Sara Atito

6

Papers

46

Total Citations

Papers (6)

SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-Supervised Skeleton-Based Action Recognition

C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition

SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion

Text Augmented Correlation Transformer For Few-shot Classification & Segmentation

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning