{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreigb6rvojohigga6tlvqorkrmli3xeqhsn6d5egpecmsldzrtyl3n4",
"uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mhydyltg7j32"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreid3zigxinxaz53njtu6xbrdviz4kkk7bw4l3tdxw4z42jwvdilf4a"
},
"mimeType": "image/jpeg",
"size": 90687
},
"path": "/news/2026-03-ai-tech-human-actions-videos.html",
"publishedAt": "2026-03-26T14:50:01.000Z",
"site": "https://techxplore.com",
"tags": [
"Software"
],
"textContent": "Typically, AI requires massive amounts of training data to understand complex human actions. However, in real-world scenarios, it is often difficult to secure sufficient video data for specific actions. A research team led by Jae-Pil Heo, Professor in the Department of Software at Sungkyunkwan University, has developed an AI technology that can accurately recognize new actions from only a small number of example videos. The research team focused on few-shot action recognition, which enables AI to learn and distinguish the characteristics of new actions from only a few examples.",
"title": "AI tech recognizes human actions from just a few example videos"
}