CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
This work addresses video classification for researchers and practitioners, but it is incremental as it builds on existing temporal segment networks.
The paper tackled the untrimmed video classification task in the ActivityNet Challenge 2016 by using an ensemble of deep models with techniques like ResNet, Inception V3, top-k and attention-weighted pooling, and audio CNN, achieving a classification accuracy of 93.23% mAP and securing first place.
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 temporal segment networks 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 new aggregation schemes (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 high classification accuracy (mAP $93.23\%$) on the testing set and secured the first place in the challenge.