Unverified50% confidenceFactExact time
The dataset from Ukraine's Avengers Labs data platform contains approximately 5 million annotated images; the system trained on it processes over 100,000 drone video streams per month, identifies enemy equipment with approximately 70% accuracy, and takes 2.2 seconds to identify a single target.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedImageNet-1K 数据集包含约 128 万张训练图像，分布在 1000 个类别中69% similarUnverifiedAccording to a 2023 RUSI report, Ukrainian forces consume tens of thousands of drones per month, the vast majority of which are consumer-grade modified models.65% similarUnverifiedCOCO 数据集包含约12万张训练图像、80个类别、超过150万个目标实例，由微软研究院发布63% similarUnverifiedSA-1B 数据集包含约 1100 万张图像和超过 10 亿个自动生成的高质量掩膜61% similarUnverifiedThe goal of this project is to collect approximately 800,000 high-rank League of Legends match records.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945929API
curl https://kongchang.com/api/v1/knowledge/claims/945929MCP
get_claim(id=945929)