G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory
Paper
• 2307.14277 • Published
Hongxiang Li
lihxxx
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 14 days ago
A Very Big Video Reasoning Suite upvoted a paper 5 months ago
Diffusion Transformers with Representation Autoencoders upvoted a paper 5 months ago
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning
for LLMs Organizations
