5 papers
The impact of abstract and object tags on image privacy classification
Darya Baranouskaya, Andrea Cavallaro
Object tags denote concrete entities and are central to many computer vision tasks, whereas abstract tags capture higher-level information, which is relevant for tasks that require…
Which private attributes do VLMs agree on and predict well?
Olena Hrynenko, Darya Baranouskaya, Alina Elena Baia +1
Visual Language Models (VLMs) are often used for zero-shot detection of visual attributes in the image. We present a zero-shot evaluation of open-source VLMs for privacy-related at…
PrivLEX: Detecting legal concepts in images through Vision-Language Models
Darya Baranouskaya, Andrea Cavallaro
We present PrivLEX, a novel image privacy classifier that grounds its decisions in legally defined personal data concepts. PrivLEX is the first interpretable privacy classifier ali…
Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training
Naisong Zhou, Saisamarth Rajesh Phaye, Milos Cernak +4
Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Ne…
3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation
Evangelos Sariyanidi, Claudio Ferrari, Federico Nocentini +3
Computing the standard benchmark metric for 3D face reconstruction, namely geometric error, requires a number of steps, such as mesh cropping, rigid alignment, or point corresponde…