热点
"视频描述" 相关文章
From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach
cs.AI updates on arXiv.org 2025-07-08T04:33:50.000000Z
英伟达开源「描述一切」模型，拿下7个基准SOTA
机器之心 2025-04-27T15:36:14.000000Z
英伟达推 DAM-3B 模型：突破局部描述难题，让 AI 看懂图像 / 视频每一个角落
IT之家 2025-04-24T05:58:15.000000Z
NVIDIA AI Releases Describe Anything 3B: A Multimodal LLM for Fine-Grained Image and Video Captioning
MarkTechPost@AI 2025-04-23T17:00:35.000000Z