On the Generalization of Optical Flow: Quantifying Robustness to Dataset Shifts (link)
CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos (link)
Enhancing Domain Diversity in Synthetic Data Face Recognition with Dataset Fusion (🥈 in the competition, link)
YearGuessr: A Worldwide Building Age Benchmark with 55k Wikipedia Images and Ordinal Targets (presented at workshop, not published, link)
Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations (link)
Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark (link)
Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation (🥇in the competition, link)
MAPILLARY VISTAS VALIDATION FOR FINE-GRAINED TRAFFIC SIGNS: A Benchmark Revealing Vision-Language Model Limitations (link)
LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning (link)
Synthetic Hands Meet Legacy Data: A Synthetic Dataset for Structured, Controllable, and Multimodal Evaluation (link)
SynRES: Towards Referring Expression Segmentation in the Wild via Synthetic Data (link)Â
QuarrySet: An RGB Dataset and Benchmark for Data-centric Quarry Analysis (link)
The PDFs of these papers will be available after the camera-ready submission
For additional information please contact us.