Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.
#2 best model for Instance Segmentation on COCO
Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow.
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.
In particular, we evaluate our method on the large-scale multi-modal Youtube-8M v2 dataset and outperform all other methods in the Youtube 8M Large-Scale Video Understanding challenge.
In this paper, we devise multiple variants of bottleneck building blocks in a residual learning framework by simulating $3\times3\times3$ convolutions with $1\times3\times3$ convolutional filters on spatial domain (equivalent to 2D CNN) plus $3\times1\times1$ convolutions to construct temporal connections on adjacent feature maps in time.
Advantages of TLEs are: (a) they encode the entire video into a compact feature representation, learning the semantics and a discriminative feature space; (b) they are applicable to all kinds of networks like 2D and 3D CNNs for video classification; and (c) they model feature interactions in a more expressive way and without loss of information.
One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with such data.