Wave-digital filter circuits for single-chip 4-D light field depth-based enhancement

Gullapalli, Sai K.; Edussooriya, Chamira U. S.; Wijenayake, Chamith; Dansereau, Donald G.; Bruton, L.T.; Madanayake, Arjuna

doi:10.1007/s11045-020-00751-y

Cited by 4 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, this technology has made multiple signi cant breakthroughs. In 2006, a new exploration direction named DL appeared in the machine learning, and started to be studied by the academic community and gradually applied by the industry [22,23] technology is to study the way that computers simulate and achieve animals' behavior of learning new knowledge or skills, rewrite the structure of data, and optimze the performance of the program. From the statistics perspective, machine learning is to forcast the distribution of data, obtain a model from the data and appliy this model to new data prediction [24].…”

Section: Convolutional Neural Network (Cnn) Researchmentioning

confidence: 99%

The Image Survival and Protection of Intangible Cultural Heritage in the New Media Environment

Wang

2023

Preprint

View full text Add to dashboard Cite

As a product of agricultural civilization, intangible cultural heritage (ICH) has been in a bad situation in recent years. Modern video media, with the dual identity of art and media, is an effective way to preserve and disseminate ICH. First, a hybrid network composed of a Bi-directional Long Short-Term Memory (Bi-LSTM) network with attention structure and Neural Network is adopted to extract relevant knowledge. Then, the generative adversarial network (GAN) is optimized. Lastly, this model is tested. The test results reveal that in the dataset constructed here, when the resolution of the processed image is 48×64×48, it takes 0.4825s for the unimproved GAN to process the image, while the algorithm improved only needs 0.0391s to process the image, with a speedup of 12.2.

show abstract

Section: Convolutional Neural Network (Cnn) Researchmentioning

confidence: 99%