20170605计算机视觉报告小结

听了一个关于计算机视觉的报告，报告名字叫"computer vision ++: Where do we go from here?"，做点小结。我对计算机视觉了解的不多，连入门都算不上，但是近来对此产生了兴趣。报告主要讲的是一些应用。

提到了David Marr (neuroscientist)好像是一个大牛，写过一本书：Vision-豆瓣，Vision-Amazon

两个超过人的事情：1.人脸识别，LFW数据集；2.图像分类，ImageNet数据集。

两个数据集：

1.国际权威人脸识别公开测试集LFW(Labeled Faces in the Wild)，LFW由马萨诸塞大学于2007年建立，用于评测非约束条件下的人脸识别算法性能，是人脸识别领域使用最广泛的评测集合。

2.ImageNet

应用

图像分类

Liu J, Luo J, Shah M. Recognizing realistic actions from videos[C]// Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 2009:1996-2003.

Cao L, Luo J, Liang F, et al. Heterogeneous feature machines for visual recognition[C]// IEEE, International Conference on Computer Vision. IEEE, 2010:1095-1102.

行为识别

Li Q, Qiu Z, Yao T, et al. Action Recognition by Learning Deep Multi-Granular Spatio-Temporal Video Representation[C]// ACM on International Conference on Multimedia Retrieval. ACM, 2016:159-166.

vision+Language

Unsupervised Alignment of Actions in Video with Text Descriptions

You Q, Jin H, Wang Z, et al. Image Captioning with Semantic Attention[J]. 2016:4651-4659.

Li Y, Song Y, Cao L, et al. TGIF: A New Dataset and Benchmark on Animated GIF Description[C]// IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2016:4641-4650.

什么是Image Captioning？

感觉是从图像中获取信息，caption应该是字幕的意思，那么应该是从图像中识别一些信息并把它标注出来，看起来应该是这样（Image Captioning - Kiran Vodrahalli）：

视频和文本的无监督对准

Naim I, Song Y C, Liu Q, et al. Unsupervised alignment of natural language instructions with video segments[C]// Twenty-Eighth AAAI Conference on Artificial Intelligence. AAAI Press, 2014:1558-1564.

Image/Video Captioning with visual and semantic attention

You Q, Jin H, Wang Z, et al. Image Captioning with Semantic Attention[J]. 2016:4651-4659.

情感计算

情感计算—人工智能的重要发展方向

You Q, Luo J, Jin H, et al. Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark[J]. 2016.

You Q, Cao L, Jin H, et al. Robust Visual-Textual Sentiment Analysis: When Attention meets Tree-structured Recursive Neural Networks[C]// ACM, 2016:1008-1017.

研究自拍的

Chen T, Chen Y, Luo J. A Selfie is Worth a Thousand Words: Mining Personal Patterns behind User Selfie-posting Behaviours[J]. 2017.

用大数据来找到热销衣服的特征：

Chen K T, Luo J. When Fashion Meets Big Data: Discriminative Mining of Best Selling Clothing Features[J]. 2017.

医疗方面的应用

帮助新手医生练习手术