Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. Given this minimal input, CenterTrack localizes objects and predicts their associations with the previous frame. That's it. CenterTrack is simple, online (no peeking into the future), and real-time.

**StreaMRAK** is a streaming version of kernel ridge regression. It divdes the problem into several levels of resolution, which allows continual refinement to the predictions.

StreaMRAK

StreaMRAK a Streaming Multi-Resolution Adaptive Kernel Algorithm

CenterTrack

Tracking Objects as Points

**Spectral-Normalized Identity Priors**, or **SNIP**, is a structured pruning approach that penalizes an entire [residual module](https://paperswithcode.com/method/residual-connection) in a [Transformer model](https://paperswithcode.com/method/residual-connection) toward an identity mapping. It is applicable to any structured module, including a single [attention head](https://paperswithcode.com/method/scaled), an [entire attention block](https://paperswithcode.com/method/multi-head-attention), or a [feed-forward subnetwork](https://paperswithcode.com/method/position-wise-feed-forward-layer). The method identifies and discards unimportant non-linear mappings in the [residual connections](https://paperswithcode.com/method/residual-connection) by applying a thresholding operator on the function norm. Furthermore, [spectral normalization](https://paperswithcode.com/method/spectral-normalization) to stabilize the distribution of the post-activation values of the [Transformer](https://paperswithcode.com/method/transformer) layers, further improving the pruning effectiveness of the proposed methodology.

Source	Tracking Objects as Points
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com