# Unified Embedding and Metric Learning for Zero-Exemplar Event Detection

arXiv: https://arxiv.org/abs/1705.02148 · HTML: https://mlsanity.com/paper/1705.02148/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2017.

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

- [Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition](https://mlsanity.com/paper/2101.06636/) (2021)
- [NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition](https://mlsanity.com/paper/2104.01110/) (2021)

## Abstract (arXiv)

Event detection in unconstrained videos is conceived as a content-based video retrieval with two modalities: textual and visual. Given a text describing a novel event, the goal is to rank related videos accordingly. This task is zero-exemplar, no video examples are given to the novel event. Related works train a bank of concept detectors on external data sources. These detectors predict confidence scores for test videos, which are ranked and retrieved accordingly. In contrast, we learn a joint space in which the visual and textual representations are embedded. The space casts a novel event as a probability of pre-defined events. Also, it learns to measure the distance between an event and its related videos. Our model is trained end-to-end on publicly available EventNet. When applied to TRECVID Multimedia Event Detection dataset, it outperforms the state-of-the-art by a considerable margin.