TGIF: A New Dataset and Benchmark on Animated GIF Description

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2016)

引用 246|浏览117
暂无评分
摘要
With the recent popularity of animated GIFs on social media, there is need for ways to index them with rich metadata. To advance research on animated GIF understanding, we collected a new dataset, Tumblr GIF (TGIF), with 100K animated GIFs from Tumblr and 120K natural language descriptions obtained via crowdsourcing. The motivation for this work is to develop a testbed for image sequence description systems, where the task is to generate natural language descriptions for animated GIFs or video clips. To ensure a high quality dataset, we developed a series of novel quality controls to validate free-form text input from crowdworkers. We show that there is unambiguous association between visual content and natural language descriptions in our dataset, making it an ideal benchmark for the visual content captioning task. We perform extensive statistical analyses to compare our dataset to existing image and video description datasets. Next, we provide baseline results on the animated GIF description task, using three representative techniques: nearest neighbor, statistical machine translation, and recurrent neural networks. Finally, we show that models fine-tuned from our animated GIF description dataset can be helpful for automatic movie description.
更多
查看译文
关键词
animated GIF description,Tumblr GIF,natural language descriptions,crowdsourcing,image sequence description systems,video clips,quality control,free-form text input,visual content captioning task,statistical analyses,nearest neighbor,statistical machine translation,recurrent neural networks,representative techniques
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要