MSc AI | Building systems in vision, language, and multimodal understanding
-
22:48
(UTC +01:00) - in/hank-song-391856298
Stars
4
stars
written in Jupyter Notebook
Clear filter
Multimodal AI pipeline to predict Big Five personality traits and assess charismatic leadership using audio, text, and video inputs.
Deep learning-based image restoration pipeline with DnCNN, NAFNet, and legacy joint models. Includes PSNR/SSIM/LPIPS evaluation and visual comparisons.
Benchmarking CNNs and Vision Transformers on CIFAR-10/100 using a unified PyTorch pipeline with transfer learning and model fusion.
Image stitching with Harris corner detection, SIFT descriptors, Lowe’s ratio test, and affine RANSAC warp.