Žan Pušenjak
Studies / Research - deep-learning

    Convolutional Neural Networks

    Implementing ResNet-18 and U-Net architectures for fine-grained image classification and semantic segmentation.

    deep-learning computer-vision neural-networks

    Face Recognition Pipeline

    Evaluating deep-learning feature extractors and detectors in a recognition pipeline for a 100-person portrait dataset.

    biometrics deep-learning

    Long-Term Tracking

    Extending SiamFC into a long-term tracker and evaluating confidence thresholds with precision, recall, and F-score.

    computer-vision object-tracking deep-learning

    LSTM and Transformer Language Models

    Implementing LSTM and Transformer models for character-level text generation and comparing sequence lengths.

    deep-learning
© 2026 Žan Pušenjak
using Astrofy Template
Profile image
  • Home
  • Projects
  • Studies / Research
  • Personal
  • CV