Abstract: With the rapid advancement of urbanization and intelligent transportation systems (ITSs), traffic surveillance has become essential for road safety, traffic management, and data-driven ...

⚡ The first token compression framework for VideoLLMs featuring dynamic frame budget allocation. LLaVA-OneVision token_compressor/vidcom2/models/llava.py LLaVA ...

A modern, professional video compression application built with Python and CustomTkinter. Designed specifically for the ITG Software QA Team to efficiently compress videos while maintaining quality.

Abstract: This paper addresses the limitations of generative face video compression (GFVC) under conditions of substantial head movement and complex facial deformations. Previous GFVC frameworks ...