Linear classifier using random convolutional kernels applied to time series.

**Dimension-wise Fusion** is an image model block that attempts to capture global information by combining features globally. It is an alternative to point-wise [convolution](https://paperswithcode.com/method/convolution). A point-wise convolutional layer applies $D$ point-wise kernels $\mathbf{k}\_p \in \mathbb{R}^{3D \times 1 \times 1}$ and performs $3D^2HW$ operations to combine dimension-wise representations of $\mathbf{Y_{Dim}} \in \mathbb{R}^{3D \times H \times W}$ and produce an output $\mathbf{Y} \in \mathbb{R}^{D \times H \times W}$. This is computationally expensive. Dimension-wise fusion is an alternative that can allow us to combine representations of $\mathbf{Y\_{Dim}}$ efficiently. As illustrated in the Figure to the right, it factorizes the point-wise convolution in two steps: (1) local fusion and (2) global fusion.

DimFuse

DiCENet: Dimension-wise Convolutions for Efficient Networks

ROCKET

ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

**CMCL**, or **Crossmodal Contrastive Learning**, is a method for unifying visual and textual representations into the same semantic space based on a large-scale corpus of image collections, text corpus and image-text pairs. The CMCL aligns the visual representations and textual representations, and unifies them into the same semantic space based on image-text pairs. As shown in the Figure, to facilitate different levels of semantic alignment between vision and language, a series of text rewriting techniques are utilized to improve the diversity of cross-modal information. Specifically, for an image-text pair, various positive examples and hard negative examples can be obtained by rewriting the original caption at different levels. Moreover, to incorporate more background information from the single-modal data, text and image retrieval are also applied to augment each image-text pair with various related texts and images. The positive pairs, negative pairs, related images and texts are learned jointly by CMCL. In this way, the model can effectively unify different levels of visual and textual representations into the same semantic space, and incorporate more single-modal knowledge to enhance each other.

Source	ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com