**Linear Warmup With Linear Decay** is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

**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.

AlignPS

Efficient Person Search: An Anchor-Free Approach

Linear Warmup With Linear Decay

**NeuralRecon** is a framework for real-time 3D scene reconstruction from a monocular video. Unlike previous methods that estimate single-view depth maps separately on each key-frame and fuse them later, NeuralRecon proposes to directly reconstruct local surfaces represented as sparse TSDF volumes for each video fragment sequentially by a neural network. A learning-based TSDF fusion module based on gated recurrent units is used to guide the network to fuse features from previous fragments. This design allows the network to capture local smoothness prior and global shape prior of 3D surfaces.

Year	2000
Data Source	Papers with Code archive (CC BY-SA)