@@ -71,4 +71,8 @@ The ability to understand the ways to interact with objects from visual cues, a.
Spatial-temporal, channel-wise, and motion patterns are three complementary and crucial types of information for video action recognition. Conventional 2D CNNs are computationally cheap but cannot catch temporal relationships; 3D CNNs can achieve good performance but are computationally intensive. In this work, we tackle this dilemma by designing a generic and effective module that can be embedded into 2D CNNs. To this end, we propose a spAtiotemporal, Channel and moTion excitatION (ACTION) module consisting of three paths: Spatio-Temporal Excitation (STE) path, Channel Excitation (CE) path, and Motion Excitation (ME) path. The STE path employs one channel 3D convolution to characterize spatio-temporal representation. The CE path adaptively recalibrates channel-wise feature responses by explicitly modeling interdependencies between channels in terms of the temporal aspect. The ME path calculates feature-level temporal differences, which is then utilized to excite motion-sensitive channels. We equip 2D CNNs with the proposed ACTION module to form a simple yet effective ACTION-Net with very limited extra computational cost. ACTION-Net is demonstrated by consistently outperforming 2D CNN counterparts on three backbones (i.e., ResNet-50, MobileNet V2 and BNInception) employing three datasets (i.e., Something-Something V2, Jester, and EgoGesture). Codes are available at [https://github.com/V-Sense/ACTION-Net](https://github.com/V-Sense/ACTION-Net).
## A connectomic study of a petascale fragment of human cerebral cortex
We acquired a rapidly preserved human surgical sample from the temporal lobe of the cerebral cortex. We stained a 1 mm3 volume with heavy metals, embedded it in resin, cut more than 5000 slices at ~30 nm and imaged these sections using a high-speed multibeam scanning electron microscope. We used computational methods to render the three-dimensional structure of 50,000 cells, hundreds of millions of neurites and 130 million synaptic connections. The 1.4 petabyte electron microscopy volume, the segmented cells, cell parts, blood vessels, myelin, inhibitory and excitatory synapses, and 100 manually proofread cells are available to peruse online. Despite the incompleteness of the automated segmentation caused by split and merge errors, many interesting features were evident. Glia outnumbered neurons 2:1 and oligodendrocytes were the most common cell type in the volume. The E:I balance of neurons was 69:31%, as was the ratio of excitatory versus inhibitory synapses in the volume. The E:I ratio of synapses was significantly higher on pyramidal neurons than inhibitory interneurons. We found that deep layer excitatory cell types can be classified into subsets based on structural and connectivity differences, that chandelier interneurons not only innervate excitatory neuron initial segments as previously described, but also each other’s initial segments, and that among the thousands of weak connections established on each neuron, there exist rarer highly powerful axonal inputs that establish multi-synaptic contacts (up to ~20 synapses) with target neurons. Our analysis indicates that these strong inputs are specific, and allow small numbers of axons to have an outsized role in the activity of some of their postsynaptic partners.
