems with high-dimensional data. It projects the data into a low-dimensional subspace and keeps the projected data distinguishable in different classes. In addition to preserving the discriminant information for binary or multiple classes, some real-world applications also require keeping the preference degrees of assigning the data to multiple aspects, e.g., to keep the different intensities for co-occurring facial expressions or the product ratings in different aspects. To address this issue, we propose a novel supervised DR method for DR in multiple ordinal regression (DRMOR), whose projected subspace preserves all the ordinal information in multiple aspects or labels. We formulate this problem as a joint optimization framework to simultaneously perform DR and ordinal regression. In contrast to most existing DR methods, which are conducted independently of the subsequent classification or ordinal regression, the proposed framework fully benefits from both of the procedures. We experimentally demonstrate that the proposed DRMOR method (DRMOR-M) well preserves the ordinal information from all the aspects or labels in the learned subspace. Moreover, DRMOR-M exhibits advantages compared with representative DR or ordinal regression algorithms on three standard data sets.

The large scale of Q&A archives accumulated in community based question answering (CQA) servivces are important information and knowledge resource on the web. Question and answer matching task has been attached much importance to for its ability to reuse knowledge stored in these systems: it can be useful in enhancing user experience with recurrent questions. In this paper, a Word Embedding based Correlation (WEC) model is proposed by integrating advantages of both the translation model and word embedding. Given a random pair of words, WEC can score their co-occurrence probability in Q&A pairs, while it can also leverage the continuity and smoothness of continuous space word representation to deal with new pairs of words that are rare in the training parallel text. An experimental study on Yahoo! Answers dataset and Baidu Zhidao dataset shows this new method's promising potential.

Customer volume prediction, which predicts the volume from a customer source to a service place, is a very important technique for location selection, market investigation, and other related applications. Most of traditional methods only make use of partial information for either supervised or unsupervised modeling, which cannot well integrate overall available knowledge. In this paper, we propose a method titled GR-NMF for jointly modeling both implicit correlations hidden inside customer volumes and explicit geographical knowledge via an integrated probabilistic framework. The effectiveness of GR-NMF in coupling all-round knowledge is verified over a real-life outpatient dataset under different scenarios. GR-NMF shows particularly evident advantages to all baselines in location selection with the cold-start challenge.

Recently, variants of neural networks for computational linguistics have been proposed and successfully applied to neural language modeling and neural machine translation. These neural models can leverage knowledge from massive corpora but they are extremely slow as they predict candidate words from a large vocabulary during training and inference. As an alternative to gradient approximation and softmax with class decomposition, we explore the tree-based hierarchical softmax method and reform its architecture, making it compatible with modern GPUs and introducing a compact tree-based loss function. When combined with several word hierarchical clustering algorithms, improved performance is achieved in language modelling task with intrinsic evaluation criterions on PTB, WikiText-2 and WikiText-103 datasets.

For the past decades, stock prediction has been a popular topic in financial applications. Many approaches including machine learning based and statistical models have been employed to forecast price changes in stock market. Considering the power of Restricted Bolztmann Machine (RBM) for feature extraction, we propose to incorporate RBM and several classifiers to predict short-term stock market trend. In this paper, eleven technical indicators are firstly inferred by using trading data, e.g., close price, lowest price, open price and highest price. Afterwards, these technical indicators are conveyed to binary values by using a trend deterministic preparation layer. We apply a RBM to extract features from binary valued features from the last step. The experimental study demonstrates this model's effectiveness compared with several traditional methods.

Paraphrase identification is a fundamental task in natural language process areas. During the process of fulfilling this challenge, different features are exploited. Semantically equivalence and syntactic similarity are of the most importance. Apart from advance feature extraction, deep learning based models are also proven their promising in natural language process jobs. As a result in this research, we adopted an interactive representation to modelling the relationship between two sentences not only on word level, but also on phrase and sentence level by employing convolution neural network to conduct paraphrase identification by using semantic and syntactic features at the same time. The experimental study on commonly used MSRP has shown the proposed method's promising potential.

Recent years have witnessed the continuous growth of megalopolises worldwide, which makes urban safety a top priority in modern city life. Among various threats, dangerous goods such as gas and hazardous chemicals transported through and around cities have increasingly become the deadly "bomb" we sleep with every day. In both academia and government, tremendous efforts have been dedicated to dealing with dangerous goods transportation (DGT) issues, but further study is still in great need to quantify the problem and explore its intrinsic dynamics in a big data perspective. In this paper, we present a novel system called DGeye, which features a "duet" between DGT trajectory data and human mobility data for risky zones identification. Moreover, DGeye innovatively takes risky patterns as the keystones in DGT management, and builds causality networks among them for pain point identification, attribution and prediction. Experiments on both Beijing and Tianjin cities demonstrate the effectiveness of DGeye. In particular, the report generated by DGeye driven the Beijing government to lay down gas pipelines for the famous Guijie food street.

The project named after City-Eyes is based on the HBASE big data analyzing platform and the real-time-display technology with H5/CSS3, which could analyze data and result dynamically. The project is devoted to designing the online city-data-analyzing platform, with interacting in real time, filtering, analyzing and displaying data. In the view of filtering, we sample Wuxi and collect much information, including phone signaling, railway, airports, Weibo, population mobility and etc. Moreover, we write enough data mining scripts for varieties of data to extract the value of them. In the view of analyzing, we build an efficient analyzing model, which divides the task into two parts, which includes the front end and the back end. The back end is focusing on compressing data and extracting valid information by clustering the data streams. At the same time, the front-end applies the real-time-display technology to provide an interactive and nice-looking data visualizing solution for our users. In the view of displaying, we come up with various solutions from two angles for every variety of data: 'distribution and network'. With svg/canvas animation tech, the data can be mixed into the map and display itself dynamically.

Unlike traditional multi-view images, sampling in angular domain of light field images is distributed in different directions. Therefore, an angular sampling image (ASI), comprising of possible matching points extracted from each view, is available for each point. In this paper, we analyze the geometric relationship between ASIs and reference sub-aperture images, and then prove the occlusion boundary similarity. Based on the geometric relationship in extreme cases, we show that some points in ASI have higher reliability than other points for depth calculation. An integral guided filter is then built based on the sub-aperture image to predict occlusion probabilities in ASIs. The filter is independent of ASIs and has no requirement for high angular resolution so that it is easy to apply to the cost volume calculation. We integrate the filter into our depth estimation framework and other state-of-the-art depth estimation frameworks. Experimental results demonstrate that the proposed filter is more effective to occluded point detection in ASIs than other methods. Results from different data sets show that our method outperforms the existing state-of-the-art depth estimation methods, especially along occlusion boundaries.

Light field images, which capture multiple images from different angles of a scene, have been proved that can detect salient regions more effectively. Instead of estimating depth labels from light field images, we proposed to extract relative locations, which can distinguish whether the object is located before the focus plane of the main lens or not, for saliency detection. The relative locations are calculated by comparing raw light field images captured by plenoptic cameras and central views of scenes. The relative locations are then integrated to a modified saliency detection framework to obtain the salient regions. Experimental results demonstrate that the proposed relative locations can help to improve the accuracy of results, which is also efficient. Moreover, the modified framework outperforms the state-of-the-art methods for light field images saliency detection.

Traffic speed prediction is a long-standing and critically important topic in the area of Intelligent Transportation Systems (ITS). Recent years have witnessed the encouraging potentials of deep neural networks for real-life applications of various domains. Traffic speed prediction, however, is still in its initial stage without making full use of spatio-temporal traffic information. In light of this, in this paper, we propose a deep learning method with an Error-feedback Recurrent Convolutional Neural Network structure (eRCNN) for continuous traffic speed prediction. By integrating the spatio-temporal traffic speeds of contiguous road segments as an input matrix, eRCNN explicitly leverages the implicit correlations among nearby segments to improve the predictive accuracy. By further introducing separate error feedback neurons to the recurrent layer, eRCNN learns from prediction errors so as to meet predictive challenges rising from abrupt traffic events such as morning peaks and traffic accidents. Extensive experiments on real-life speed data of taxis running on the 2nd and 3rd ring roads of Beijing city demonstrate the strong predictive power of eRCNN in comparison to some state-of-the-art competitors. The necessity of weight pre-training using a transfer learning notion has also been testified. More interestingly, we design a novel influence function based on the deep learning model, and showcase how to leverage it to recognize the congestion sources of the ring roads in Beijing.

This work proposes a novel person re-identification method based on Hierarchical Bipartite Graph Matching. Because human eyes observe person appearance roughly first and then goes further into the details gradually, our method abstracts person image from coarse to fine granularity, and finally into a three layer tree structure. Then, three bipartite graph matching methods are proposed for the matching of each layer between the trees. At the bottom layer Non-complete Bipartite Graph matching is proposed to collect matching pairs among small local regions. At the middle layer Semi-complete Bipartite Graph matching is used to deal with the problem of spatial misalignment between two person bodies. Complete Bipartite Graph matching is presented to refine the ranking result at the top layer. The effectiveness of our method is validated on the CAVIAR4REID and VIPeR datasets, and competitive results are achieved on both datasets.

We propose a segmentation model for light field images based on superpixels segmentation and graph-cuts algorithm. Unlike traditional images, which do not offer information for different directions, a light field image encodes space data which can be computed on its epipolar plane images (EPI) with some effective methods. In our work, we analyze the structure of EPI and research the computational process of disparity using EPI. On this basis, we present a new method for computing disparity using the modified structure tensor on EPIs. We further apply the computed disparity labels by fusing RGB images and disparity labels to obtain more detailed over-segmentation. Meanwhile, the modified structure tensor algorithm is used to get more accurate image boundaries, which plays a role in computing disparity features. All these processes are applied in an interactive segmentation model. Our experiments on public data sets demonstrate that the proposed light field image segmentation achieves a higher performance compared with state-of-the-art methods.

Sentimental polarity detection has long been a hot task in natural language processing since its applications range from product feedback analysis to user statement understanding. Recently a lot of machine learning approaches have been proposed in the literature, e.g., SVM, Naive Bayes, recursive neural network, auto-encoders and etc. Among these different models, Convolutional Neural Network (CNN) architecture have also demonstrated profound efficiency in NLP tasks including sentiment classification. In CNN, the width of convolutional filter functions alike number N in N-grams model. Thus, different filter lengths may influence the performance of CNN classifier. In this paper, we want to study the possibility of leveraging the contribution of different filter lengths and grasp their potential in the final polarity of the sentence. We then use Adaboost to combine different classifiers with respective filter sizes. The experimental study on commonly used datasets has shown its potential in identifying the different roles of specific N-grams in a sentence respectively and merging their contribution in a weighted classifier.

Community-based Question Answering (CQA) sites have become popular since they allow users to get answers to complex, detailed and personal question from other users directly. However, since answering a question depends on the ability and willingness of other users to address the askers' real needs, a significant fraction of the questions remain unanswered. To decrease the unanswered question rate and then improve the user experience, in this paper, a multidimensional scaling (MDS) based data reorganization method is proposed. By using this method, the CQA system can predict the askers' intention and accordingly provide related previous question/answer pairs to help them find useful information. The method has been evaluated on an off-line dataset extracted from Baidu Zhidao and the result has shown its promising potential in knowledge management in CQA systems.

Person re-identification is one of the most important issues in intelligent transportation systems. Recently, the widespread availability of cameras and a growing need for public safety have increasingly motivated interest in the problem of person re-identification in multi-camera networks. The main difficulty of person re-identification arises from the variations in human pose, different viewpoint in multi-camera, cluttered background, occlusion, and low image resolution, which lead person re-identification to a challenging problem. This paper presents a method based on sparse coding for person re-identification. To apply sparse coding method, we firstly solve the problem of aligning person images, and to enhance the discrimination of dictionary, a dictionary learning model is added into our method. Experiments on benchmark dataset (CAVIARa, ETZH, i-LIDS) demonstrate that the proposed method outperforms the state-of-the-art approaches.

In the above paper [1, p. 1215], it was assumed that [1, eq. (8)] was a convex optimization problem. However,$C(X)$(see [1, eq. (6)]) is in general not convex, since it is an absolute value of the difference between two convex functions. Indeed, the proposed cost function is non-convex. By using the subgradient method with the chosen steps, however, we can get a quite good solution (probably a local minimum) that has a sufficiently low cost function value. This makes the proposed algorithm work sufficiently well, as demonstrated by the experimental results.

Facial action unit (AU) detection from video has been a long-standing problem in the automated facial expression analysis. While progress has been made, accurate detection of facial AUs remains challenging due to ubiquitous sources of errors, such as inter-personal variability, pose, and low-intensity AUs. In this paper, we refer to samples causing such errors as hard samples, and the remaining as easy samples. To address learning with the hard samples, we propose the confidence preserving machine (CPM), a novel two-stage learning framework that combines multiple classifiers following an "easy-to-hard" strategy. During the training stage, CPM learns two confident classifiers. Each classifier focuses on separating easy samples of one class from all else, and thus preserves confidence on predicting each class. During the test stage, the confident classifiers provide "virtual labels" for easy test samples. Given the virtual labels, we propose a quasi-semi-supervised (QSS) learning strategy to learn a person-specific classifier. The QSS strategy employs a spatio-temporal smoothness that encourages similar predictions for samples within a spatio-temporal neighborhood. In addition, to further improve detection performance, we introduce two CPM extensions: iterative CPM that iteratively augments training samples to train the confident classifiers, and kernel CPM that kernelizes the original CPM model to promote nonlinearity. Experiments on four spontaneous data sets GFT, BP4D, DISFA, and RU-FACS illustrate the benefits of the proposed CPM models over baseline methods and the state-of-the-art semi-supervised learning and transfer learning methods.

A battle between two Chinese taxi booking mobile apps, namely, Didi and Kuaidadi, had recently occurred in early 2014. These two apps, which are backed by Internet giants Tencent and Alipay, gave promotion fees to taxi drivers for each deal made and also allowed each taxi passenger to save some money, when a customer had taken a taxi through the app and paid the fare through the mobile payment method. As expected, the taxi service pattern had been greatly changed during this battle. To address the debates on social justice, equity, and improvements of taxi service, we collect 37-day trip data of over 9000 taxis in Beijing to study the influence of this pattern change. In the first 18 days, the battle had not occurred and in the remaining 19 days, the battle is white-hot. We quantitatively demonstrate how several important service indices (e.g., the traveling distances and idle time lengths) of taxi drivers had been changed. The spatial-temporal traveling patterns of taxis are then studied. Based on comprehensive analysis, the benefits and drawbacks brought by money promotion are finally discussed. The obtained results indicate that productively employing big data can help answer some important questions attracting the interest of the whole society.

Community-based Question Answering (CQA) has become popular in knowledge sharing sites since it allows users to get answers to complex, detailed, and personal questions directly from other users. Large archives of historical questions and associated answers have been accumulated. Retrieving relevant historical answers that best match a question is an essential component of a CQA service. Most state of the art approaches are based on bag-of-words models, which have been proven successful in a range of text matching tasks, but are insufficient for capturing the important word sequence information in short text matching. In this paper, a new architecture is proposed to more effectively model the complicated matching relations between questions and answers. It utilises a similarity matrix which contains both lexical and sequential information. Afterwards the information is put into a deep architecture to find potentially suitable answers. The experimental study shows its potential in improving matching accuracy of question and answer.

We present a structured light measurement system to collect high accuracy surface information of the measured object with a good real-time performance. Utilizing phase-shifting method in conjunction with a matching method proposed in this paper which can significantly reduce the noisy points, we can achieve high accuracy and noiseless point cloud in a complex industrial environment. Due to the use of the heterogeneous parallel computation model, the parallelism of the algorithm is developed in a deep way. The OpenMP+CUDA hybrid computing model is then used in the system to get a better real-time performance.

Varied sources of error contribute to the challenge of facial action unit detection. Previous approaches address specific and known sources. However, many sources are unknown. To address the ubiquity of error, we propose a Confident Preserving Machine (CPM) that follows an easy-to-hard classification strategy. During training, CPM learns two confident classifiers. A confident positive classifier separates easily identified positive samples from all else, a confident negative classifier does same for negative samples. During testing, CPM then learns a person-specific classifier using "virtual labels" provided by confident classifiers. This step is achieved using a quasi-semi-supervised (QSS) approach. Hard samples are typically close to the decision boundary, and the QSS approach disambiguates them using spatio-temporal constraints. To evaluate CPM, we compared it with a baseline single-margin classifier and state-of-the-art semi-supervised learning, transfer learning, and boosting methods in three datasets of spontaneous facial behavior. With few exceptions, CPM outperformed baseline and state-of-the art methods.

Different from the traditional multi-view images, the sampling in angular resolution of light field images is continuous in each direction. Therefore, an angular sampling image, comprising of matching points extracted from each view, can be constructed at different possible depth for each point. In this paper, we prove that the angular sampling image of an occluded point at the correct depth is similar to the scene around the point. On this basis, a guided integral filter acquired from the reference view is proposed to weight the matching points for consistency measure, which predicts the probabilities of occlusions. The discrete labeling problem is then solved by a filter-based algorithm to approximate the optimal solution. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods for light field depth estimation both in occluded and ambiguous regions, and has no requirement for angular resolution.

Machine learning algorithms depend heavily on the data representation, which dominates its success in experiment accuracy. Autoencoder model structure is proposed to learn from data a good representation with the least possible amount of distortion. Furthermore, it has been proven that boosting sparsity when learning representation can significantly improve performance on classification tasks and also make the feature vector easy to interpret. One straightforward approach for autoencoder to obtain sparse representation is to impose sparse penalty on its overall cost function. Nevertheless, few comparative analysis has been conducted to evaluate which sparse penalty term works better. In this paper, we adopt L1 norm, L2 norm, Student-t penalties, which are rarely deployed to penalise the hidden unit outputs, and commonly used penalty KL-divergence in the literature. Then, we present a detailed analysis to evaluate which penalty achieves better result in terms of reconstruction error, sparseness of representation and classification performance on test datasets. Experimental study on MNIST, CIFAR-10, SVHN, OPTDIGITS and NORB datasets reveals that all these penalties achieve sparse representation and outperforms representations learned by pure autoencoder on classification performance and sparseness of feature vectors. Moreover, we hope this topics and the practices would provide insights for future research.

In this paper, we propose a novel unsupervised color spatial pyramid matching (UCSPM) approach for person re-identification. It is well motivated by our study on spatial pyramid to build effective structural object representation for person re-identification. Through the combination of illumination invariance color feature, UCSPM can well cope with the variations of viewpoint, illumination and pose. First, local superpixel regions are divided to accurately represent the color feature. Second, human body are divided into increasing fine vertical sub-regions to construct the spatial pyramid matching scheme. Third, the color feature and its spatial distribution information are used in a pyramid match kernel for calculating the similarity between person and person. The effectiveness of our approach is validated on the VIPeR dataset and CUHK campus dataset. Comparing with other approaches, our UCSPM improves the best unsupervised rank-1 matching rate on the VIPeR dataset by 3.08% with only one kind of feature—color.

Currently the collaborative filtering based recommender system has become more and more indispensable due to its capability in providing users with personalised suggestions. Despite its advances in term of efficiency, easy implementation and robustness, traditional collaborative filtering techniques suffer from several challenges such as cold-start and data sparsity. To overcome these limitations, external information is expected to help improve the overall effectiveness. Among the diverse context information, trust relationships is a widely utilised mechanism. Meanwhile, researchers also found distrust relationships is unavoidable in social network and recommender systems can benefit from distrust information. However, most existed distrusted oriented methods do not take the property of multi-facets in distrust relationships into consideration. In this paper, we exploit distrust relationships in a multi-faceted perspective and proposed a matrix factorization based model with integration of different distrust relationship of quality user between different people. Experimental study on well-known dataset has shown promising result and it is expected that this work could provide insight for researchers in this domain to further discuss the distrust in recommender systems.

In vehicular networks, since reliable end-to-end paths between data source and destination seldom exist, replication-based routing protocols are widely used to increase the delivery ratio and reduce the transfer delay. However, after a data message is delivered, its replicas still exist and greatly waste network resources, such as transmission bandwidth and storage spaces. In mobile multimedia communications, the large size of multimedia data greatly aggravates this situation. In this paper, we propose a GPS-based replica deletion scheme with anti-packet distribution for vehicular networks, namely RAD. It utilizes vehicle-to-vehicle and vehicle-to-roadside-unit communications to remove redundant data replicas by a certain number of anti-packets. A roadside unit at each crossing distributes its collected anti-packets to nearby vehicles moving for different directions according to the geographical locations of the to-be-deleted targets. This distribution increases the delivery probability of these anti-packets. Experiment results in a real taxi network show that, compared with others, RAD accelerates replica deletion with less extra overhead

Median filtering enjoys its popularity as a widely adopted image denoising and smoothing tool. It is also used by anti-forensic researchers in helping disguise traces of other image processing operations, e.g., image resampling and JPEG compression. This paper proposes an image variational deconvolution framework for both quality enhancement and anti-forensics of median filtered (MF) images. The proposed optimization-based framework consists of a convolution term, a fidelity term with respect to the MF image, and a prior term. The first term is for the approximation of the median filtering process, using a convolution kernel. The second fidelity term keeps the processed image to some extent still close to the MF image, retaining some denoising or other image processing artifact hiding effects. Using the generalized Gaussian as the distribution model, the last image prior term regularizes the pixel value derivative of the obtained image so that its distribution resembles the original one. Our method can serve as an MF image quality enhancement technique, whose efficacy is validated by experiments conducted on MF images which have been previously “salt & pepper” noised. Using another parameter setting and with an additional pixel value perturbation procedure, the proposed method outperforms the state-of-the-art median filtering anti-forensics, with a better forensic undetectability against existing detectors as well as a higher visual quality of the processed image. Furthermore, the feasibility of concealing image resampling traces and JPEG blocking artifacts is demonstrated by experiments, using the proposed median filtering anti-forensic method.

View-based 3D model retrieval uses a set of views to represent each object. Discovering the complex relationship between multiple views remains challenging in 3D object retrieval. Recent progress in the latent Dirichlet allocation (LDA) model leads us to propose its use for 3D object retrieval. This LDA approach explores the hidden relationships between extracted primordial features of these views. Since LDA is limited to a fixed number of topics, we further propose a multitopic model to improve retrieval performance. We take advantage of a relevance feedback mechanism to balance the contributions of multiple topic models with specified numbers of topics. We demonstrate our improved retrieval performance over the state-of-the-art approaches.

In this paper, we study the block delivery delay of random linear network coding in two-hop single-unicast delay-tolerant networks with grid-based mobility. By block delivery delay, we mean how long it takes the destination to receive all the K information packets of a single block. Our work includes two parts. First, we give a general analysis of the dependency between packet spaces spanned by different nodes in a stochastic way. Then we simplify the result by means of the approximation. By the dependency analysis, we can accurately update nodes' innovativeness rank. Second, via tracking the innovativeness ranks of all nodes, we develop an analytic framework to iteratively compute the cumulative distribution function of the block delivery delay. Our simulation results verify that both parts of our analysis are sufficiently accurate. Copyright © 2013 John Wiley & Sons, Ltd.

The data are complexity and heterogeneous in the city-scale. When the tasks are nonlinear, existing systems cannot perform well. This paper proposes a data service oriented architecture that is based on the data vitalization theory. In this perspective, the vitalized cells are the basic units of a system, which are organized through nested and/or layer structure. A smart service platform bases on crowd intelligence network is developed according the theory of data vitalization. It allows the developers upload their own services and data to open for other developers. Then the architecture and implement technologies of the platform are introduced. At last, an application example of this architecture is given, which is used to sense social hot-spots in a period and rebuild the scene of the hot-spots. The platform and example show that the data vitalization theory achieves high scalability and flexibility for both linear and non-linear tasks.

Work-based learning is a crucial approach to promoting professionals' working and learning efficiency. It is just-in-time, work-related, informal and spontaneous. With an aim to facilitate this kind of learning, in the paper we propose WoBaLearn, a work-based learning system, which can provide professionals with just-in-time, personalized and work-related learning supports. This paper specifies the design of a learning process in WoBaLearn based on a previously designed architecture. To evaluate the system, a learning scenario, in which professionals engage in a work-based learning activity with the support of WoBaLearn, is assumed and implemented. Results obtained from the scenario evaluate positively the design of WoBaLearn.

Wavelet-based compression is widely used to reduce image redundancy for efficiently storing and transmitting the data. Thus it is an important part in digital image forensics to trace the wavelet-based image compression history. The wavelet-based compression leaves comb-like quantization artifacts in the DWT (Discrete Wavelet Transform) histogram, which however can be disguised using a proper dithering operation. In this paper, standing on the forensic side, we study the joint histogram of DWT coefficients across different levels, whose pattern is robust across a wide range of natural uncompressed images but can be easily destroyed by the wavelet-based compression or the dithering operation used for anti-forensic purposes. By applying the Hough transform to the joint DWT histogram, we derive a 12-dimensional feature vector and a merged discriminating feature. Experimental results demonstrate the effectiveness of the proposed method for differentiating uncompressed images from (anti-forensic) wavelet-based compressed images.

This paper proposes a JPEG anti-forensic method, which aims at removing from a given image the footprints left by JPEG compression, in both the spatial domain and DCT domain. With reasonable loss of image quality, the proposed method can defeat existing forensic detectors that attempt to identify traces of the image JPEG compression history or JPEG anti-forensic processing. In our framework, first because of a total variation-based deblocking operation, the partly recovered DCT information is thereafter used to build an adaptive local dithering signal model, which is able to bring the DCT histogram of the processed image close to that of the original one. Then, a perceptual DCT histogram smoothing is carried out by solving a simplified assignment problem, where the cost function is established as the total perceptual quality loss due to the DCT coefficient modification. The second-round deblocking and de-calibration operations successfully bring the image statistics that are used by the JPEG forensic detectors to the normal status. Experimental results show that the proposed method outperforms the state-of-the-art methods in a better tradeoff between the JPEG forensic undetectability and the visual quality of processed images. Moreover, the application of the proposed anti-forensic method in disguising double JPEG compression artifacts is proven to be feasible by experiments.

Nowadays a large amount of data on the web are stored in relational database (RDB). How to effectively map these data to ontology has become one of the most important challenges in semantic web. Several efforts have been conducted in this area and direct mapping (DM) is a notable one as the W3C candidate recommendation. Though DM has shown its effectiveness, it still faces a lot of challenges. Its performance in term of storage space and time complexity will become worse when RDBS is becoming big and updating frequently. Furthermore, it cannot satisfy monotonicity and semantics preservation at the same time. In this paper, inspired by the idea of ontology-based data access (OBDA), a mechanism is proposed where database is accessed via description logic (DL) ontology and a real TBox and mapping file will be generated accordingly. This method can achieve similar function compared to standard ontology like OWL. The experimental study has shown that it can provide better performance with regard to the storage space and ontology generation time. It has also shown its capability in supporting rapid query process. Different from the other methods which generate virtue RDF data, the proposed approach can also support adding rules, which will enhance the semantic expression ability of the knowledge base.

Sentiment analysis is one of the most important challenges to understand opinions online. In this research, inspired by the idea that the structural information among words, phrases and sentences is playing important role in identifying the overall statement's polarity, a novel sentiment analysis model is proposed based on recurrent neural network. The key point of the proposed approach, in order to utilise recurrent character, is to take the partial document as input and then the next parts to predict the sentiment label distribution rather than the next word. The proposed method learns words representation simultaneously the sentiment distribution. Experimental studies have been conducted on commonly used datasets and the results have shown its promising potential.

This paper proposes a framework for a professional context-aware mobile learning system. This system provides learning contents delivered via mobile devices and adapted to learning needs, personal characteristics and particular circumstances. Supported by this system, professionals will acquire personalized, just-in-time and problem-based learning contents in real working situations.

International audience

During the process of building business agility, the concept of Service Oriented Architecture (SOA) is proposed and widely lauded as an innovative business oriented solution. One of the most fundamental components in SOA based applications is a service, which represents the repeatable business functionalities to help the development of loosely coupled applications. Due to its important role in implementing SOA based applications for achieving dynamic business process, how to build a scalable, reliable service efficiently has become a vital challenge, while the service lifecycle management becomes one of the critical mechanisms to ensure the service quality. Currently, there are a large number of service lifecycle models proposed in the literature to fit their own purposes. However, few of them clearly indicate the integration of the lifecycle processes with stakeholders. To meet this gap, in this research a conceptual stakeholder analysis framework is proposed to associate the stakeholders with different lifecycle stages. It is believed that this method is able to offer the researchers in the community further insight into service lifecycle management from the stakeholder's perspective.

This paper proposes an anti-forensic method that disguises the footprints left by JPEG compression, whose objective is to fool existing JPEG forensic detectors while keeping a high visual quality of the processed image. First we examine the reliability of existing detectors and point out the potential vulnerability of the quantization table estimation based detector. Then we construct a new, non-parametric method to DCT histogram smoothing without any histogram statistical model. Finally JPEG forensic detectors are fooled by optimizing an objective function considering both the anti-forensic terms and a natural image statistical model. We show that compared to the state-of-the-art methods the proposed JPEG anti-forensic method is able to achieve a higher image visual quality while being undetectable under existing detectors.

Moving object detection is an important component of a traffic surveillance system. Usual background subtraction approaches often poorly perform on a long outdoor traffic video due to vehicles waiting at an intersection and gradual changes of illumination and background shadow position. We present a fast and robust background subtraction algorithm based on unified spatio-temporal background and foreground modeling. The correlation between neighboring pixels provides high levels of detection accuracy in the dynamic background scene. Our Bayesian fusion method, which establishes the traffic scene model, combines both background and foreground models and considers prior probabilities to adapt changes of background in each frame. We explicitly model both temporal and spatial information based on the kernel density estimation (KDE) formulation for background modeling. Then, we use a Gaussian formulation to describe the spatial correlation of moving objects for foreground modeling. In the updating step, a fusion background frame is generated, and reasonable updating rates are also proposed for the traffic scene. The experimental results show that the proposed method outperforms the previous work with less computation and is better suited for the traffic scenes.

Document clustering is one of the most effective techniques to organize documents in an unsupervised manner. In this paper, an Incremental method for document Clustering based on Information Bottleneck theory (ICIB) is presented. The ICIB is designed to improve the accuracy and efficiency of document clustering, and resolve the issue that an arbitrary choice of document similarity measure could produce an inaccurate clustering result. In our approach, document similarity is calculated using information bottleneck theory and documents are grouped incrementally. A first document is selected randomly and classified as one cluster, then each remaining document is processed incrementally according to the mutual information loss introduced by the merger of the document and each existing cluster. If the minimum value of mutual information loss is below a certain threshold, the document will be added to its closest cluster; otherwise it will be classified as a new cluster. The incremental clustering process is low-precision and order-dependent, which cannot guarantee accurate clustering results. Therefore, an improved sequential clustering algorithm (SIB) is proposed to adjust the intermediate clustering results. In order to test the effectiveness of ICIB method, ten independent document subsets are constructed based on the 20NewsGroup and Reuters-21578 corpora. Experimental results show that our ICIB method achieves higher accuracy and time performance than K-Means, AIB and SIB algorithms.

Latent Factor Model (LFM) based approaches are becoming popular when implementing Collaborative Filtering (CF) recommenders, due to their high recommendation accuracy. However, current LFM approaches address the accuracy issue only based on the rating data, whereas early research indicates that integrating information from additional data sources is helpful to the recommendation accuracy. In this work we focus on improving the recommendation accuracy of a LFM based CF recommender by integrating folksonomy information. To implement this approach, we first propose a novel model named Item Folsonomy Relevance (IFR) to analyze the item relevance inside the folksonomy; we subsequently integrate the latent factors of the IFR model and rating data through probabilistic matrix factorization (PMF), a state-of-the-art matrix factorization technique, to produce recommendations based on information from both the ratings and folksonomy simultaneously. The experiments on MovieLens dataset showed that compared to two state-of-the-art LFM approaches and another folksonomy-augmented recommder, our approach could obtain advantage in recommendation accuracy.

Nowadays, datasets grow enormously both in size and complexity. One of the key issues confronted by large-scale dataset analysis is how to adapt systems to new, unprecedented query loads. Existing systems nail down the data organization scheme once and for all at the beginning of the system design, thus inevitably will see the performance goes down when user requirements change. In this paper, we propose a new paradigm, Data Vitalization, for large-scale dataset analysis. Our goal is to enable high flexibility such that the system is adaptive to complex analytical applications. Specifically, data are organized into a group of vitalized cells, each of which is a collection of data coupled with computing power. As user requirements change over time, cells evolve spontaneously to meet the potential new query loads. Besides basic functionality of Data Vitalization, we also explore an envisioned architecture of Data Vitalization including possible approaches for query processing, data evolution, as well as its tight-coupled mechanism for data storage and computing.

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.

Watermarking embeds information into a digital signal like audio, image, or video. Reversible image watermarking can restore the original image without any distortion after the hidden data is extracted. In this paper, we present a novel reversible watermarking scheme using an interpolation technique, which can embed a large amount of covert data into images with imperceptible modification. Different from previous watermarking schemes, we utilize the interpolation-error, the difference between interpolation value and corresponding pixel value, to embed bit ¿1¿ or ¿0¿ by expanding it additively or leaving it unchanged. Due to the slight modification of pixels, high image quality is preserved. Experimental results also demonstrate that the proposed scheme can provide greater payload capacity and higher image fidelity compared with other state-of-the-art schemes.

This paper proposes a reversible image watermarking scheme of low distortion and relatively large capacity, wherein prediction-errors are modified at most by 1 to embed secret bits. Different from most existing predictors, where only a partial prediction context is available, we provide a full context for every pixel in our watermarking scheme. Predictors operating on full contexts are preciser and thus produce smaller prediction-errors, which are more favorable for data embedding. Experimental results also validate that the proposed scheme can achieve high image fidelity while providing relatively large capacity.

The location awareness is a crucial foundation for perceptions of the surroundings in the smart environment. Radio frequency identification (RFID), as one of the most promising technologies, plays a more important role in the indoor location awareness. This paper surveys current RFID-based locating research and discusses the problem that is brought by the tag's diversity derived from different manufacturer types and different used-time of built-in battery. We present the algorithm named RFDiffFreeLoc to improve the location precision by eliminating the dissimilarity among tags. In the stimulation experiments, we analyze the impact of noise on performance and contrast our algorithm with the existing LANDMARC algorithm. The simulation performances show that our algorithm is feasible via two metrics: the mean error and cumulative error distribution. The results indicate that RFDiffFreeLoc significantly increases the locating accuracy: when the space between the reference tags is 1 m, the mean error drops 0.076–0.344 m according to various noise conditions. Furthermore, a prototype system named RFHome is deployed for validating the algorithm in the actual home environment. The practical experimental results demonstrate that our algorithm is more effective than previous LANDMARC algorithm.

Abstract Wireless sensor networks are prone to failure, so prolonging their lifetime and preventing loss of connectivity are significant. A simple but efficient strategy is to place redundant sensor nodes to establish multi‐connectivity. This paper explores how to add as few as possible nodes (called Steiner nodes) to a sensor network such that the resulting network isk‐connected or partiallyk‐connected.k‐connectivity means that each pair of the nodes, whether Steiner or original, is connected by at leastknode‐disjoint paths, while partialk‐connectivity only requires such connectivity among original nodes. The contribution lies in two aspects. First, the approximation ratio of an existingk‐connectivity repair algorithm is decreased fromO(k4α) toO(k3α), whereαis the approximation ratio of any algorithm that finds a minimum‐weightk‐connected spanning subgraph of a weighted complete graph. This is the best result ever obtained. Second, the first generic partialk‐connectivity repair algorithm is proposed. It is proved that the approximation ratio of this algorithm is at mostO(k3α). Copyright © 2008 John Wiley & Sons, Ltd.

There has been a growing interest in wireless sensor networks (WSNs). Considering the limited energy, memory and computational capacity of the sensor nodes, it becomes necessary to ensure rational use of their resources. The fairness and congestion control are also need to be taken into account. It is in this context that a robust routing algorithm with fair congestion control in wireless sensor network (called RRA- FCC) is proposed. RRA-FCC performs a low cost and robust routing based on dividing the monitoring region into several subareas initially. Furthermore, RRA-FCC provides a fair congestion control, which improves the whole network fairness in congestion. The simulation results show that RRA-FCC performs well in the throughput of Sink nodes, energy consumption and the whole network fairness in congestion.

On the impact of the node mobility, location service approaches based on the node location management incur high protocol overhead and low validity of location information. Therefore, a mobile location agent (MLA) algorithm is introduced to optimize location service. For each node, a location agent will be used to perform the location update and query by location service to decrease the protocol overhead. The location agent will assist the packet routing to the destination, which will upgrade the validity of location information caching in the network and improve the performance of geographic routing. When analyzing routing according to the location agent, we show a new method traversing all local closest nodes around a void location agent region to obtain the location information of the destination node. We select representative location service protocols and perform MLA algorithm. Simulation experimental results show that MLA algorithm can significantly reduce the protocol overhead of location service and improve the packet delivery ratio of geographic routing effectively.