To address the limitations of Transformer decoders in capturing edge details, recognizing local textures and modeling spatial continuity, this paper proposes a novel decoder framework specifically designed for medical image segmentation, comprising three core modules. First, the Adaptive Cross-Fusion Attention (ACFA) module integrates channel feature enhancement with spatial attention mechanisms and introduces learnable guidance in three directions (planar, horizontal, and vertical) to enhance responsiveness to key regions and structural orientations. Second, the Triple Feature Fusion Attention (TFFA) module fuses features from Spatial, Fourier and Wavelet domains, achieving joint frequency-spatial representation that strengthens global dependency and structural modeling while preserving local information such as edges and textures, making it particularly effective in complex and blurred boundary scenarios. Finally, the Structural-aware Multi-scale Masking Module (SMMM) optimizes the skip connections between encoder and decoder by leveraging multi-scale context and structural saliency filtering, effectively reducing feature redundancy and improving semantic interaction quality. Working synergistically, these modules not only address the shortcomings of traditional decoders but also significantly enhance performance in high-precision tasks such as tumor segmentation and organ boundary extraction, improving both segmentation accuracy and model generalization. Experimental results demonstrate that this framework provides an efficient and practical solution for medical image segmentation.

Deep neural networks (DNNs) can automatically fetch specific features from seismic data, which can be used in the process of multiple elimination. An extended single-sided autofocusing guided by an inverse-scattering theory is introduced to remove internal multiples in a data-driven manner, which can be used as labels in DNNs. In this research, we have developed a novel workflow to explore the potential of neural networks in identifying the internal multiples with the guidance of inverse-scattering theory. In particular, we use the U-net with a self-attention (SA) block during the training process, which could extract features from seismic data effectively. The neural network is fed with training data pairs, consisting of the shot records with internal multiples, and the primary-only datasets as labels, which are generated by an extended single-sided autofocusing method. The testing pairs show that internal multiple elimination via the neural network takes the advantage of the extended single-sided autofocusing method and is cheaper when the neural network is well-trained. The numerical results demonstrate the promising performances of the SA U-net method in terms of noise resistance, internal multiples elimination, and the reverse time migration (RTM) images, in comparison with the extended single-sided autofocusing method.

Marchenko equation-based imaging methods have been proved as an effective way to remove the internal multiples. Conventional Marchenko imaging needs the reflection response at the surface and an estimate of the direct arrival times from the virtual source point to the acquisition surface. It contains the procedure of redatuming and imaging. The redatuming process is valid only for layered media with a moderately curved interface. We rederive the single reflection retrieval by a focusing source method based on the scattering theory and avoid the use of redatuming plane and the upgoing/downgoing decomposition. This scheme reproduces a new data free from internal multiples for complex structures, such as salt dome. Our theory/method expands the application range of Marchenko imaging and internal multiple elimination. With an artifact-free image obtained by this procedure, an illumination compensation can be further applied to obtain a high-fidelity image, especially in the subsalt area. Numerical examples using the 2-D SEG/EAGE salt model are shown to validate this method.

With the development of communication systems, information securities remain one of the main concerns for the last few years. The smart devices are connected to communicate, process, compute, and monitor diverse real-time scenarios. Intruders are trying to attack the network and capture the organization’s important information for its own benefits. Intrusion detection is a way of identifying security violations and examining unwanted occurrences in a computer network. Building an accurate and effective identification system for intrusion detection or malicious activities can secure the existing system for smooth and secure end-to-end communication. In the proposed research work, a deep learning-based approach is followed for the accurate intrusion detection purposes to ensure the high security of the network. A convolution neural network based approach is followed for the feature classification and malicious data identification purposes. In the end, comparative results are generated after evaluating the performance of the proposed algorithm to other rival algorithms in the proposed field. These comparative algorithms were FGSM, JSMA, C&W, and ENM. After evaluating the performance of these algorithms and the proposed algorithm based on different threshold values ranging, Lp norms, and different parametric values for c, it was concluded that the proposed algorithm outperforms with small Lp values and high Kitsune scores. These results reflect that the proposed research is promising toward the identification of attack on data packets, and it also reflects the applicability of the proposed algorithms in the network security field.

For full-waveform inversion (FWI), building the salt structure velocity model is a challenging problem. In the absence of a high-fidelity initial model, low-frequency seismic data are indispensable for accurate reconstruction of the long-wavelength components of salt domes, which are often missing in field data. The envelope isolates the amplitude information from the seismic data and has a stronger linear relationship with the velocity than the seismic data. It is used to enhance the convexity of the objective function in an envelope inversion (EI). However, the properties of the envelope are not effectively utilized in EI due to the lack of their proper understanding. In order to solve the problems that EI has in building the salt structure velocity, such as the cycle-skipping problem, the gradient calculation problem caused by the waveform Fréchet derivative, and the multisolution problem caused by the missing polarity information of the envelope, we propose a multiscale direct signed EI (MSDSEI) based on the direct envelope Fréchet derivative and multiscale signed envelope. The development process from EI to MSDSEI also inspired us to understand the physical mechanism involved in the low-frequency components of the envelope: the signed envelope can be regarded as a low-pass filter of the reflection sequences in the subsurface. Thus, we use the smoothness and phase-independent properties of the envelope to propose an envelope-based full-band seismic data reconstruction method for multiscale FWI. Finally, the performance of various EI methods is verified on the Sigsbee2A model.

With the advent of Web 2.0 application, and the increasing number of browsers and platforms on which the applications can be executed, cross-browser incompatibilities (XBIs) are becoming a serious problem for organizations to develop web-based software. Although many techniques and tools have been proposed to detect cross-browser issues, there still lacks a comprehensive approach to locate the root causes of various cross-browser issues. To address this limitation, this paper proposes X-Diag, an automated technique for debugging XBIs based on our findings from an extensive study of the root causes of XBIs in real-world applications. The characteristic of X-Diag is that it narrows down the root causes of cross-browser issues step-by-step by checking whether such issues are caused by incompatible DOM APIs, CSS properties or Html elements. Our empirical evaluation shows that X-Diag is effective in locating the root causes of cross-browser issues, and can provide useful support to developers for (eventually) eliminate XBIs.

Recently, graph-based semisupervised learning methods have been widely applied in multimedia research area. However, for the application of video semantic annotation in multilabel setting, these methods neglect an important characteristic of video data: The semantic concepts appear correlatively and interact naturally with each other rather than exist in isolation. In this paper, we adapt this semantic correlation into graph-based semisupervised learning and propose a novel method named correlative linear neighborhood propagation to improve annotation performance. Experiments conducted on the Text REtrieval Conference VIDeo retrieval evaluation data set have demonstrated its effectiveness and efficiency.

This paper presents a novel learning-based method, called “multi-layer multi-instance (MLMI) learning,” for video concept detection. Most of existing methods have treated video as a flat data sequence and have not investigated theintrinsic hierarchy structureof the video content deeply. However, video is essentially a kind of media with ML structure. For example, a video can be represented by a hierarchical structure including, from large to small,shot,frame, andregion, where each pair of contiguous layers fits the typical MI setting. We call such a ML structure and the MI relations embedded in the structure as the MLMI setting. In this paper, we systematically study both ML structure and MI relations embedded in video content by formulating video concept detection as a MLMI learning problem. Specifically, we first construct a MLMI kernel to simultaneously model such ML structure and MI relations. To deal with theambiguity propagationproblem which is introduced by weak labeling and ML structure, we then propose a regularization framework which takeshyper-bagprediction error, sublayer prediction error, inter-layer inconsistency measure, and classifier complexity into consideration. We have applied the proposed MLMI learning method to concept detection task over TRECVid 2005 development corpus, and report better performance to vector-based and the state-of-the-art MI learning methods.

Automatic image annotation is a promising solution to enable more effective image retrieval by keywords. Traditionally, statistical models for image auto-annotation predicate each annotated keyword independently without considering the correlation of words. In this paper, we propose a novel probability model, in which the correspondence between keywords and image visual tokens/regions and the word-to-word correlation are well combined. We employ the conditional probability to express two kinds of correlation uniformly and obtain the correspondence between keyword and visual feature with the cross-media relevance model (CMRM). Experiments conducted on standard Corel dataset demonstrate the effectiveness of the proposed method for image automatic annotation.

This paper proposes a novel energy minimization based approach to video scene segmentation. In video content analysis, scene is defined as a set of adjacent shots related to a particular setting or a continuous action in one place. This indicates that not only the global distribution of time and content, but also the local temporal continuity should be taken into account for scene segmentation. Motivated from this fact, we formulate the segmentation procedure as a unified energy minimization framework, in which the global and local constraint is represented by content and context energy, respectively. This energy minimization problem is optimized by two steps in an iterative fashion: first find an initial estimation of scene label for content energy by a generative model; and then iterated conditional modes (ICM) is used for context energy to find the global optimization. Furthermore, a boundary voting procedure is devised to decide the optimal scene boundaries. We apply EMS on an extensive set of home videos and feature movies, and report superior performance compared with several existing key approaches to scene segmentation.

In this paper, we address the issue of typicality ranking for video annotation and propose to use a novel criterion, average typicality precision (ATP), to replace the frequently used one, average precision (AP), for evaluating the performance of video annotation algorithms. General annotation methods just care the number of true-positive samples at the top of the ranked list; they actually do not care the order of these samples. We argue that it is more reasonable to rank "typical" true-positive samples higher than non-typical ones, which can be evaluated by our proposed ATP. However, generally the labels of the training data only differentiate true from false; that is to say, typical or non-typical training samples have the same contribution to the learning process. Therefore, the labels of the unlabeled data learned from these training data can not well measure the typicality. In this paper, we relax the labels of the training data to real-valued typicality scores by a pre-processing stage, which is accomplished by three approaches, including density estimation, user feedback and active learning. Then the typicality scores of the training data are propagated to unlabeled data using manifold-ranking. Experiments conducted on the TRECVID data set demonstrate that this typicality ranking scheme is more consistent with human perception than normal accuracy based ranking schemes.

In video concept detection, most existing methods have not well studied the intrinsic hierarchical structure of video content. However, unlike flat attribute-value data used in many existing methods, video is essentially a structured media with multi-layer representation. For example, a video can be represented by a hierarchical structure including, from large to small, shot, key-frame, and region. Moreover, it fits the typical Multi-Instance (MI) setting in which the "bag-instance" correspondence is embedded among contiguous layers. We call such multi-layer structure and the "bag-instance" relation embedded in the structure as Multi-Layer Multi-Instance (MLMI) setting in this paper. We formulate video concept detection as an MLMI learning problem in which a rooted tree with MLMI nature embedded is devised to represent a video segment. Furthermore, by fusing the information from different layers, we construct a novel MLMI kernel to measure the similarities between the instances in the same and different layers. In contrast to traditional MI learning, both the Multi-Layer structure and Multi-Instance relations are leveraged simultaneously in the proposed kernel. We applied MLMI kernel to concept detection task on TRECVID 2005 corpus and reported superior performance (+25% in Mean Average Precision) to standard Support Vector Machine based approaches.