# Dynamic Concept Composition for Zero-Example Event Detection

arXiv: https://arxiv.org/abs/1601.03679 · HTML: https://mlsanity.com/paper/1601.03679/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2016.

## Built on by (most cited first, 6 of 6)

- [Semantics-Guided Contrastive Network for Zero-Shot Object detection](https://mlsanity.com/paper/2109.06062/) (2021)
- [Object Priors for Classifying and Localizing Unseen Actions](https://mlsanity.com/paper/2104.04715/) (2021)
- [TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2208.14542/) (2022)
- [Zero-Shot Action Recognition from Diverse Object-Scene Compositions](https://mlsanity.com/paper/2110.13479/) (2021)
- [CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2303.09044/) (2023)
- [Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos](https://mlsanity.com/paper/2407.06018/) (2024)

## Abstract (arXiv)

In this paper, we focus on automatically detecting events in unconstrained videos without the use of any visual training exemplars. In principle, zero-shot learning makes it possible to train an event detection model based on the assumption that events (e.g. birthday party) can be described by multiple mid-level semantic concepts (e.g. "blowing candle", "birthday cake"). Towards this goal, we first pre-train a bundle of concept classifiers using data from other sources. Then we evaluate the semantic correlation of each concept wrt the event of interest and pick up the relevant concept classifiers, which are applied on all test videos to get multiple prediction score vectors. While most existing systems combine the predictions of the concept classifiers with fixed weights, we propose to learn the optimal weights of the concept classifiers for each testing video by exploring a set of online available videos with free-form text descriptions of their content. To validate the effectiveness of the proposed approach, we have conducted extensive experiments on the latest TRECVID MEDTest 2014, MEDTest 2013 and CCV dataset. The experimental results confirm the superiority of the proposed approach.