Researchers from the USC Viterbi School of Engineering are presenting 24 papers at the 2025 International Conference on Learning Representations (ICLR), Apr. 24-28, one of the premier global ...

This valuable study introduces a self-supervised machine learning method to classify C. elegans postures and behaviors directly from video data, offering an alternative to the skeleton-based ...

Advt A new class ... complex algorithms and datasets, and tiny AI, which focuses on running lightweight models that can perform basic inference tasks. For example, audio and visual information ...

Subtle differences in how people grasp everyday objects may help identify autism, according to a new study published in ...

a groundbreaking benchmark tailored to assess the performance of visual object tracking algorithms on tiny objects under low-light conditions. The Lunar Tracking benchmark comprises 700 diverse videos ...

The evaluation of tracking objects, dynamic positions and their visual information in results are quite difficult tasks. Until now, most real-time visual tracking algorithms suffer from poor ...

How one computer vision company is turning passive surveillance into proactive protection—across schools, cities, federal ...

The background soundtrack is a soothing accompaniment of ambient noise – floorboards that creak with character underfoot, the gentle murmur of conversations between vendors and shoppers, occasional ...

Runway – This object must take off and land on it. Were you able to guess the word based on the visual hints within 9 seconds? Even if you were not successful, do not lose your morale.

From theatrical release to streaming, some think that eye-tracking AI could lengthen the life-span of movies and series.