Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering

SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models

Label Efficient Learning Methods for Computer Vision Applications

CLIP-Actor-X: Text-driven 4D Human Avatar Generation via Cross-modal Synthesis-through-Optimization

ConfBALD: Deep Bayesian Active Learning against Confusing Classes

GL-Transformer: Globality-Enhanced Motion Transformer for Unsupervised Skeleton-Based Action Learning

Scratching Visual Transformer's Back with Uniform Attention

Sound Source Localization is All about Cross-Modal Alignment

TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation

for Depth-Aware Video Panoptic Segmentation