Unverified50% confidenceFactExact time
MFVSR is a large-scale, multi-style benchmark for video subtitle removal oriented toward fine-grained and reliability evaluation.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe MFVSR benchmark contains 3,000 paired videos, covering three sources: Real-HQ (real high quality), Real-LQ (real low quality), and AI-Generated.70% similarUnverifiedMFVSR also includes 953 in-the-wild real videos as an auxiliary set, used to analyze real-world coverage.67% similarUnverified视频超分辨率（VSR）通过光流估计对齐相邻帧并融合多帧信息重建目标帧，在恢复细节的同时保证时序稳定性65% similarUnverifiedvideo-subtitle-remover (VSR) is an open-source project that uses AI restoration algorithms to locally remove hard-coded subtitles and text watermarks at lossless resolution and intelligently fill in the covered areas.62% similarUnverifiedVCR-Bench is a modular open-source benchmark framework for evaluating the robustness of video classification.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1024040API
curl https://kongchang.com/api/v1/knowledge/claims/1024040MCP
get_claim(id=1024040)