theopsall/video-summarization

Multimodal summarization of user-generated videos from wearable cameras

Hello there! 👋,

Welcome to my digital realm,

I am Theodoros Psallidas, hailing from the historic land of Greece, currently living the dream. A passionate Ph.D. candidate at the University of Thessaly and Machine Learning Engineer, I specialize in audiovisual data analysis and machine learning, with a focus on multimodal video summarization.

• 🔭 Currently working as a Full Stack Software Engineer at Behavioral Signals.
• 🌱 Deep expertise in Machine Learning and Full Stack Development.
• 👨‍💻 Skilled in ReactJS, FastAPI, Django, Python, JavaScript/TypeScript, and machine learning frameworks like scikit-learn, PyTorch, Keras and TensorFlow.
• 🏆 Winner of "Code the IoT Hackathon of MaTHiSiS Project" at the University of West Attica.
• 📚 Published author and researcher in fields like multimodal video summarization and sound event detection.
• 🍺 When I'm not coding, I enjoy a cold craft beer, hopping from one code to another brew! Sometimes, they come together.
• 🐕 Pair programming with Barney, my dog who enjoys keeping me company while I code.

Technical Proficiency

As a Machine Learning Engineer and Full Stack Developer, I have honed my skills across a broad range of technologies and tools. Here are some of the key areas of my expertise:

• 💻  :

• 🧠  :

• 🌐  :

• 🛢  :

• ⚙️  :

---

Now Playing — Spotify 🎧

---

---

Thank you for visiting my profile!

video-summarization's Issues

Dataset Questions

Impressive work! I am wondering where I can access and download the original .mp4 video and .wav audio files? In the provided Google Drive link, there are only .npy files for the groundtrunth annotation files. Thanks in advance!