Transformer-based hybrid architectures have achieved remarkable performance in dynamic hand gesture recognition. However, their high computational overhead and model size limit deployment in resource-limited environments. Motivated by this limitation, we propose the Decoupled Spatio-Temporal Convolutional Network (DSTCNet), a lightweight, pure convolutional framework trained end-toend delivering high accuracy with a fraction of the complexity. DSTCNet integrates two components: (1) an efficient pseudo-3D spatial backbone, the Pseudo-3D Gated Attentional Fusion Network (P3D-GAFNet), enhancing spatial feature extraction via positional prior injection, and (2) a temporal modeling network, the Multi-Variable Decomposition Temporal Convolutional Network (MVD-TCN), leveraging multi-variable feature decomposition with modern convolutional blocks to capture long-range temporal dependencies without the cost of self-attention. With only 9.6M parameters, DSTCNet matches or surpasses the accuracy of substantially larger models on several challenging benchmarks, while offering high computational efficiency, lower memory usage, and reduced energy consumption—making it a practical solution for deployment on edge devices. Our results demonstrate that modernized pure convolutional architectures can serve as a robust and efficient alternative to hybrid designs, offering valuable insights for the broader field of video understanding.

Dynamic Hand Gesture Recognition (DHGR) aims to detect dynamic hand movements by leveraging the features and continuity of video frames. Existing methods mainly utilize backbone networks to extract latent features from individual video frames and sequence modeling through a Transformer. However, the hand usually occupies a relatively small proportion in the video, resulting in a large amount of invalid information in the extracted features, which affects the model’s robustness and subsequent temporal modeling performance. Moreover, the traditional Transformer structure has a high time complexity, which affects the model’s operational efficiency. To address these issues, we propose a novel data preprocessing and data fusion approach. It filters the hand contour using the motion vector of video coding and extracts features from RGB images and contour images through a dual-stream network. Additionally, a Gated-MLP GCN (GM-GCN) fusion module is proposed to fully fuse the dual-stream features. Meanwhile, we developed an Efficient Multi-scale Recurrent Attention (EMRA) module as our temporal modeling network, which adopts a recurrent structure similar to an RNN for attention calculation, enabling efficient parallel training of the model. Moreover, it better captures the details and dynamic changes of gestures through wavelet transform and multi-scale pooling strategies. Extensive experiments demonstrate that our proposed framework achieves highly competitive results on key benchmarks (e.g., 83.87% accuracy on NVGesture) while ensuring computational efficiency, reducing MACs by 28% compared to the standard Transformer.

Event extraction is a long-standing and challenging task in natural language processing, and existing studies mainly focus on extracting events within sentences. However, a significant problem that has not been carefully investigated is whether an “event topic” can be identified to represent the main aspects of extracted events. This article formulates the “topic event” extraction problem, aiming to identify a representative event from extracted ones. Specifically, after defining the topic event, we develop a multifocal graph-based framework to handle the extraction task. To enrich the associations of events and their tokens, we construct four event graphs, including the event subgraph and three event-associated graphs (i.e., event dependency parsing graph, event organization graph, and event share token graph), that reflect the internal and external structures of events, respectively. Subsequently, we design a multi-attention event-graph neural network to capture these event graph structures and improve event subgraph embedding. Finally, the output embeddings in the last layer of each channel are concatenated and fed into a fully connected network for topic event recognition. Extensive experiments validate the effectiveness of our method, and the results confirm its superiority over state-of-the-art baselines. In-depth analyses explore the essential factors (e.g., graph structures, attentions, feature generation method, etc.) determining the extraction performance.

On event-based social platforms such as Meetup and Douban, online groups serve as more than virtual communities for users to share experiences, they also provide an essential pathway for users to discover and participate in offline events. As the number of groups grows, it imposes the need of the study of online group recommendation. Despite there being many existing approaches to solve this problem, they all ignore the phenomenon that the groups that users participate in often contain a number of similar users. This phenomenon implies that similar users play a crucial role in identifying the groups that users are likely to join. In order to exploit similar users to improve the recommendation performance, we propose an effective multi-scale contrastive learning system for online Group Recommendation services, which is with a two-Tower model in event-based social networks (Tower4GR). Specifically, we first adopt the two-tower model to capture the interactive signals within the sequences and groups. We then incorporate the features of similar users into the sequence encoder, and aggregate the relevant users’ features into the group encoder, through which the preferred groups of similar users are more likely to be discovered by the target user. Finally, we propose an effective multi-scale contrastive learning framework for the two-tower architecture. It derives self-supervision signals from both same-scale data and cross-scale data, thereby extracting more meaningful data patterns. Moreover, the framework strengthens the cooperative associations between two towers. Extensive experiments on three real-world datasets from Meetup demonstrate the superiority of our proposed model over existing state-of-the-art models.

Large language models (LLMs) with prompting have achieved encouraging results on many natural language processing (NLP) tasks based on task-tailored promptings. Text-to-SQL is a critical task that generates SQL queries from natural language questions. However, prompting on LLMs haven’t show superior performance on Text-to-SQL task due to the absence of tailored promptings. In this work, we propose three promptings specifically designed for Text-to-SQL: SL-prompt, CC-prompt, and SL+CC prompt. SL-prompt is designed to guide LLMs to identify relevant tables; CC-prompt directs LLMs to generate SQL clause by clause; and SL+CC prompt is proposed to combine the strengths of these above promptings. The three prompting strategies makes three solutions for Text-to-SQL. Then, another prompting strategy, the RS-prompt is proposed to direct LLMs to select the best answer from the results of the solutions. We conducted extensive experiments, and experimental results show that our method achieved an execution accuracy of 86.2% and a test-suite accuracy of 76.9%, which is 1.1%, and 2.7% higher than the current state-of-the-art Text-to-SQL methods, respectively. The results confirmed that the proposed promptings enhanced the capabilities of LLMs on Text-to-SQL. Experimental results also show that the granularity of schema linking and the order of clause generation have great impact on the performance, which are considered little in previous research.

The nonlinear structure of a directed acyclic graph (DAG)-based blockchain facilitates parallel transaction processing, improving the overall scalability and throughput of the system. Compared with chain-based structures, DAG-based blockchains offer more flexibility in transaction processing. However, current research predominantly concentrates on improving throughput and reducing latency, with insufficient attention given to the real-time characteristics of transactions. Consequently, these systems struggle to effectively support business scenarios with deadlines, such as supply chain management and engineering manufacturing. In this article, we present a prototype of a DAG-based blockchain called RT-DAG, which supports the execution of real-time transactions. Specifically, RT-DAG assigns priorities to transactions based on deadlines and captures address utilization during transaction execution via an address resource graph (ARG). To enhance address utilization efficiency and provide additional opportunities to commit transactions before deadlines, we introduce a concurrency control scheme based on ARG called opportunity seizing (OS), which involves reordering transactions to replenish available addresses. Additionally, we propose a load-balancing grouping strategy to alleviate single-node workload pressures. The strategy assesses each group’s workload based on transaction quantity and type. Leveraging the bat algorithm, the algorithm strives to balance the workload distribution among groups, ultimately improving transaction execution efficiency. Numerous experiments have shown that RT-DAG performs well under different conflict rates and deadline ranges, effectively meeting the transaction timeliness requirements.

In event-based social networks (EBSN), group event recommendation has become an important task for groups to quickly find events that they are interested in. Existing methods on group event recommendation either consider just one type of information, explicit or implicit, or separately model the explicit and implicit information. However, these methods often generate a problem of data sparsity or of model vector redundancy. In this paper, we present a Graph Multi-head Attention Network (GMAN) model for group event recommendation that integrates the explicit and implicit information in EBSN. Specifically, we first construct a user-explicit graph based on the user's explicit information, such as gender, age, occupation and the interactions between users and events. Then we build a user-implicit graph based on the user's implicit information, such as friend relationships. The incorporated both explicit and implicit information can effectively describe the user's interests and alleviate the data sparsity problem. Considering that there may be a correlation between the user's explicit and implicit information in EBSN, we take the user's explicit vector representation as the input of the implicit information aggregation when modeling with graph neural networks. This unified user modeling can solve the aforementioned problem of user model vector redundancy and is also suitable for event modeling. Furthermore, we utilize a multi-head attention network to learn richer implicit information vectors of users and events from multiple perspectives. Finally, in order to get a higher level of group vector representation, we use a vanilla attention mechanism to fuse different user vectors in the group. Through experimenting on two real-world Meetup datasets, we demonstrate that GMAN model consistently outperforms state-of-the-art methods on group event recommendation.

Industrial cyber-physical systems are smart systems, which amalgamate the physical processes with computational capabilities to seamlessly capture, monitor and control the entities and scenarios in industrial environments. Among them, event-based industrial cyber-physical systems (EICPSs), such as Meetup and Plancast, have gained rapid developments. EICPSs provide event recommendation service for groups, which alleviates the information overload problem. However, existing group recommendation models in EICPSs focus on how to aggregate the preferences of group members, failing to model the complex and deep influence of contexts on groups. In this article, we propose an attention-based context-aware group event recommendation model (ACGER) in EICPSs. ACGER models the deep, nonlinear influence of contexts on users, groups, and events through multilayer neural networks. Especially, a novel attention mechanism is designed to enable the influence weights of contexts on users/groups change dynamically with the events concerned. Considering that groups may have completely different behavior patterns from group members, we acquire the preference of a group from two perspectives: indirect preference and direct preference. To obtain the indirect preference, we propose a method of aggregating preferences based on attention mechanism. Compared with existing predefined strategies, this method can flexibly adapt the strategy according to the events concerned by the group. To obtain the direct preference, we employ neural networks to learn it from group-event interactions. Furthermore, to make full use of rich user-event interactions in EICPSs, we integrate the context-aware individual recommendation task into ACGER, which enhances the accuracy of learning of user embeddings and event embeddings. Extensive experiments on three real datasets from Meetup and Douban event show that our model ACGER significantly outperforms the state-of-the-art models.

Recently, event-based social networks(EBSN) such as Meetup, Plancast, and Douban have become popular. As users in the networks usually take groups as an unit to participate in events, it is necessary and meaningful to study effective strategies for recommending events to groups. Existing research on group event recommendation either has the problems of data sparse and cold start due to without considering of social relationships in the networks or makes the assumption that the influence weights between any pair of nodes in the user social graph are equal. In this paper, inspired by the graph neural network and attention mechanism, we propose a novel recommendation model named leveraging social relationship-based graph attention model (SRGAM) for group event recommendation. Specifically, we not only construct a user-event interaction graph and an event-user interaction graph, but also build a user-user social graph and an event-event social graph, to alleviate the problems of data sparse and cold start. In addition, by using a graph attention neural network to learn graph data, we can calculate the influence weight of each node in the graph, thereby generating more reasonable user latent vectors and event latent vectors. Furthermore, we use an attention mechanism to fuse multiple user vectors in a group, so as to generate a high-level group latent vector for rating prediction. Extensive experiments on real-world Meetup datasets demonstrate the effectiveness of the proposed model.

With the rapid development of wireless communication technologies, location-based social networks (LBSNs) like foursquare and Gowalla have become very popular. Point of interest (POI) recommendation is a kind of important recommendation in LBSNs for enhancing user experiences. Unlike online social networks, LBSNs have a great deal of check-in data and comment information, which can provide valuable information for POI recommendation. In this paper, a novel recommendation strategy using tensor factorization is proposed for improving accurate rate of POI recommendation. Firstly, the latent dirichlet allocation(LDA) topic model is used to extract topic information and generate topic probability distribution of each POI based on comment information from users. Secondly, the check-in data of each user is divided into multiple data slices corresponding to each hour of a day. By connecting with the topic distributions of the visited POIs of each user, a user-topic-time tensor is conducted to present the potential preferences of all users. Finally, a higher order singular value decomposition (HOSVD) algorithm is employed to decompose the third-order tensor, to get dense preference information for POI recommendation. The experiments on a real dataset show that the proposed approach have better performance than the baseline methods.

Nowadays, Radio Frequency Identification (RFID) technology has been widely employed in the fields of object positioning, tracking and monitoring. However, there are a large number of redundant data generated in RFID systems due to duplicate detection and cross detection. Since RFID data is usually streaming, uncertain and mobile data, traditional static data and data stream filtering strategies cannot be applied to filter the RFID data effectively. In the paper, we first present a three-phase filtering framework under a block-based sliding window model. Aiming to filter the temporal redundant events, we propose an approximate Probability Synthesis Bloom Filter (PSBF) and discuss its filter principle, update rules and error rate in details. Comparing with the existing RFID filters, PSBF can not only filter the redundant probabilistic events, but also can calculate object existential probabilities with temporal decaying, and handle with the situations of location movement and staying at the overlapping areas among multiple readers correctly. The experiments on the simulated dataset show that the proposed filter outperforms the state-of-the-art filtering method.

With the rapid development of Radio Frequency Identification (RFID), sensor and wireless technologies, a large amount of trajectory data of moving objects are emerging, and trajectory data mining has received more and more attentions recently. However, since the data collected by sensors and RFID readers are usually noisy, it is necessary and meaningful to clean up the noise, including missing detection events and cross detection events, so as to provide high quality data for various applications using trajectory data. Cleaning up the trajectory events should take into account of uncertainty of location and unreliability of event detection at the same time. In the paper, we first discuss the rules to distinguish between normal detection events and false detection events in the trajectories, using constraints on continuous motion between adjacent detection regions and direct moving time between neighboring physical regions. Then, as a unified cleaning framework, we establish a probabilistic region connection graph to represent region detection features, region connection relationships, and region transition probabilities of neighboring physical regions. Focusing on interpolating missing events, we suggest two path-based probabilistic interpolating strategies, namely, the Most Likely Path (MLP) strategy and the Highest Weighting Probability Path (HWPP) strategy. Also, we discuss pruning rules of candidate paths for reducing computational cost. Finally, we conduct experiments over simulation data to demonstrate the effectiveness and efficiency of the proposed methods.

Offline ephemeral social networks (OffESNs) are the networks created ad-hoc at a specific location for a specific purpose and lasting for short period of time, relying on mobile social media such as Radio Frequency Identification (RFID) and Bluetooth devices. The primary purpose of people in the OffESNs is to acquire and share information via attending prescheduled events. Event Recommendation over this kind of networks can facilitate attendees on selecting the prescheduled events and organizers on making resource planning. However, because of lack of users' preference and rating information, as well as explicit social relations, the existing recommendation methods can no longer work well to recommend the events in the OffESNs. To address the challenges such as how to derive latent preferences and social relations and how to fuse the latent information in a unified model, we first construct two heterogeneous interaction social networks, an event participation network and a physical proximity network. Then, we use them to derive users' latent preferences and latent networks on social relations, including like-minded peers, co-attendees and friends. Finally, we propose an LNF (Latent Networks Fusion) model under a pairwise factor graph to infer event attendance probabilities for recommendation. Experiments on an RFID-based real conference dataset have demonstrated the effectiveness of the proposed model compared with typical solutions.

Recently, the RFID technology has been widely used in many kinds of applications. However, because of the interference from environmental factors and limitations of the radio frequency technology, the data streams collected by the RFID readers are usually contain a lot of cross-reads. To address this issue, we propose a KerneL dEnsity-bAsed Probability cleaning method (KLEAP) to remove cross-reads within a sliding window. The method estimates the density of each tag using a kernel-based function. The reader corresponding to the micro-cluster with the largest density will be regarded as the position that the tagged object should locate in current window, and the readings derived from other readers will be treated as the cross-reads. Experiments verify the effectiveness and efficiency of the proposed method.