4 papers
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos
Sharana Dharshikgan Suresh Dass, Hrishav Bakul Barua, Ganesh Krishnasamy +2
Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human…
GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction
Hrishav Bakul Barua, Kalin Stefanov, KokSheik Wong +2
High Dynamic Range (HDR) content (i.e., images and videos) has a broad range of applications. However, capturing HDR content from real-world scenes is expensive and time-consuming.…
HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translation
Hrishav Bakul Barua, Ganesh Krishnasamy, KokSheik Wong +2
High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. Due to the high costs associated with HDR imaging, the literature offer…
ArtHDR-Net: Perceptually Realistic and Accurate HDR Content Creation
Hrishav Bakul Barua, Ganesh Krishnasamy, KokSheik Wong +2
High Dynamic Range (HDR) content creation has become an important topic for modern media and entertainment sectors, gaming and Augmented/Virtual Reality industries. Many methods ha…