A **(2+1)D Convolution** is a type of [convolution](https://paperswithcode.com/method/convolution) used for action recognition convolutional neural networks, with a spatiotemporal volume. As opposed to applying a [3D Convolution](https://paperswithcode.com/method/3d-convolution) over the entire volume, which can be computationally expensive and lead to overfitting, a (2+1)D convolution splits computation into two convolutions: a spatial 2D convolution followed by a temporal 1D convolution.

MobileViT is a vision transformer that is tuned to mobile phone

MobileViT

MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

(2+1)D Convolution

A Closer Look at Spatiotemporal Convolutions for Action Recognition

**Cycle Consistency Loss** is a type of loss used for generative adversarial networks that performs unpaired image-to-image translation. It was introduced with the [CycleGAN](https://paperswithcode.com/method/cyclegan) architecture. For two domains $X$ and $Y$, we want to learn a mapping $G : X \rightarrow Y$ and $F: Y \rightarrow X$. We want to enforce the intuition that these mappings should be reverses of each other and that both mappings should be bijections. Cycle Consistency Loss encourages $F\left(G\left(x\right)\right) \approx x$ and $G\left(F\left(y\right)\right) \approx y$.  It reduces the space of possible mapping functions by enforcing forward and backwards consistency:

$$ \mathcal{L}\_{cyc}\left(G, F\right) = \mathbb{E}\_{x \sim p\_{data}\left(x\right)}\left[||F\left(G\left(x\right)\right) - x||\_{1}\right] + \mathbb{E}\_{y \sim p\_{data}\left(y\right)}\left[||G\left(F\left(y\right)\right) - y||\_{1}\right] $$

Source	A Closer Look at Spatiotemporal Convolutions for Action Recognition
Year	2000
Data Source	Papers with Code archive (CC BY-SA)