Location: TBD
Schedule: October 19, 2025, 08:30 am - 12:30 pm
8:30 am – 8:40 am Workshop Kick Off and Opening Comments
8:40 am – 9:10 am Invited Talk: Prof. Dima Damen (25mins for talk and 5mins for Q&A)
9:10 am – 9:50 am Oral Presentations (4 presentations, 10mins each, 7mins for talk and 3mins for Q&A)
9:10 am – 9:20 am: On the Generalization of Optical Flow: Quantifying Robustness to Dataset Shifts
9:20 am – 9:20 am: CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos
9:30 am – 9:40 am: Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark
9:40 am – 9:50 am: Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation (🥇in the competition)
9:50 pm – 10:25 pm Poster Session
10:25 am – 10:45 am ☕ Coffee Break
10:45 am – 11:25 am Oral Presentations (4 presentations, 10mins each, 7mins for talk and 3mins for Q&A)
10:45 am – 11:55 am: Enhancing Domain Diversity in Synthetic Data Face Recognition with Dataset Fusion (🥈 in the competition)
10:55 am – 11:05 am: YearGuessr: A Worldwide Building Age Benchmark with 55k Wikipedia Images and Ordinal Targets
10:05 am – 11:15 am: Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations
11:15 am – 11:25 am: MAPILLARY VISTAS VALIDATION FOR FINE-GRAINED TRAFFIC SIGNS: A Benchmark Revealing Vision-Language Model Limitations
11:25 am – 11:30 am Challenge Introduction and Winner Announcement
11:30 am – 12:00 pm Invited Talk: Prof. Serena Yeung-Levy (25 mins for talk and 5mins for Q&A)
For additional information please contact us.