Video understanding endeavors to generate descriptive texts by analyzing structured semantics from dynamic visual sequences, thus facilitating context-aware reasoning and interpretation. Recent advancements primarily rely on patch-level visual–textual alignment, bridging the gap between visual and textual modalities and therefore enabling more comprehensive reasoning. While promising, they often struggle to capture object-level semantics and temporal dependencies, resulting in limited interpretability and suboptimal compositional understanding. To address these issues, we propose a novel temporal relation framework for multi-modal video understanding, dubbed VideoU-MTR, which explicitly models object-level temporal relations to facilitate fine-grained and coherent representations of cross-frame object interactions. Specifically, we introduce a query-oriented frames identification mechanism that synergistically combines textual and visual attention, allowing the model to dynamically attend to semantically relevant video content across hierarchical levels while effectively filtering out irrelevant information. Furthermore, we employ an explicit temporal relation module to capture fine-grained temporal dependencies and inter-object dynamics by modeling object-centric sequences with time-aware attention and frame-level embeddings. Additionally, we propose a cross-modal alignment adapter that aligns temporally contextualized visual features with linguistic semantics at both object and frame levels. Extensive experiments on eight benchmarks across video question answering (VideoQA), long-term video understanding (LTVU), and video captioning (VideoCap) benchmarks demonstrate that VideoU-MTR achieves superior performance compared to state-of-the-art methods. Moreover, visualization analysis further validates the effectiveness of incorporating temporal information for enhancing video comprehension.

This paper presents MonoRelief V2, an end-to-end model designed for directly recovering 2.5D reliefs from single images under complex material and illumination variations. In contrast to its predecessor, MonoRelief V1 (Gao et al. 2025), which was solely trained on synthetic data, MonoRelief V2 incorporates real data to achieve improved robustness, accuracy and efficiency. To overcome the challenge of acquiring large-scale real-world dataset, we generate approximately 15,000 pseudo-real images using a text-to-image generative model, and derive corresponding depth pseudo-labels through fusion of depth and normal predictions. Furthermore, we construct a small-scale real-world dataset (800 samples) via multi-view reconstruction and detail refinement. MonoRelief V2 is then progressively trained on the pseudo-real and real-world datasets. Comprehensive experiments demonstrate its state-of-the-art performance both in depth and normal predictions, highlighting its strong potential for a range of downstream applications.

Text watermarking provides an effective solution for identifying synthetic text generated by large language models. However, existing techniques often focus on satisfying specific criteria while ignoring other key aspects, lacking a unified evaluation. To fill this gap, we propose the Comprehensive Evaluation Framework for Watermark (CEFW), a unified framework that comprehensively evaluates watermarking methods across five key dimensions: ease of detection, fidelity of text quality, minimal embedding cost, robustness to adversarial attacks, and imperceptibility to prevent imitation or forgery. By assessing watermarks according to all these key criteria, CEFW offers a thorough evaluation of their practicality and effectiveness. Moreover, we introduce a simple and effective watermarking method called Balanced Watermark (BW), which guarantees robustness and imperceptibility through balancing the way watermark information is added. Extensive experiments show that BW outperforms existing methods in overall performance across all evaluation dimensions. We release our code to the community for future research1.

Web services, as an effective realization technology of SOA, have been deployed largely on the Internet. Comparing with the traditional Web pages, the information island problem existing in Web services field is more serious. Web services with specific functions not only submerge in the Web services library, but also submerge in the traditional Web pages library. As a result, finding web service rapidly and accurately becomes a problem needing solving, and this promots the research on the field of web services discovery. In this paper, we propose a semantics mining&indexing-based rapid Web services discovery framework. First, focus on the Web services formalizing model with the basic information of Web service or composition. Then propose a Web services matching engine with high accurency, and there is no semantics ontology dependence in matching engine, also, we propose a Web services discovery framework basing index library, which can help providing a low processing time in request searching. When creating the index library, we apply semantics mining to overcome the shortcoming of low searching accurancy in traditional index framework. Finally, the experiments are tested that the Web service discovery framework shows high precision rate and recall rate, which can provides a solution to the problem of persuiting both low searching processing time and high search accurancy in Web service discovery field.

In recent years, Web service discovery has been a hot research topic. In this paper, we propose a novel Web services discovery approach, which can mine the underlying semantic structures of interaction interface parameters to help users find and employ Web services, and can match interfaces with high precision when the parameters of those interfaces contain meaningful synonyms, abbreviations, and combinations of disordered fragments. Our approach is based on mining the underlying semantics. First, we propose a conceptual Web services description model in which we include the type path for the interaction interface parameters in addition to the traditional text description. Then, based on this description model, we mine the underlying semantics of the interaction interface to create index libraries by clustering interaction interface names and fragments under the supervision of co-occurrence probability. This index library can help provide a high-efficiency interface that can match not only synonyms but also abbreviations and fragment combinations. Finally, we propose a Web service Operations Discovery algorithm (OpD). The OpD discovery results include two types of Web services: services with “Single” operations and services with “Composite” operations. The experimental evaluation shows that our approach performs better than other Web service discovery methods in terms of both discovery time and precision/ recall rate.

This paper proposes a novel Web service discovery approach that depend on the mining the underlying semantic structures of interaction interface parameters, which can match interfaces with high precision when the parameters of those interfaces contain meaningful synonyms, abbreviations, and combinations of disordered fragments. Especially, we propose a conceptual Web services description model in which we include the type path for the interaction interface parameters in addition to the traditional text description. Then, based on this description model, we mine the underlying semantics of the interaction interface to create index libraries by clustering interaction interface names and fragments under the supervision of co-occurrence probability. Finally, we propose a Web service Operations Discovery algorithm (OpD) that support the “Single” operations and services with “Composite” operations discovery. The experimental shows that our approach performs better than other approaches in terms of both discovery time and precision.

The mashup is a hot research topic in recent years. In this paper, we propose an efficient Mashup Resource Discovery(MRD) approach to facilitating mashup searching. Basing on an index library, MRD acts high performance in response time. By an external ontology base and a synonym base, we apply a semantics discovery, avoiding semantics annotation in mashup description files. By evaluating the prestige of mashups(especially for mashup api), we rank the results and make mashups with high prestige get higher ranking. The experimental evaluation shows that our MRD act high performance both in time consuming and r-p curve statistics.

During the design procedure of BPEL (Business Process Execution Language) processes, there may be control dependency deadlocks among the activities in BPEL. We design a novel Agree/Refuse Matrix (ARM) to real-timely detect control dependency deadlocks. Online detection approach can be integrated into Active BPEL Designer to extend their functions and improve the accuracy of BPEL processes. Most importantly, this method's real-time property can help avoiding detecting the whole process from scratch caused by process's partial modifications.

Web service evaluation is one of the key problems in web service discovery and selection research fields. In this paper, we propose an approach to evaluate the web service performance. Different from traditional evaluation methods, our approach is based on users experience, and we apply the idea and result in common webs evaluation fields to help construct our evaluation system. We import the Alexa ranking to help evaluate the information providing performance of web services, we import the idea of Page Rank to help designing our evaluation method for the function sharing performance of web services.

With the rapid development of Service-Oriented Architecture (SOA), more and more enterprise applications are built on the Enterprise Services Bus (ESB). However, ESB would not be able to deal with the exchange of data among multiple ESBs. In this paper, we propose an Enterprise Cloud Bus (ECB) framework that combines the WS-Notification with cloud computing. On the basis of WS-Notification specification and cloud queue model, we design and implement the Subscribe Request Queue cloud service model that supports real-time communication among distributed ESB, and supports running non-Service components or composition services deployed on distributed ESB or in different business process. On the basis of cloud platform, our framework shows better scalability and reliability.

We propose a Discovery approach to find web services composition flows sorted by similarity. The approach extracts information from BPEL files. When creating new web services composition, the discovery result can be reused directly or provide reference. We import the lexical semantic in matching keywords. By analysis and proof, we show that our keyword splitting method can extend the application of lexical semantics matching to a large extent and our approach can provide higher precision ratio than traditional search engine.