Abstract: Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that use ...

Official implementation of the paper $\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation. **Abstract**: *Current video-language models ...

These alternatives to Google's default on Android are feature-rich and privacy-focused ...

Abstract: Deep generative models, and particularly facial animation schemes, can be used in video conferencing applications to efficiently compress a video through a sparse set of key-points, without ...