CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016

This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016. We follow the basic pipeline of very deep two-stream CNN [16] and further raise the performance via a number of other techniques. Specifically, we use the latest deep model architecture, e.g. ResNet and Inception V3 and introduce a new aggregation scheme (top-k and attention-weighted pooling). Additionally, we incorporate the audio as a complementary channel, extracting relevant information via a CNN applied to the spectrograms. With these techniques, we derive an ensemble of deep models, which, together, attains a very high classification accuracy (mAP 93.23%) on the testing set and secured the first place in the challenge.