一次贴不完,再帮我翻译一下

来源:百度知道 编辑:UC知道 时间:2024/05/25 05:33:45
Using people to scan video streams to label the content is too slow and costly, according to Smith. "Categorizing the content of video through human labor can take 10 times as long as the duration of the content," Smith said. The software can be trained to recognize images by providing it with a group of similar images, he said.

IBM is working with broadcasters CNN and ABC to identify concepts that can be used to classify news footage, Smith said. IBM first demonstrated the technology in August 2004, and expects to have 1,000 concepts identified by April 2005.

Search engine companies have not publicly committed to using the image-scanning technologies. Google declined to comment on its research efforts, while Yahoo is trying to improve the quality of video searches by asking video producers to improve the labeling of their content. Yahoo created the Media RSS format, a syntax for labeling video content for its video search site, which debuted in Decemb

人们用扫描视频流标签的内容过于缓慢和昂贵,据史密斯. "就把影象的内容,通过人力可以采取的10倍,只要期限的内容, " 史密斯说. 该软件可训练识别图像,为它提供一组相似的形象,他说. IBM公司正在与广播有线新闻网和美国广播公司,找出概念,可以用来区分新闻片段, 史密斯说. IBM公司首次展示了科技在2004年8月,预计将有1000概念确定的2005年4月. 搜索引擎公司都没有公开承诺,利用影像扫描技术. 谷歌拒绝评论其研究工作, 而雅虎正试图改善视频质量胶片的视频要求生产者改善标签 其内容. 雅虎成立媒体转播格式,语法标记视频内容的视频搜索网站, 公开亮相,其中12 . 克伦豪,副总裁兼总经理singingfish说,她有所保留,用图像识别软件. "技术,图像识别和现场总结是创业领域,我们肯定会觉得很有趣, 虽然目前他们正处于初期发展阶段,不符合成本效益作商业用途, "布赖恩说.