UEC at TRECVID 2016 AVS task
暂无分享,去创建一个
We started participating TRECVID in 2005, and we have been continuously submitting the results to TRECVID for ten years. For those years we usually participate in semantic indexing task (SIN) and MED tasks. Because in TRECVID2016[1] the SIN task was replaced with the AVS task, this year we participated in the Ad-hoc Video Search (AVS) task. AVS is a new and very challenging task as among the TRECVID tasks, since in the AVS task no training data is provided and instead participants require to collect training data on their own. Event queries of the AVS tasks were very complicated and the number of queries is small compared to SIN task. For the AVS this year, we collected our training dataset using the Bing image search engine, and used an off-the-shelf feature extractor, VGG-16 fc7, and linear SVM as a classifier. As a result we achieved the 0.005 mean average precision.
[1] Andrew Zisserman,et al. Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.
[2] Trevor Darrell,et al. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.
[3] Jonathan G. Fiscus,et al. TRECVID 2016: Evaluating Video Search, Video Event Detection, Localization, and Hyperlinking , 2016, TRECVID.