Workshops Organized

Multimodal Machine Learning for Human Behaviour Understanding

AMLD 2024, EPFL, Lausanne, Switzerland • April 2024 • Materials & Repo

This workshop introduced participants to the foundations and applications of multimodal machine learning for human-centric AI applications. The goal was to provide a brief overview of how to process different modalities such as video, audio, and text, and to highlight how communication extends beyond words through facial expressions, tone, and non-verbal cues. We included hands-on code for extracting features from these modalities and demonstrated how multimodal fusion could support data-driven evaluation of interview communication skills by combining facial, acoustic, and textual signals.

---

Virtual Interviewer: Build your own interviewing agent

AMLD 2021, EPFL, Lausanne, Switzerland • April 2021 • Materials & Repo

This workshop aimed to build a virtual interviewing agent capable of asking dynamic follow-up questions. It was conducted in two parts: first, we showed how to build a follow-up question generation model using a pre-trained GPT-2 language model; second, we demonstrated how to deploy the model as a virtual interviewing agent using AWS Sumerian. The session combined model development with practical system deployment and gave participants a hands-on understanding of how conversational agents can support interview scenarios.

---

Procedure Detection Hands-on Session

R V College of Engineering, Bengaluru, India • 2020 • Materials & Repo

This hands-on session introduced participants to procedure detection and helped them understand how machine learning and computer vision techniques can be used to recognize and model activity sequences and procedural steps. It provided a practical overview of the underlying methods and demonstrated how these approaches can be applied to real-world activity understanding tasks.