High-definition (HD) maps are crucial to autonomous driving, providing structured representations of road elements to support navigation and planning. However, existing query-based methods often employ random query initialization and depend on implicit temporal modeling, which lead to temporal inconsistencies and instabilities during the construction of a global map. To overcome these challenges, we introduce a novel end-to-end framework for consistent online HD vectorized map construction, which jointly performs map instance tracking and short-term prediction. First, we propose a Semantic-Aware Query Generator that initializes queries with spatially aligned semantic masks to capture scene-level context globally. Next, we design a History Rasterized Map Memory to store fine-grained instance-level maps for each tracked instance, enabling explicit historical priors. A History-Map Guidance Module then integrates rasterized map information into track queries, improving temporal continuity. Finally, we propose a Short-Term Future Guidance module to forecast the immediate motion of map instances based on the stored history trajectories. These predicted future locations serve as hints for tracked instances to further avoid implausible predictions and keep temporal consistency. Extensive experiments on the nuScenes and Argoverse2 datasets demonstrate that our proposed method outperforms state-of-the-art (SOTA) methods with good efficiency.

Extracting Tactics, Techniques, and Procedures (TTP) from unstructured threat reports remains a critical challenge in cyber threat intelligence (CTI). Although large language models (LLMs) may automate TTP extraction, their understanding of TTP knowledge and robustness remain unverified due to the lack of evaluation benchmarks. To address this, we propose TTP-RoB, a novel framework for probing the TTP knowledge and robustness inherent in LLMs. In TTP-RoB, by analyzing real-world CTI reports, we identify key interference factors: the absence of correct answers and the interference of similar technique names. Then, we develop a knowledge sampling algorithm to select representative examples from a relevant knowledge base. Finally, we construct a probing dataset that integrates the identified interferences and sampled knowledge.Our TTP-RoB evaluation of mainstream LLMs—including the Deepseek, GPT, Llama, and Qwen series—demonstrate that while all models show strong understanding of basic technical concepts, their robustness varies significantly under different interference conditions. The models generally maintain stable performance when faced with the absence of correct answers, but display substantial vulnerability to the interference of similar technique names and suffer accuracy drops ranging from 15.4% to 59.1%. Overall, model robustness exhibits a significant decline as model scale decreases. Furthermore, the evaluation results reveal that the distilled models (e.g., DeepSeek-R1-distill-Qwen) exhibit significantly lower robustness compared to their corresponding foundation models. These results confirm that rigorous evaluation for model selection is critical before using LLMs for TTP extraction and other CTI tasks.

3D human pose estimation (3D HPE) is an important computer vision task with various practical applications. Researchers have proposed various deep learning-based methods for 3D HPE. However, the majority of such methods rely on lifting 2D pose sequence to 3D which do not perform well in challenging scenarios and are often computationally expensive. Such methods typically rely on 2D joint coordinates which do not provide much spatial context to solve ambiguity problem. In addition, merely relying on information extracted from RGB frames may miss temporal information and structural context. Thus, in this paper, we propose a framework that incorporates event stream as an additional input since event features provide such useful information. Moreover, instead of using 2D joint coordinates in pose sequence, our framework uses intermediate visual representations produced by off-the-shelf 2D pose detectors to implicitly encode joint-centric spatial context. Our new framework is a novel state space model (SSM)-based solution called Event-Guided Context Aware MambaPose (CA-MambaPose). In CA-MambaPose framework, we design a novel cross modality fusion mamba module to skillfully fuse the RGB and Event features. CA-MambaPose has lower computational cost due to the efficiency of Mamba blocks. We conduct extensive experiments to evaluate CA-MambaPose using two existing datasets. Our experimental results show that CA-MambaPose achieves better performance than SOTA methods.

3D human pose estimation (3D HPE) is an important computer vision task with various practical applications. However, 3D pose estimation for multi-person from a monocular video (3DMPPE) is particularly challenging. Recent transformer-based approaches focus on capturing the spatial-temporal information from sequential 2D poses, which unfortunately loses the visual feature relevant for 3D pose estimation. In this paper, we propose an end-to-end framework called Event Guided Video Transformer (EVT) which predicts 3D poses directly from video frames by learning spatial-temporal contextual information from visual features effectively. In addition, our design is the first that incorporates event features to help guide 3D pose estimation. EVT first decouples persons into different instance-aware feature maps from video frames. These features containing specific clues of body structure information are then fed together with event features into an attention based Event-Aware Embedding Module. Next, the fused features for each instance are then fed into an intra-human relation extraction module and subsequently to a temporal transformer to extract inter-frame relationship. Finally, the extracted features are fed into a decoder for 3D pose estimation. Experiments using three widely used 3D pose estimation benchmarks show that our proposed EVT achieves better performance than state-of-the-art models.

Remote Access Trojans (RATs) are malware that allow attackers to remotely control infected systems and steal sensitive user data via the internet. Although current detection methods based on network traffic rules are widely adopted due to their efficiency and accuracy, writing these rules heavily relies on expert knowledge and is costly. This is incredibly challenging when extracting rules for obfuscated Trojans. To achieve effective and efficient RAT detection, this paper proposes a Parallel Sliding Window Sequence Alignment (Parallel-SWSA) algorithm. This method uses a sliding window to segment the data, then uses the Jaccard Similarity coefficient to calculate the similarity between sequences within the window, selects the most similar sequence pairs for alignment one by one, and extracts the common feature sequences. By introducing parallel processing techniques, the extraction efficiency of the feature sequences is significantly improved. Additionally, we developed an automatic conversion tool for Snort rules to address the issue of labor-intensive rule writing. This tool can automatically transform extracted feature sequences into Snort-compatible rules, suitable for intrusion detection systems that support Snort rules. The Parallel-SWSA algorithm was validated on five datasets and achieved high detection rates. The results indicate that the method can effectively extract malicious feature sequences generated during RAT communication and possess strong noise resistance capability.

Botnet is one of the main threats to cybersecurity because of its concealment and hazardous nature, especially in autonomous systems (ASs), such as campus networks. Graph-based detection methods are attracting increasing attention due to their ability to find and use the topological features of botnets. However, constructing or obtaining a botnet dataset is always difficult, and almost all existing public datasets suffer from extreme imbalances and poor authenticity, which makes training graph-based detection models challenging. To address these problems, we propose a role-based multistage growth method for generating AS botnet datasets, which is scalable and efficient. Our method generates a background communication graph based on complex network theory, models botnet behaviors by building a state machine, and generates the traffic of botnets. The experimental results show that our method can effectively restore the AS communication graph, and the generated datasets can significantly improve the performance of various graph-based detection models. Our generated dataset is available athttps://github.com/Yebmoon/Botnet-graph-dataset.

For autonomous vehicles (AVs), the ability for effective end-to-end perception and future trajectory prediction is critical in planning a safe automatic maneuver. In the current AVs systems, perception and prediction are two separate modules. The prediction module receives only a restricted amount of information from the perception module. Furthermore, perception errors will propagate into the prediction module, ultimately having a negative impact on the accuracy of the prediction results. In this paper, we present a novel framework termed BEV-TP, a visual context-guided center-based transformer network for joint 3D perception and trajectory prediction. BEV-TP exploits visual information from consecutive multi-view images and context information from HD semantic maps, to predict better objects’ centers whose locations are then used to query visual features and context features via the attention mechanism. Generated agent queries and map queries facilitate learning of the transformer module for further feature aggregation. Finally, multiple regression heads are used to perform 3D bounding box detection and future velocity prediction. This center-based approach achieves a differentiable, simple, and efficient E2E trajectory prediction framework. Extensive experiments conducted on the nuScenes dataset demonstrate the effectiveness of BEV-TP over traditional pipelines with sequential paradigms.

In recent years, the design of models for performing the trajectory prediction task, one of the critical tasks in autonomous driving, has received great attention from researchers. However, accurately predicting future locations is challenging due to the difficulty of learning accurate intentions and modeling multimodality. Historical paths at a certain location can help predict the future trajectory of an agent currently located in that position and address these limitations. In this work, we propose a goal-based local behavior guided model, Goal-LBP, using such information (referred to as local behavior data) to generate potential goals and guide the prediction of trajectories conditioned on such goals. Goal-LBP uses Transformer encoders to extract homogeneous features and attention mechanism to represent the heterogeneous interactions and subsequently uses an encoder-decoder Gated Recurrent Unit (GRU) model to generate predictions. We evaluate our Goal-LBP using two large-scale real-world autonomous driving datasets, namely nuScenes and Argoverse. Our results show that compared to several SOTA models, Goal-LBP achieves the best ADE/FDE performance and it ranked #2 on the leaderboard of the nuScenes trajectory benchmark in June 2023. In addition, we also demonstrate that our local behavior estimator block can be easily added to two existing SOTA methods, namely AgentFormer and LaPred. Adding this LBE block improves the original AgentFormer and LaPred performance by at least 10%.

Abstract Objects in a real scene often occlude each other and inferring a complete appearance from the visible part is an important and challenging task. In this paper, the authors propose a self‐supervised generative adversarial network GIGAN (GAN for generating the invisible), which can generate the complete appearance of objects without labelled invisible part information. The authors build two cycle transformation networks CycleIncomplete (CycleI) and CycleComplete (CycleC) that share parameters to improve the accuracy of mask completion. This design does not require well‐matched training images and can make better use of the limited labelled samples. In addition, the authors propose a conditional normalization module and combine it with the inferred complete mask output. The combination not only enhances the content recovery ability and obtains more realistic outputs, but also improves the efficiency of the generation process. Experimental results show that compared with existing self‐supervised learning models, our method achieves l 1 error, mean intersection‐over‐union (mIOU), and Fréchet inception distance (FID) improvements on the COCOA and KINS datasets.

Recent years have witnessed the rapid development of car-hailing services, which provide a convenient approach for connecting passengers and local drivers using their personal vehicles. At the same time, the concern on passenger safety has gradually emerged and attracted more and more attention. While car-hailing service providers have made considerable efforts on developing real-time trajectory tracking systems and alarm mechanisms, most of them only focus on providing rescue-supporting information rather than preventing potential crimes. Recently, the newly available large-scale car-hailing order data have provided an unparalleled chance for researchers to explore the risky travel area and behavior of car-hailing services, which can be used for building an intelligent crime early warning system. To this end, in this article, we propose a Risky Area and Risky Behavior Evaluation System (RARBEs) based on the real-world car-hailing order data. In RARBEs, we first mine massive multi-source urban data and train an effective area risk prediction model, which estimates area risk at the urban block level. Then, we propose a transverse and longitudinal double detection method, which estimates behavior risk based on two aspects, including fraud trajectory recognition and fraud patterns mining. In particular, we creatively propose a bipartite graph-based algorithm to model the implicit relationship between areas and behaviors, which collaboratively adjusts area risk and behavior risk estimation based on random walk regularization. Finally, extensive experiments on multi-source real-world urban data clearly validate the effectiveness and efficiency of our system.

Introducing the words of texts, entities, and relations of a knowledge graph (KG) into the same semantic space has great significance in KG complement and knowledge computing. Current methods mainly utilize the "alignment constraint" of words and entities to construct uniform objective functions. However, the "alignment constraint" limits the joint representation space to specific KGs and texts. Meanwhile, the representation effect still suffers from the scale of the "alignment constraint". This paper propose a novel transference framework, the method firstly learns the text representation space and KG representation space independently, and then transfers the word representation in the text space to the knowledge space with projection models, and finally constructs a joint representation space. Our approach can decrease the dependency on "alignment constraint", and allow two spaces to be optimized and extended independently. Hence, it has better flexibility, general applicability and helps improve the capability of the joint representation space. Further more, to enhance the word transference performance, we incorporate the relation constraint into the mapping models. To the best of our knowledge, this is the first study using transference method to construct the joint semantic space. The experimental results show that linear mapping models are more suitable than nonlinear models during the projection process. The results of word analogy and relation extraction tasks illustrate the effectiveness of our method compared with state-of-the-art methods.

Deep learning methods can directly extract effective features from original data. However, this type of model is complex and considered to be a “black box”, which leads to low interpretability of the models. Since the results of attack detection are significant to cybersecurity, every decision should be supported with convincing reasons. Hence, the problem of interpretability has become a bottleneck for deep learning methods applied to attack detection. We propose an interpretable deep learning method based on spatial domain attention. The model can discover and locate the feature strings in the packets, thereby providing a meaningful semantic explanation for the detection results. We conducted qualitative and quantitative experiments on the DARPA1998, UNSW-NB15, and CIC-IDS-2017 datasets. Experimental results show that the interpretability of our method is superior to the state-of-the-art interpretable models in quantifiable criteria, while maintaining comparable classification accuracy.

At present, private protocols are widely used on the Internet. As a result, traditional traffic classification methods including port-based and DPI methods have become restricted. Existing machine learning-based methods depend on feature engineering, which makes feature design difficult. In addition, classification models can only classify data as predefined categories, which restricts the models when they are used to detect unknown protocol traffic. To address the above problems, we propose a two-stage traffic classification method combining a CNN model and a density-based clustering algorithm, which can classify known protocol traffic and detect arbitrary kinds of unknown protocol traffic simultaneously. We conducted sufficient experiments on the Information Security Centre of Excellence (ISCX) VPN-nonVPN and Defense Advanced Research Projects Agency (DARPA) 1998 datasets, and the accuracies on the test sets containing known and unknown protocol traffic achieved 97.03% and 98.50%, respectively, which are superior to other studies.

Keyword search over encrypted data is essential for accessing outsourced sensitive data in cloud computing. In some circumstances, the keywords that the user searches on are only semantically related to the data rather than via an exact or fuzzy match. Hence, semantic-based keyword search over encrypted cloud data becomes of paramount importance. However, existing schemes usually depend upon a global dictionary, which not only affects the accuracy of search results but also causes inefficiency in data updating. Additionally, although compound keyword search is common in practice, the existing approaches only process them as single words, which split the original semantics and achieve low accuracy. To address these limitations, we initially propose a compound concept semantic similarity (CCSS) calculation method to measure the semantic similarity between compound concepts. Next, by integrating CCSS with Locality-Sensitive Hashing function and the secure kk-Nearest Neighbor scheme, a semantic-based compound keyword search (SCKS) scheme is proposed. SCKS achieves not only semantic-based search but also multi-keyword search and ranked keyword search. Additionally, SCKS also eliminates the predefined global library and can efficiently support data update. The experimental results on real-world dataset indicate that SCKS introduces low overhead on computation and the search accuracy outperforms the existing schemes.

Deep salient object detection (DSOD), which leverages the popular deep learning techniques, is a promising new branch of salient object detection (SOD). By training on large-scale public datasets, DSOD methods showed significant performance improvement while avoiding the involvement of manually designed visual features and prior knowledge of specific datasets. This paper proposes a novel superpixel-based DSOD method based on fuzzy superpixel extraction (FSE), a neural network-based differentiable superpixel extraction method, and controlled filter convolution (CFC), a modified convolution operation that accepts two input feature maps and can balance their influences without hand-picked coefficients. Different from other superpixel-based methods, by using FSE, the proposed method is able to include superpixel extraction in the training process, which optimizes the superpixel representations according to the datasets. Then, the CFC layers combine two different parts of the information possessed by the superpixels, which are intrasuperpixel features and intersuperpixel features, to generate a unified feature map. In the experiments conducted on 5 widely used public datasets, the proposed method significantly outperformed state-of-the-art models, which proved its effectiveness and generalization ability.

Orthogonal matrix has shown advantages in training Recurrent Neural Networks (RNNs), but such matrix is limited to be square for the hidden-to-hidden transformation in RNNs. In this paper, we generalize such square orthogonal matrix to orthogonal rectangular matrix and formulating this problem in feed-forward Neural Networks (FNNs) as Optimization over Multiple Dependent Stiefel Manifolds (OMDSM). We show that the orthogonal rectangular matrix can stabilize the distribution of network activations and regularize FNNs. We propose a novel orthogonal weight normalization method to solve OMDSM. Particularly, it constructs orthogonal transformation over proxy parameters to ensure the weight matrix is orthogonal. To guarantee stability, we minimize the distortions between proxy parameters and canonical weights over all tractable orthogonal transformations. In addition, we design orthogonal linear module (OLM) to learn orthogonal filter banks in practice, which can be used as an alternative to standard linear module. Extensive experiments demonstrate that by simply substituting OLM for standard linear module without revising any experimental protocols, our method improves the performance of the state-of-the-art networks, including Inception and residual networks on CIFAR and ImageNet datasets.

Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches. In this work, we propose Decorrelated Batch Normalization (DBN), which not just centers and scales activations but whitens them. We explore multiple whitening techniques, and find that PCA whitening causes a problem we call stochastic axis swapping, which is detrimental to learning. We show that ZCA whitening does not suffer from this problem, permitting successful learning. DBN retains the desirable qualities of BN and further improves BN's optimization efficiency and generalization ability. We design comprehensive experiments to show that DBN can improve the performance of BN on multilayer perceptrons and convolutional neural networks. Furthermore, we consistently improve the accuracy of residual networks on CIFAR-10, CIFAR-100, and ImageNet.

With the development of the Internet and personal digital devices, self-organizing and open-pattern collaborations are becoming popular. In such environments, data are usually outsourced to third-party servers in the cloud, which are out of the control domain of data owners. Hence, traditional access control models, which are enforced relying on data storage servers, will face new security challenges. In this paper, we propose a self- contained read and write access control (RWAC) scheme based on ciphertext-policy attribute-based encryption (CP-ABE) and attribute-based group signature (ABGS) mechanism. By adopting a two-step encryption strategy using CP-ABE and utilizing the write control policy as the signature policy in ABGS, RWAC ensures that fine-grained read and write access control can be enforced during decryption and signature generation without dependence on any third parties. To prevent privacy leakage from RWAC policies, we adopt a CP-ABE scheme with hidden policy. Then, we introduce the policy hiding method into ABGS and propose an ABGS scheme with hidden policy. Moreover, users can trace the edit history of each data object with the signature or a write list. The security analysis indicates that RWAC is able to enforce fine-grained read and write access controls for group collaborations while also ensuring data confidentiality and integrity.

Training deep neural networks is difficult for the pathological curvature problem. Re-parameterization is an effective way to relieve the problem by learning the curvature approximately or constraining the solutions of weights with good properties for optimization. This paper proposes to reparameterize the input weight of each neuron in deep neural networks by normalizing it with zero-mean and unit-norm, followed by a learnable scalar parameter to adjust the norm of the weight. This technique effectively stabilizes the distribution implicitly. Besides, it improves the conditioning of the optimization problem and thus accelerates the training of deep neural networks. It can be wrapped as a linear module in practice and plugged in any architecture to replace the standard linear module. We highlight the benefits of our method on both multi-layer perceptrons and convolutional neural networks, and demonstrate its scalability and efficiency on SVHN, CIFAR-10, CIFAR-100 and ImageNet datasets.

Region-based Image Retrieval (RBIR), which bases itself on image segmentation rather than global features or key-point-based local features, is a branch of Content-based Image Retrieval. This paper proposes a novel RBIR-oriented image segmentation algorithm named Edge Integrated Minimum Spanning Tree (EI-MST). The difference between EI-MST and the traditional MST-based methods is that EI-MST generates MSTs over edge-maps rather than the original images, which achieved high retrieval performance cooperating with state-of-the-art matching strategies. In addition, by limiting the nodes in every MST with adaptive scale selection, EI-MST is efficient especially when processing high resolution images. The experiments on four popular public datasets proved that, EI-MST is capable of achieving higher retrieval accuracy over four widely used segmentation methods while only consuming moderate amount of time in both online and offline parts of RBIR systems.

Media streaming has largely dominated the Internet traffic and the trend will keep increasing in the next years. To efficiently distribute the media content, Information-Centric Networking (ICN) has attracted many researchers. Since end users usually obtain content from indeterminate caches in ICN, the publisher cannot reinforce data security and access control depending on the caches. Hence, the ability of self-contained protection is important for the cached contents. Attribute-based encryption (ABE) is considered the preferred solution to achieve this goal. However, the existing ABE schemes usually have problems regarding efficiency. The exponentiation in key generation and pairing operation in decryption respectively increases linearly with the number of attributes involved, which make it costly. In this paper, we propose an efficient key-policy ABE with fast key generation and decryption (FKP-ABE). In the key generation, we get rid of exponentiation and only require multiplications/divisions for each attribute in the access policy. And in the decryption, we reduce the pairing operations to a constant number, no matter how many attributes are used. The efficiency analysis indicates that our scheme has better performance than the existing KP-ABE schemes. Finally, we present an implementation framework that incorporates the proposed FKP-ABE with the ICN architecture.

Hashing has been proved as an attractive solution to approximate nearest neighbor search, owing to its theoretical guarantee and computational efficiency. Though most of prior hashing algorithms can achieve low memory and computation consumption by pursuing compact hash codes, however, they are still far beyond the capability of learning discriminative hash functions from the data with complex inherent structure among them. To address this issue, in this paper, we propose a structure sensitive hashing based on cluster prototypes, which explicitly exploits both global and local structures. An alternating optimization algorithm, respectively, minimizing the quantization loss and spectral embedding loss, is presented to simultaneously discover the cluster prototypes for each hash function, and optimally assign unique binary codes to them satisfying the affinity alignment between them. For hash codes of a desired length, an adaptive bit assignment is further appended to the product quantization of the subspaces, approximating the Hamming distances and meanwhile balancing the variance among hash functions. Experimental results on four large-scale benchmarks CIFAR-10, NUS-WIDE, SIFT1M, and GIST1M demonstrate that our approach significantly outperforms state-of-the-art hashing methods in terms of semantic and metric neighbor search.

Recent years have witnessed the success of binary hashing techniques in approximate nearest neighbor search. In practice, multiple hash tables are usually built using hashing to cover more desired results in the hit buckets of each table. However, rare work studies the unified approach to constructing multiple informative hash tables using any type of hashing algorithms. Meanwhile, for multiple table search, it also lacks of a generic query-adaptive and fine-grained ranking scheme that can alleviate the binary quantization loss suffered in the standard hashing techniques. To solve the above problems, in this paper, we first regard the table construction as a selection problem over a set of candidate hash functions. With the graph representation of the function set, we propose an efficient solution that sequentially applies normalized dominant set to finding the most informative and independent hash functions for each table. To further reduce the redundancy between tables, we explore the reciprocal hash tables in a boosting manner, where the hash function graph is updated with high weights emphasized on the misclassified neighbor pairs of previous hash tables. To refine the ranking of the retrieved buckets within a certain Hamming radius from the query, we propose a query-adaptive bitwise weighting scheme to enable fine-grained bucket ranking in each hash table, exploiting the discriminative power of its hash functions and their complement for nearest neighbor search. Moreover, we integrate such scheme into the multiple table search using a fast, yet reciprocal table lookup algorithm within the adaptive weighted Hamming radius. In this paper, both the construction method and the query-adaptive search method are general and compatible with different types of hashing algorithms using different feature spaces and/or parameter settings. Our extensive experiments on several large-scale benchmarks demonstrate that the proposed techniques can significantly outperform both the naive construction methods and the state-of-the-art hashing algorithms.

Hash-based nearest neighbor search has become attractive in many applications. However, the quantization in hashing usually degenerates the discriminative power when using Hamming distance ranking. Besides, for large-scale visual search, existing hashing methods cannot directly support the efficient search over the data with multiple sources, and while the literature has shown that adaptively incorporating complementary information from diverse sources or views can significantly boost the search performance. To address the problems, this paper proposes a novel and generic approach to building multiple hash tables with multiple views and generating fine-grained ranking results at bitwise and tablewise levels. For each hash table, a query-adaptive bitwise weighting is introduced to alleviate the quantization loss by simultaneously exploiting the quality of hash functions and their complement for nearest neighbor search. From the tablewise aspect, multiple hash tables are built for different data views as a joint index, over which a query-specific rank fusion is proposed to rerank all results from the bitwise ranking by diffusing in a graph. Comprehensive experiments on image search over three well-known benchmarks show that the proposed method achieves up to 17.11% and 20.28% performance gains on single and multiple table search over the state-of-the-art methods.

Recent years have witnessed the success of hashing techniques in fast nearest neighbor search. In practice many applications (eg., visual search, object detection, image matching, etc.) have enjoyed the benefits of complementary hash tables and information fusion over multiple views. However, most of prior research mainly focused on compact hash code cleaning, and rare work studies how to build multiple complementary hash tables, much less to adaptively integrate information stemming from multiple views. In this paper we first present a novel multi-view complementary hash table method that learns complementarity hash tables from the data with multiple views. For single multi-view table, using exemplar based feature fusion, we approximate the inherent data similarities with a low-rank matrix, and learn discriminative hash functions in an efficient way. To build complementary tables and meanwhile maintain scalable training and fast out-of-sample extension, an exemplar reweighting scheme is introduced to update the induced low-rank similarity in the sequential table construction framework, which indeed brings mutual benefits between tables by placing greater importance on exemplars shared by mis-separated neighbors. Extensive experiments on three large-scale image datasets demonstrate that the proposed method significantly outperforms various naive solutions and state-of-the-art multi-table methods.

The computation of semantic similarity between words is important in information retrieval, knowledge acquisition and many other fields. The existing studies are mainly aiming at single concepts composed of single terms. For the compound concepts composed of multiple terms, they usually neglect the special constitution features of compounds and only process them as single concepts, which may affect the ultimate accuracy. In this paper, we propose a novel ontology-based Compound Concept Semantic Similarity calculation approach called CCSS which exploits concept constitution features. In CCSS, the compound is decomposed into Subject headings and Auxiliary words (SaA), and the relationships between these two sets are used to measure the similarity. Besides, the errors that may be caused by SaA recognition are corrected. Moreover, several information sources of ontology such as taxonomical features, local density and depth are considered. Extensive experimental evaluations demonstrate that our approach significantly outperforms existing approaches.

Hashing methods are effective in generating compact binary signatures for images and videos. This paper addresses an important open issue in the literature, i.e., how to learn compact hash codes by enhancing the complementarity among different hash functions. Most of prior studies solve this problem either by adopting time-consuming sequential learning algorithms or by generating the hash functions which are subject to some deliberately-designed constraints (e.g., enforcing hash functions orthogonal to one another). We analyze the drawbacks of past works and propose a new solution to this problem. Our idea is to decompose the feature space into a subspace shared by all hash functions and its complementary subspace. On one hand, the shared subspace, corresponding to the common structure across different hash functions, conveys most relevant information for the hashing task. Similar to data de-noising, irrelevant information is explicitly suppressed during hash function generation. On the other hand, in case that the complementary subspace also contains useful information for specific hash functions, the final form of our proposed hashing scheme is a compromise between these two kinds of subspaces. To make hash functions not only preserve the local neighborhood structure but also capture the global cluster distribution of the whole data, an objective function incorporating spectral embedding loss, binary quantization loss, and shared subspace contribution is introduced to guide the hash function learning. We propose an efficient alternating optimization method to simultaneously learn both the shared structure and the hash functions. Experimental results on three well-known benchmarks CIFAR-10, NUS-WIDE, and a-TRECVID demonstrate that our approach significantly outperforms state-of-the-art hashing methods.

Hashing technique has become a promising approach for fast similarity search. Most of existing hashing research pursue the binary codes for the same type of entities by preserving their similarities. In practice, there are many scenarios involving nearest neighbor search on the data given in matrix form, where two different types of, yet naturally associated entities respectively correspond to its two dimensions or views. To fully explore the duality between the two views, we propose a collaborative hashing scheme for the data in matrix form to enable fast search in various applications such as image search using bag of words and recommendation using user-item ratings. By simultaneously preserving both the entity similarities in each view and the interrelationship between views, our collaborative hashing effectively learns the compact binary codes and the explicit hash functions for out-of-sample extension in an alternating optimization way. Extensive evaluations are conducted on three well-known datasets for search inside a single view and search across different views, demonstrating that our proposed method outperforms state-of-the-art baselines, with significant accuracy gains ranging from 7.67% to 45.87% relatively.

In recent years, the concept similarity measure has received wide attention in many applications, such as ontology construction, text analysis, image retrieval, etc.Currently, the concept similarity measure depends on the information mining in various knowledge bases, like dictionaries, ontologies, image annotation labels, and search engines.However, these knowledge bases usually only contain semantic information.With the development of the Internet and the popularity of the digital imaging devices, a lot of images and related texts have appeared, which help us to further mine the concept similarity relationships.The concept similarity is the outcome of human subjective perception.In addition to analysis of semantic information, the content of image itself precisely provides the visual perception information, which also plays an important role in the access of concept similarity relationships.To integrate both image semantic and visual information, in this paper we propose an ontology concept similarity measure that simultaneously utilizes the image semantic annotations and visual features to optimize the ontology-based metrics.The experiment result on the Corel dataset demonstrates the effectiveness of our proposed method.

Semi-supervised learning and active learning are important techniques to build more accurate model while labeled data are scarce. The objective of this paper is combining both to effectively relieve user labor for multi-class annotation. We propose a novel graph-based active semi-supervised learning framework which aim at efficiently learning a multi-class model with minimal human labor. In particular, we propose Minimize Expected Global Uncertainty algorithm to actively select examples (for labels), which naturally integrates with the probabilistic results of graph-based semi-supervised learning. Meanwhile, we update the model incrementally by decomposed formulation while the new example are incorporated for training, which only has the time complexity of O(n), compared to the original re-training of O(n3). Extensive evaluations over three real-world datasets demonstrate that our proposed method has the superior performance comparing with the baselines and the capability to efficiently build more accurate model with fractional human labor.

Recently hash-based nearest neighbor search has become attractive in many applications due to its compressed storage and fast query speed. However, the quantization in the hashing process usually degenerates its discriminative power when using Hamming distance ranking. To enable fine-grained ranking, hash bit weighting has been proved as a promising solution. Though achieving satisfying performance improvement, state-of-the-art weighting methods usually heavily rely on the projection's distribution assumption, and thus can hardly be directly applied to more general types of hashing algorithms. In this paper, we propose a new ranking method named QRank with query-adaptive bitwise weights by exploiting both the discriminative power of each hash function and their complement for nearest neighbor search. QRank is a general weighting method for all kinds of hashing algorithms without any strict assumptions. Experimental results on two well-known benchmarks MNIST and NUS-WIDE show that the proposed method can achieve up to 17.11\% performance gains over state-of-the-art methods.

This article defines a new hashing task motivated by real-world applications in content-based image retrieval, that is, effective data indexing and retrieval given mixed query (query image together with user-provided keywords). Our work is distinguished from state-of-the-art hashing research by two unique features: (1) Unlike conventional image retrieval systems, the input query is a combination of an exemplar image and several descriptive keywords, and (2) the input image data are often associated with multiple labels. It is an assumption that is more consistent with the realistic scenarios. The mixed image-keyword query significantly extends traditional image-based query and better explicates the user intention. Meanwhile it complicates semantics-based indexing on the multilabel data. Though several existing hashing methods can be adapted to solve the indexing task, unfortunately they all prove to suffer from low effectiveness. To enhance the hashing efficiency, we propose a novel scheme “boosted shared hashing”. Unlike prior works that learn the hashing functions on either all image labels or a single label, we observe that the hashing function can be more effective if it is designed to index over an optimal label subset. In other words, the association between labels and hash bits are moderately sparse. The sparsity of the bit-label association indicates greatly reduced computation and storage complexities for indexing a new sample, since only limited number of hashing functions will become active for the specific sample. We develop a Boosting style algorithm for simultaneously optimizing both the optimal label subsets and hashing functions in a unified formulation, and further propose a query-adaptive retrieval mechanism based on hash bit selection for mixed queries, no matter whether or not the query words exist in the training data. Moreover, we show that the proposed method can be easily extended to the case where the data similarity is gauged by nonlinear kernel functions. Extensive experiments are conducted on standard image benchmarks like CIFAR-10, NUS-WIDE and a-TRECVID. The results validate both the sparsity of the bit-label association and the convergence of the proposed algorithm, and demonstrate that the proposed hashing scheme achieves substantially superior performances over state-of-the-art methods under the same hash bit budget.

Recent years have witnessed the success of hashingtechniques in approximate nearest neighbor search. Inpractice, multiple hash tables are usually employed toretrieve more desired results from all hit buckets ofeach table. However, there are rare works studying theunified approach to constructing multiple informativehash tables except the widely used random way. In thispaper, we regard the table construction as a selectionproblem over a set of candidate hash functions. Withthe graph representation of the function set, we proposean efficient solution that sequentially applies normal-ized dominant set to finding the most informative andindependent hash functions for each table. To furtherreduce the redundancy between tables, we explore thereciprocal hash tables in a boosting manner, where thehash function graph is updated with high weights em-phasized on the misclassified neighbor pairs of previoushash tables. The construction method is general andcompatible with different types of hashing algorithmsusing different feature spaces and/or parameter settings.Extensive experiments on two large-scale benchmarksdemonstrate that the proposed method outperforms bothnaive construction method and state-of-the-art hashingalgorithms, with up to 65.93% accuracy gains.

Recent years have witnessed the active development of hashing techniques for nearest neighbor search over big datasets. However, to apply hashing techniques successfully, there are several important issues remaining open in selecting features, hashing algorithms, parameter settings, kernels, etc. In this work, we unify all these selection problems into a hash bit selection framework, i.e., selecting the most informative hash bits from a pool of candidate bits generated by different types of hashing methods using different feature spaces and/or parameter settings, etc. We represent the bit pool as a vertex- and edge-weighted graph with the candidate bits as vertices. The vertex weight represents the bit quality in terms of similarity preservation, and the edge weight reflects independence (non-redundancy) between bits. Then we formulate the bit selection problem as quadratic programming on the graph, and solve it efficiently by replicator dynamics. Moreover, a theoretical study is provided to reveal a very interesting insight: the selected bits actually are the normalized dominant set of the candidate bit graph. We conducted extensive large-scale experiments for three important application scenarios of hash techniques, i.e., hashing with multiple features, multiple hashing algorithms, and multiple bit hashing. We demonstrate that our bit selection approach can achieve superior performance over both naive selection methods and state-of-the-art hashing methods under each scenario, with significant accuracy gains ranging from 10% to 50% relatively.

Semi-supervised learning methods can largely leverage the image annotation problem using both labeled and unlabeled data, especially when the labeled information is quite limited. However, most of them suffer the expensive computation stemming from the batch learning on large training dataset. In this paper we proposed a highly efficient semi-supervised annotation approach with the partial label propagation based on the graph representation. Specifically, the label information is first propagated from labeled samples to the unlabeled ones, and then spreads only among unlabeled ones like a spreading activation network. Our approach takes advantage of the decomposed formulation to achieve a fast incremental learning instead of the expensive batch one without accuracy loss. Extensive evaluations over two large datasets demonstrate the superior performance of the proposed method and its significant efficiency.

Hashing for nearest neighbor search has attracted great attentions in the past years. Many hashing methods have been successfully applied in real-world applications like the mobile product search. The performance of these applications usually highly relies on the quality of hash bits. However, it still lacks of a general method that can provide good hash bits for different scenarios. In this paper, we propose a novel method that can select compact, independent and informative hash bits using the Markov Process. Our method can serve as a unified framework compatible with different hashing methods. We design two algorithms, BS-CMP and BS-DMP, and formulate the selection problem as the subgraph discovery on a graph. Experiments are conducted for two important selection scenarios when applying hash techniques, i.e., hashing using different hashing algorithms and hashing with multiple features. The result indicates that our proposed bit selection approaches outperform naive selection methods significantly under aforementioned two scenarios.

The explosive growth of image data leads to severe challenges to the traditional image retrieval methods. In order to manage massive images more accurate and efficient, this paper firstly proposes a scalable architecture for image retrieval based on a uniform data model and makes this function a sub-engine of AUDR, an advanced unstructured data management system, which can simultaneously manage several kinds of unstructured data including image, video, audio and text. The paper then proposes a new image retrieval algorithm, which incorporates rich visual features and two text models for multi-modal retrieval. Experiments on both ImageNet dataset and ImageCLEF medical dataset show that our proposed architecture and the new retrieval algorithm are appropriate for efficient management of massive image.

Recently locality-sensitive hashing (LSH) algorithms have attracted much attention owing to its empirical success and theoretic guarantee in large-scale visual search. In this paper we address the new topic of hashing with multi-label data, in which images in the database are assumed to be associated with missing or noisy multiple labels and each query consists of a query image and several textual search terms, similar to the new "Search with Image" function introduced by the Google Image Search. The returned images are judged based on the combination of visual similarity and semantic information conveyed by search terms. In most of the state-of-the-art approaches, the learned hashing functions are universal for all labels. To further enhance the hashing efficiency for such multi-label data, we propose a novel scheme "boosted shared hashing". Our basic observation is that image labels typically form cliques in the feature space. Hashing efficacy can be greatly improved by making each hashing function more targeted at and only shared across such cliques instead of all labels in conventional hashing methods. In other words, each hashing function is deliberately designed such that it is especially effective for a subset of labels. The targeted, but sparse association between labels and hash bits reduces the computation and storage when indexing a new datum, since only a small number of relevant hashing functions become active given the labels. We develop a Boosting-style algorithm for simultaneously optimizing the label subset and hashing function in a unified framework. Experimental results on standard image benchmarks like CIFAR-10 and NUS-WIDE show that the proposed hashing scheme achieves substantially superior performances over conventional methods in terms of accuracy under the same hash bit budget.

Hashing methods, which generate binary codes to preserve certain similarity, recently have become attractive in many applications like large scale visual search. However, most of state-of-the-art hashing methods only utilize single feature type, while combining multiple features has been proved very helpful in image search. In this paper we propose a novel hashing approach that utilizes the information conveyed by different features. The multiple feature hashing can be formulated as a similarity preserving problem with optimal linearly-combined multiple kernels. Such formulation is not only compatible with general types of data and diverse types of similarities indicated by different visual features, but also helpful to achieve fast training and search. We present an efficient alternating optimization to learn the hashing functions and the optimal kernel combination. Experimental results on two well-known benchmarks CIFAR-10 and NUS-WIDE show that the proposed method can achieve 11% and 34% performance gains over state-of-the-art methods.

Performance of state-of-the-art image retrieval systems has been improved significantly using bag-of-words approaches. After represented by visual words quantized from local features, images can be indexed and retrieved using scalable textual retrieval approaches. However, there exist at least two issues unsolved, especially for search by mobile images with large variations: (1) the loss of features discriminative power due to quantization; and (2) the underuse of spatial relationships among visual words. To address both issues, considering properties of mobile images, this paper presents a novel method coupling visual and spatial information consistently: to improve discriminative power, features of the query image are first grouped using both matched visual features and their spatial relationships; Then grouped features are softly matched to alleviate quantization loss. Experiments on both UKBench database and a collected database with more than one million images show that the proposed method achieves 10% improvement over the approach with a vocabulary tree and bundled feature method.

This paper proposes a model for image representation and image analysis using a multi-layer neural network, which is rooted in the human vision system. Having complex neural layers to represent and process information, the biological vision system is far more efficient than machine vision system. The neural model simulate non-classical receptive field of ganglion cell and its local feedback control circuit, and can represent images, beyond pixel level, self-adaptively and regularly. The results of experiments, rebuilding, distribution and contour detection, prove this method can represent image faithfully with low cost, and can produce a compact and abstract approximation to facilitate successive image segmentation and integration. This representation schema is good at extracting spatial relationships from different components of images and highlighting foreground objects from background, especially for nature images with complicated scenes. Further it can be applied to object recognition or image classification tasks in future.

Since there has been significant amount of XML documents generated in various application domains, efficient XML management has become an important problem. Distributed XML storage and parallel query based on Map Reduce can be an effective solution to this problem. As XML data placement strategy is a key factor of parallel system performance, in this paper we present an XML placement strategy, which is Query Workload Estimation based XML Placement strategy (QWEXP) for efficient distributed XML storage and parallel query. To achieve query workload balance, it partitions XML based on query workload estimation which is calculated by XML structure without knowing of user queries, considering that in common application scenarios user queries are unknown in advance. The partitioned XML segments are around an XML storage unit W0, to support scalability of parallel XML database. Finally segments are distributed to each processing node evenly to ensure workload balance on parallel query execution. Experimental results have shown that QWEXP promotes the speedup and scale up properties of parallel XML system greatly.

A Grid system is a Virtual Organization that is composed of several autonomous domains. Authorization in such a system needs to be flexible and scalable to support multiple security policies. Basing on the Web Services security specifications such as XACML, SAML, and the special security needs of the Grid computing, we have constructed an authorization framework in the Globus Toolkit 4 that can support multiple policies. This paper describes the concepts of our design and introduces the structure and the components of the authorization framework. To show the flexibility and scalability of the framework, we introduce a new blacklist/whitelistbased authorization mechanism that can be seamlessly integrated into the framework.