It uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions.

**MEI** introduces the *multi-partition embedding interaction* technique with block term tensor format to systematically address the efficiency--expressiveness trade-off in knowledge graph embedding. It divides the embedding vector into multiple partitions and learns the local interaction patterns from data instead of using fixed special patterns as in ComplEx or SimplE models. This enables MEI to achieve optimal efficiency--expressiveness trade-off, not just being fully expressive. Previous methods such as TuckER, RESCAL, DistMult, ComplEx, and SimplE are suboptimal restricted special cases of MEI.

Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion

Facial Expression Recognition using Residual Masking Network

**Involution** is an atomic operation for deep neural networks that inverts the design principles of convolution. Involution kernels are distinct in the spatial extent but shared across channels. If involution kernels are parameterized as fixed-sized matrices like convolution kernels and updated using the back-propagation algorithm, the learned involution kernels are impeded from transferring between input images with variable resolutions. 

The authors argue for two benefits of involution over convolution: (i) involution can summarize the context in a wider spatial arrangement, thus overcome the difficulty of modeling long-range interactions well; (ii) involution can adaptively allocate the weights over different positions, so as to prioritize the most informative visual elements in the spatial domain.

Source	Facial Expression Recognition using Residual Masking Network
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com