Chaotic moving video quality enhancement based on deep in-loop filtering by Tong Tang, Yi Yang, Dapeng Wu, Ruyan Wang, Zhidu Li

“…The in-loop filter in VVC inherits the De-Blocking Filter (DBF) and Sample Adaptive Offset (SAO) of High Efficiency Video Coding (HEVC, H.265), and adds the Adaptive Loop Filter (ALF) to minimize the error between the original sample and the decoded sample. …”
Get full text

SVPDSA: Selective View Perception Data Synthesis With Annotations Using Lightweight Diffusion Network by S. Raghavendra, Vijayalakshmi, Vainidhi, S. K. Abhilash, Venu Madhav Nookala, P. V. Arun Kumar, Ramyashree

“…The proposed model efficiently generates diverse synthetic images with high-quality perception annotations. …”
Get full text

Copy-Move Forgery Verification in Images Using Local Feature Extractors and Optimized Classifiers by S. B. G. Tilak Babu, Ch Srinivasa Rao

“…The proposed algorithms are more efficient than state-of-the-art algorithms even though the suspected image is post-processed.…”
Get full text

A Robust H.264/AVC Video Watermarking Scheme with Drift Compensation by Xinghao Jiang, Tanfeng Sun, Yue Zhou, Wan Wang, Yun-Qing Shi

“…Malicious attacks with different quantization parameters (QPs) or motion estimation algorithms can be resisted efficiently, with 80% accuracy on average after lossy compression.…”
Get full text

Cloud–Edge Collaborative Learning and Model Compression Framework for Communication-Assisted Human Action Recognition by Bo Gao, Quan Zhou

“…The growing demand for efficient human action recognition has led to significant advancements in applications such as surveillance, healthcare, and human–computer interaction. …”
Get full text

DPU empowered intelligent congestion control mechanism for the intelligent computing center network by CHEN Jinqian, GUO Shaoyong, LIU Chang, QI Feng, QIU Xuesong

“…By integrating pruning and quantization, the model was lightweighted. Moreover, the model was transformed into the efficient gradient-boosted decision tree through knowledge distillation method, allowing for precise matching of control actions with real-time network conditions. …”
Get full text

FloodNet-Lite: A Lightweight Deep Learning for Flood Mapping Using Remote Sensing Data With Optimized UNet and Edge Deployment Approach in 6G by Puviyarasi Thirugnanasammandamoorthi, Debabrata Ghosh, Ram Kishan Dewangan, Mohammad Kamrul Hasan, Khairul Akram Zainol Ariffin, Huda Saleh Abbas, Hashim Elshafie, Rashid A. Saeed, Ala Eldin Awouda

“…The system integrates an optimized UNet architecture with MobileNetV3 as a backbone, enhanced by depthwise separable convolutions, attention mechanisms, and advanced model compression techniques, such as quantization-aware training and structured pruning. Knowledge distillation transfers learning from a high-capacity teacher model to a compact student model, while self-supervised learning further reduces dependency on labeled data to boost efficiency and robustness. …”
Get full text

Reinforcement learning energy management control strategy of electric tractor based on condition identification by Liqiao Li, Jiangchun Chen, Jing Nie, Zongyu Gao

“…However, low traction efficiency, short battery life, and high energy consumption are the main reasons hindering the industrialization of ET. …”
Get full text

A fast monocular 6D pose estimation method for textureless objects based on perceptual hashing and template matching by Jose Moises Araya-Martinez, Jose Moises Araya-Martinez, Vinicius Soares Matthiesen, Vinicius Soares Matthiesen, Simon Bøgh, Jens Lambrecht, Rui Pimentel de Figueiredo

“…Additionally, our algorithm efficiently utilizes all CPU cores and includes adjustable parameters for balancing computation time and accuracy, making it suitable for a wide range of applications where hardware cost and power efficiency are critical. …”
Get full text

High-speed railway track components inspection framework based on YOLOv8 with high-performance model deployment by Youzhi Tang, Yu Qian

“…Our research introduces an efficient model inference pipeline based on a producer-consumer model, effectively utilizing parallel processing and concurrent computing to enhance performance. …”
Get full text

Digital identification and adulteration analysis of Codonopsis Radix and Stellariae Radix based on the “digital identity” of chemical compositions by Xianrui Wang, Jiating Zhang, Wenguang Jing, Xiaohan Guo, Minghua Li, Xianlong Cheng, Feng Wei

“…Finally, the above “digital identities” of CR and SR were used as benchmarks for matching positive samples and market samples to provide feedback on the matching credibility (MC) for identification and adulteration analysis.ResultsThe results showed that based on the “digital identities” of CR and SR, the digital identification of CR, SR, and positive samples can be realized at the individual level of TCM efficiently and accurately, even if 3% of SR in the mixed samples can still be identified efficiently and accurately. …”
Get full text

TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing by Amna Khatoon, Weixing Wang, Mengfei Wang, Limin Li, Asad Ullah

“…Our framework addresses critical gaps in existing methodologies, such as high computational demands and limited real-time processing capabilities, by leveraging model compression, quantization, and pruning techniques. These enhancements facilitate efficient real-time analysis directly on edge devices. …”
Get full text

High-Bit-Depth Geometry Representation and Compression in MPEG Immersive Video System by Yoonseob Lee, Kwan-Jung Oh, Gwangsoon Lee, Byung Tae Oh

“…Immersive video has been rapidly evolving as a new form of media for virtual reality (VR) applications, increasing demand for efficient compression and transmission techniques. …”
Get full text

A Comparative Analysis of Compression and Transfer Learning Techniques in DeepFake Detection Models by Andreas Karathanasis, John Violos, Ioannis Kompatsiaris

“…Pruning, knowledge distillation, quantization, and adapter modules are explored to enable efficient real-time DeepFake detection. …”
Get full text

Pruning and optimization of optical neural network as a binary optical trigger by Bokun Zhao, Xuening Dong, Kaveh Rahbardar Mojaver, Brett H. Meyer, Odile Liboiron-Ladouceur

“…Optical neural networks implemented with Mach-Zehnder Interferometer (MZI) arrays are a promising solution to enable fast and energy-efficient machine learning inference, yet finding a practical application has proven challenging due to sensitivity to thermal noise and loss. …”
Get full text

Accelerating Streaming Subgraph Matching via Vector Databases by Liuyi Chen, Yi Ding, Xushuo Tang, Fangyue Chen, Siyuan Gong, Xu Zhou, Zhengyi Yang

“…The streaming subgraph matching problem, an extension of this task, aims to efficiently process queries in a stream with minimal latency. …”
Get full text

Real-Time Acoustic Scene Recognition for Elderly Daily Routines Using Edge-Based Deep Learning by Hongyu Yang, Rou Dong, Rong Guo, Yonglin Che, Xiaolong Xie, Jianke Yang, Jiajin Zhang

“…This architecture provides an efficient, reliable, and user-friendly solution for real-time acoustic scene monitoring in elderly care.…”
Get full text

High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity by Shiyu Qiu, Chunlei Wu, Zhenghao Wan, Siyuan Tong

“…To address this, 3D Gaussian Splatting (3DGS) has emerged as an efficient alternative, utilizing Gaussian-based representations and rasterization techniques to achieve faster rendering speeds without sacrificing image quality. …”
Get full text

Engineering a multi model fallback system for edge devices by Gaurav Kadve, Abishi Chowdhury, Vishal Krishna Singh, Amrit Pal

“…The growing deployment of machine learning applications in edge environments, such as IoT devices and embedded systems, has highlighted the need for efficient, resource-aware systems for edge environments. …”
Get full text

FPG-AI RNN: A Technology-Agnostic Framework for the Automatic Acceleration of LSTM/GRU-Based Models on FPGAs by Tommaso Pacini, Pietro Nannipieri, Silvia Moranti, Luca Fanucci

“…FPGAs have emerged as an efficient technology for accelerating these algorithms, especially in resource- and power-constrained platforms such as edge devices. …”
Get full text