Video question answering (VideoQA) has recently gained considerable attention in the field of computer vision, aiming to generate answers rely on both linguistic and visual reasoning. However, existing methods often align visual or textual features directly with large language models, which limits the deep semantic association between modalities and hinders a comprehensive understanding of the interactions within spatial and temporal contexts, ultimately leading to sub-optimal reasoning performance. To address this issue, we propose a novel temporal-aware framework for multi-modal video question answering, dubbed VideoQA-TA, which enhances reasoning ability and accuracy of VideoQA by aligning videos and questions at fine-grained levels. Specifically, an effective Spatial-Temporal Attention mechanism (STA) is designed for video aggregation, transforming video features into spatial and temporal representations while attending to information at different levels. Furthermore, a Temporal Object Injection strategy (TOI) is proposed to align object-level and frame-level information within videos, which further improves the accuracy by injecting explicit temporal information. Experimental results on MSVD-QA, MSRVTT-QA, and ActivityNet-QA datasets demonstrate the superior performance of our proposed method compared with the current SOTAs, meanwhile, visualization analysis further verifies the effectiveness of incorporating temporal information to videos.

The popularity of wearable medical data collection and surveillance devices provides real-time guarantees for the whole process of a patient's medical treatment, especially medical image data plays a key role. However, existing medical images face data leakage, pollution and vulnerability to attacks during transmission over wireless body area networks(WBANs). To address these issues, a privacy protection algorithm based on Hopfield cross neural network (HCNN) for medical data is proposed. Specifically, the HCNN model is first constructed and its dynamic behavior is analyzed, which is suitable for application to image encryption. Then, a confusion method of NZ fractal curve sorting matrix (NZ-FCSM) is designed to achieve good encryption effect. Subsequently, the secret image sharing (SIS) technique based on sharing matrix is introduced to enhance the algorithm robustness. Finally, an alignment embedding of double diamond prediction (AEDDP) method is proposed to implement lossless hiding of private information. The present issues in medical image protection include ensuring the security and effectiveness of encryption algorithms while maintaining the robustness and concealment of ciphertext data, and balancing the need for preservation with the limited resources of complex work environment. Experimental results show that the proposed algorithm achieves PSNR of 53 dB for the cipher image, more than 36 dB for the reconstructed image, and the information entropy of the secret image is over 7.99, and displays good robustness. These findings highlight the validity of the algorithm in medical image data privacy preserving applications that ensure confidentiality and extend to practical applications of concealed transmission of confidential information and secure multi-party transactions.

This study examines the diverse environmental practices of multinational firms, the degree of digitalization among parent firms, and green innovation. Using data from multinational listed firms from 2007 to 2018 as a sample, this article uses regression analysis to show that the more widely distributed the subsidiaries of multinational firms, the more heterogeneous the environmental knowledge acquired by the parent firm. The more diverse the environmental practices, the worse the green innovation performance of the parent firm. The degree of digitalization of the parent firm can effectively mitigate this negative effect. The more digital the parent company is, the more quickly it can process the large amount of complex information that helps the parent firm to achieve green innovation. These findings provide a new perspective on innovation in firms.

A class of nonlinear networked systems with external interference is designed in this paper. Currently, we have witnessed that networked control technology has played a key role in the Internet of Things (IoT). However, the amount of big data in the Internet of Things will cause network congestion in the data transmission of the network control system. In order to solve this problem, event‐driven control scheme can effectively save the network resources of the network control system. But when there is interference in the system, the conventional constant threshold parameter is difficult to achieve the expected energy‐saving effect. In order to solve this challenge, this paper proposes a design with a continuously variable threshold. After each trigger to transmit data, the threshold gets changed accordingly, and the sliding mode approach rate is changed simultaneously. Compared with the constant threshold event drive, the number of transmissions in this design can be greatly reduced, while sliding mode jitter is suppressed. The simulation results show that the scheme can achieve higher resource utilization efficiency and better robustness.