Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability

arXiv:2508.07388 · cs.AI · Submitted 2025-08-10 · Read on arXiv

cs.AI

Submitted: 2025-08-10

Updated: 2026-10-29

Code: https://github.com/Deep-Agent/R1-V

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers