Unverified50% confidenceFactExact time
DigUp can map text, images, audio, and video into the same vector space, enabling cross-media semantic retrieval.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/10/2026
First Seen
Valid until: 1/8/2027
Sources
Related Entities
Related Claims
UnverifiedDigUp splits audio and video into 30-second windows, takes one frame per shot, and then uniformly encodes them into the vector space.71% similarUnverifiedThe workflow provides latent-space upscaling functionality, supporting fine-grained processing of the complete spliced video.69% similarVerifiedThe CLIP model can map images and text to the same vector space, enabling cross-modal retrieval.68% similarUnverifiedCapCut is a video editing tool under ByteDance with a built-in speech recognition function and deep integration with the Douyin ecosystem.66% similarUnverified多模态大模型的核心技术突破在于跨模态对齐，通过CLIP等对比学习方法将图像、音频、视频映射到与文本共享的语义空间66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/994686API
curl https://kongchang.com/api/v1/knowledge/claims/994686MCP
get_claim(id=994686)