Program Schedule
13:25 - 13:30 Opening remarks
13:30 - 13:50 Keynote: Antonino Furnari
Title: Action-Centric Graphs for Procedural Video Understanding
13:50 - 13:55 Q&A
14:00 - 14:20 Keynote: Stefan Roth
14:20 - 14:25 Q&A
14:30 - 14:55 Spotlights
14:55 - 15:25 Coffee break + Poster session
15:25 - 16:05 Oral session
16:05 - 16:25 Keynote: Tolga Birdal
16:25 - 16:30 Q&A
16:30 - 16:50 Keynote: Yuta Nakashima
Title: Graphs as Knowledge Representation
16:50 - 16:55 Q&A
17:00 - 17:20 Keynote: Benjamin Busam
Title: Scene Graphs in the Era of Multi-modal Generative AI
17:20 - 17:25 Q&A
17:25 - 17:30 Closing
Presentations Schedule
Spotlights
14:30 - 14:38 Intersection Safety Modeling Through Semantic Scene Graph (Poster #245)
Akash Sonth, Lynn Abbott, Abhijit Sarkar
14:38 - 14:46 FOREcasting human activities via latent SCENE graphs diffusion (Poster #246)
Antonio Alliegro, Francesca Pistilli, Tatiana Tommasi, Giuseppe Averta
14:46 - 14:54 HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos (Poster #247)
Simone Alberto Peirone, Francesca Pistilli, Giuseppe Averta
Oral Session
15:25 - 15:38 CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations (Poster #242)
Julian Lorenz, Mrunmai Phatak, Robin Schön, Katja Ludwig, Nico Hörmann, Annemarie Friedrich, Rainer Lienhart
15:39 - 15:52 Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generation (Poster #243)
Maëlic Neau, Zoe Falomir, Cédric Buche, Akihiro Sugimoto
15:52 - 16:05 Long-form Reasoning for Keystep Recognition using Graph Neural Networks (Poster #244)
Julia Romero, Kyle Min, Subarna Tripathi, and Morteza Karimzadeh