Sergio Escalera

10

Papers

135

Total Citations

Papers (10)

Seamless Human Motion Composition with Blended Positional Encodings

CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing

A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise?

Agglomerative Token Clustering

MixerMDM: Learnable Composition of Human Motion Diffusion Models

Mixture-of-Attack-Experts with Class Regularization for Unified Physical-Digital Face Attack Detection

Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion

Sparse-Dense Side-Tuner for efficient Video Temporal Grounding

L-SWAG: Layer-Sample Wise Activation with Gradients Information for Zero-Shot NAS on Vision Transformers

From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models