# DASZL: Dynamic Action Signatures for Zero-shot Learning

arXiv: https://arxiv.org/abs/1912.03613 · HTML: https://mlsanity.com/paper/1912.03613/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2019.

## Built on by (most cited first, 2 of 2)

- [Gesture Recognition in Robotic Surgery: a Review](https://mlsanity.com/paper/2102.00027/) (2021)
- [Towards Surgical Context Inference and Translation to Gestures](https://mlsanity.com/paper/2302.14237/) (2023)

## Abstract (arXiv)

There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large. This makes end-to-end supervised training of a recognition system impractical as no training set is practically able to encompass the entire label set. In this paper, we present an approach to fine-grained recognition that models activities as compositions of dynamic action signatures. This compositional approach allows us to reframe fine-grained recognition as zero-shot activity recognition, where a detector is composed "on the fly" from simple first-principles state machines supported by deep-learned components. We evaluate our method on the Olympic Sports and UCF101 datasets, where our model establishes a new state of the art under multiple experimental paradigms. We also extend this method to form a unique framework for zero-shot joint segmentation and classification of activities in video and demonstrate the first results in zero-shot decoding of complex action sequences on a widely-used surgical dataset. Lastly, we show that we can use off-the-shelf object detectors to recognize activities in completely de-novo settings with no additional training.