We present a straightforward, flexible method to enhance the accuracy and quality of action detection by expressing temporal and structural relationships of actions in the loss function of a deep network. We describe ways to represent otherwise implicit structure in video data and demonstrate how these structures reflect natural biases that improve network training. Our experiments show that our approach improves both accuracy and edit-distance of action recognition and detection models over a baseline. Our framework leads to improvements over prior work and obtains state-of-the-art results on multiple benchmarks. The code is available here.

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.