{"html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fe4exp.hatenablog.com%2Fentry%2F2022%2F02%2F04%2F175836\" title=\"data2vec: \u753b\u50cf\uff0c\u97f3\u58f0\uff0c\u8a00\u8a9e\u3092\u540c\u3058\u624b\u6cd5\u3067\u4e8b\u524d\u5b66\u7fd2\u3067\u304d\u308b\u4e00\u822c\u7684\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af  - \u5b66\u3093\u3060\u3053\u3068\u30e1\u30e2\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_title":"\u5b66\u3093\u3060\u3053\u3068\u30e1\u30e2","provider_name":"Hatena Blog","height":"190","version":"1.0","blog_url":"https://e4exp.hatenablog.com/","author_name":"e4exp","description":"Data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language 2022/01 https://ai.facebook.com/research/data2vec-a-general-framework-for-self-supervised-learning-in-speech-vision-and-language \u97f3\u58f0\u3001\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3001\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30d3\u30b8\u30e7\u30f3\u306e\u3044\u305a\u308c\u306b\u5bfe\u3057\u3066\u3082\u540c\u3058\u5b66\u7fd2\u624b\u6cd5\u3092\u7528\u3044\u308b\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3001data2vec\u3092\u63d0\u6848 \u540c\u4e00\u30e2\u30c7\u30eb\u3092\u6559\u5e2b/\u751f\u5f92\u30e2\u30fc\u30c9\u3067\u4f7f\u7528\u3059\u308b\u81ea\u5df1\u84b8\u2026","categories":["DeepLearning","Pre-Training","Self-Supervised","Transformer","\u8ad6\u6587\u8aad\u307f"],"author_url":"https://blog.hatena.ne.jp/e4exp/","title":"data2vec: \u753b\u50cf\uff0c\u97f3\u58f0\uff0c\u8a00\u8a9e\u3092\u540c\u3058\u624b\u6cd5\u3067\u4e8b\u524d\u5b66\u7fd2\u3067\u304d\u308b\u4e00\u822c\u7684\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af ","url":"https://e4exp.hatenablog.com/entry/2022/02/04/175836","type":"rich","published":"2022-02-04 17:58:36","provider_url":"https://hatena.blog","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/e/e4exp/20220204/20220204175537.png","width":"100%"}