Yang Wu¹, Lei Guo¹, Xiaodong Dai¹, Bin Zhang¹, Dong-Won Park², Ming Ma^1,*

CMC-Computers, Materials & Continua, Vol.73, No.3, pp. 5911-5924, 2022, DOI:10.32604/cmc.2022.031664

Abstract Action recognition has become a current research hotspot in computer vision. Compared to other deep learning methods, Two-stream convolutional network structure achieves better performance in action recognition, which divides the network into spatial and temporal streams, using video frame images as well as dense optical streams in the network, respectively, to obtain the category labels. However, the two-stream network has some drawbacks, i.e., using dense optical flow as the input of the temporal stream, which is computationally expensive and extremely time-consuming for the current extraction algorithm and cannot meet the requirements of real-time tasks. In this paper, instead of the… More >

Samar Elbedwehy^1,*, T. Medhat², Taher Hamza³, Mohammed F. Alrahmawy³

CMC-Computers, Materials & Continua, Vol.73, No.1, pp. 1483-1500, 2022, DOI:10.32604/cmc.2022.029313

Abstract Image captioning is an emerging field in machine learning. It refers to the ability to automatically generate a syntactically and semantically meaningful sentence that describes the content of an image. Image captioning requires a complex machine learning process as it involves two sub models: a vision sub-model for extracting object features and a language sub-model that use the extracted features to generate meaningful captions. Attention-based vision transformers models have a great impact in vision field recently. In this paper, we studied the effect of using the vision transformers on the image captioning process by evaluating the use of four different… More >

Siyuan Mei^1,2, Yingyi Chen^1,2,*, Hanxiang Qin^1,2, Huihui Yu³, Daoliang Li^1,2, Boyang Sun^1,2, Ling Yang^1,2, Yeqi Liu^1,2

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.3, pp. 1315-1335, 2022, DOI:10.32604/cmes.2022.019378

Abstract Fish behavior analysis for recognizing stress is very important for fish welfare and production management in aquaculture. Recent advances have been made in fish behavior analysis based on deep learning. However, most existing methods with top performance rely on considerable memory and computational resources, which is impractical in the real-world scenario. In order to overcome the limitations of these methods, a new method based on knowledge distillation is proposed to identify the stress states of fish schools. The knowledge distillation architecture transfers additional inter-class information via a mixed relative loss function, and it forces a lightweight network (GhostNet) to mimic… More >

Tao Zeng^1,3, Lisheng Deng^1,3,*, Jiechao Chen^2,*, Hongyu Huang^1,3, Hanli Zhuang²

Journal of Renewable Materials, Vol.10, No.7, pp. 1845-1858, 2022, DOI:10.32604/jrm.2022.018803

Abstract A numerical study on the conjugated heat-mass transfer of helical hollow fiber membrane tube bank (HFMTB) for seawater desalination was carried out. Physical and mathematical models of fluid flow, temperature and humidity distribution were constructed to investigate the influences of flow type, Reynolds number, and temperature on the conjugated heat-mass transfer performance of hollow fibers in the distillation membrane module. The conjugated heat-mass transfer characteristics of HFMTB were discussed by utilizing the friction coefficient, Nusselt number (Nu), and Sherwood number (Sh). Results demonstrate that a distillation efficiency enhancement of 29% compared to the straight HFMTB has been detected for four-helical… More >