Web3 technologies enable novel forms of real-time digital human streaming media by supporting both high-fidelity transmission and interactive user engagement. However, Real-Time Streaming Interactive Digital Humans (RTSIDHs) remain vulnerable to network instability, resulting in buffering, latency, visual degradation, and audio–video desynchronization that substantially impair user Quality of Experience (QoE). To effectively perceive these distortions, we present RDHQA, the first large-scale RTSIDH Quality Assessment dataset. RDHQA comprises 134 representative interaction scenarios with eight digital human avatars as high-quality references, along with 1,340 distorted samples generated by simulating five common streaming degradations. Based on extensive subjective evaluations, we further propose SAV-PF, an audio–visual quality assessment method built on the human foundation model Sapiens and informed by cognitive principles such as the primacy effect and forgetting curve. Experimental results demonstrate that SAV-PF achieves superior performance over existing objective QoE assessment approaches, providing a more accurate prediction of user experience. This work is open-sourced at https://github.com/zyj-2000/RDHQA under the CC BY-NC 4.0 licence.
Lourdusamy Selvam, S. Abarna, R. Santhana Krishnan, Azarudeen K · 6 authors
Ensuring vaccine integrity requires rigorous cold-chain management, as even minor temperature deviations can compromise safety, cause financial losses, and endanger public health. Conventional monitoring systems, dependent on centralized databases and manual oversight, remain prone to delays, inaccuracies, and tampering. To address these limitations, we propose an integrated framework that combines deep learning and blockchain for secure, predictive, and real-time cold-chain monitoring. A distributed network of IoT sensors captures temperature, humidity, vibration, and GPS data at one-minute intervals. Long Short-Term Memory (LSTM) networks forecast short-term temperature trends, Autoencoders (AE) detect anomalies, and one-dimensional Convolutional Neural Networks (1D CNN) classify shipment states as Safe, At Risk, or Spoiled. A decision engine fuses outputs from these models into a unified risk score, enabling timely and data-driven interventions. Critical events and metadata are immutably recorded on the Ethereum blockchain, while raw sensor data is stored off-chain using IPFS to ensure auditability and efficiency. The system also supports automated alerts, real-time monitoring through Grafana dashboards, and adaptive model retraining for continuous improvement. Evaluation covers forecasting accuracy, anomaly detection precision, classification performance, and blockchain efficiency. By uniting predictive analytics with tamper-proof logging, the proposed framework reduces vaccine spoilage, strengthens supply chain resilience, and offers a scalable solution for broader temperature-sensitive logistics applications.
With the rise of "Metaverse" and "Web 3.0", Non-Fungible Token (NFT) has emerged as a kind of pivotal digital asset, garnering significant attention. By the end of March 2024, more than 1.7 billion NFTs have been minted across various blockchain platforms. To effectively locate a desired NFT, conducting searches within a vast array of NFTs is essential. The challenge in NFT retrieval is heightened due to the high degree of similarity among different NFTs, regarding regional and semantic aspects. In this paper, we will introduce a benchmark dataset named "NFT Top1000 Visual-Text Dataset" (NFT1000), containing 7.56 million image-text pairs, and being collected from 1000 most famous PFP1 NFT collections2 by sales volume on the Ethereum blockchain. Based on this dataset and leveraging the CLIP series of pre-trained models as our foundation, we propose the dynamic masking fine-tuning scheme. This innovative approach results in a 7.4\% improvement in the top1 accuracy rate, while utilizing merely 13\% of the total training data (0.79 million vs. 6.1 million). We also propose a robust metric Comprehensive Variance Index (CVI) to assess the similarity and retrieval difficulty of visual-text pairs data. The dataset will be released as an open-source resource. For more details, please refer to: https://github.com/ShuxunoO/NFT-Net.git.
Evaluating1 the popularity of content, developing personalized recommendation algorithms, and optimizing advertising revenue are crucial aspects of Over-the-Top (OTT) media content services. In order to achieve these goals, accurate viewership measurement of OTT content is essential. However, due to the stringent security policies of mobile platforms, it has been challenging to propose an easy and reliable method for measuring viewership. In this paper, we propose an efficient and secure viewership measurement technique for OTT content on the iOS platforms. The proposed technique utilizes audio filtering and zero-knowledge proof techniques to address the challenges. By leveraging audio filtering, the content can be quickly identified, enabling accurate viewership measurement. Additionally, the use of zero-knowledge proof ensures the protection of users' personal information, preventing indiscriminate acquisition of user data in OTT services.
The last decades have seen video production and consumption rise significantly: TV/cinematography, social networking, digital marketing, and video surveillance incrementally and cumulatively turned video content into the predilection type of data to be exchanged, stored, and processed. Belonging to video processing realm, video fingerprinting (also referred to as content-based copy detection or near duplicate detection ) regroups research efforts devoted to identifying duplicated and/or replicated versions of a given video sequence (query) in a reference video dataset. The present paper reports on a state-of-the-art study on the past and present of video fingerprinting, while attempting to identify trends for its development. First, the conceptual basis and evaluation frameworks are set. This way, the methodological approaches (situated at the cross-roads of image processing, machine learning, and neural networks) can be structured and discussed. Finally, fingerprinting is confronted to the challenges raised by the emerging video applications ( e.g. , unmanned vehicles or fake news) and to the constraints they set in terms of content traceability and computational complexity. The relationship with other technologies for content tracking ( e.g., DLT - Distributed Ledger Technologies) are also presented and discussed.
Open access
Advanced Steganography and Watermarking Techniques