**Instruction Pointer Attention Graph Neural Network**, or **IPA-GNN**, is a learning-interpreter neural network (LNN) based on GNNs for learning to execute programmes. It achieves improved systematic generalization on the task of learning to execute programs using control flow graphs. The model arises by considering RNNs operating on program traces with branch decisions as latent variables. The IPA-GNN can be seen either as a continuous relaxation of the RNN model or as a GNN variant more tailored to execution.

A method to disentangle pose from other factors in a scene.

Pose Disentangling

Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

IPA-GNN

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

**AlignPS**, or **Feature-Aligned Person Search Network**, is an anchor-free framework for efficient person search. The model employs the typical architecture of an anchor-free detection model (i.e., [FCOS](https://paperswithcode.com/method/fcos)). An aligned feature aggregation (AFA) module is designed to make the model focus more on the re-id subtask. Specifically, AFA reshapes some building blocks of [FPN](https://paperswithcode.com/method/fpn) to overcome the issues of region and scale misalignment in re-id feature learning. A [deformable convolution](https://paperswithcode.com/method/deformable-convolution) is exploited to make the re-id embeddings adaptively aligned with the foreground regions. A feature fusion scheme is designed to better aggregate features from different FPN levels, which makes the re-id features more robust to scale variations. The training procedures of re-id and detection are also optimized to place more emphasis on generating robust re-id embeddings.

Source	Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com