With the emergence of huge amounts of heterogeneous multi-modal data, including images, videos, texts/languages, audios, and multi-sensor data, deep learning-based methods have shown promising ...

In the latest in our series of interviews meeting the AAAI/SIGAI Doctoral Consortium participants, we caught up with Aniket ...

A study on visual language models explores how shared semantic frameworks improve image–text understanding across multimodal tasks. By combining feature extraction, joint embedding, and advanced ...

Contextual cueing describes the phenomenon whereby repeated exposure to specific spatial layouts enables a more efficient visual search. In such settings, the surrounding distractor configuration, ...

Children efficiently develop their visual systems through learning from their environment. How this development unfolds in noisy real-world data streams remains largely unknown. Deep neural networks ...