Dynamic Concept Composition for Zero-Example Event Detection

@inproceedings{Chang2016DynamicCC,
  title={Dynamic Concept Composition for Zero-Example Event Detection},
  author={Xiaojun Chang and Yi Yang and Guodong Long and Chengqi Zhang and Alexander G. Hauptmann},
  booktitle={AAAI},
  year={2016}
}
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… CONTINUE READING
Highly Cited
This paper has 38 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 2 times. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 29 extracted citations

Unified Embedding and Metric Learning for Zero-Exemplar Event Detection

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 5 Excerpts
Highly Influenced

From Text to Video: Exploiting Mid-Level Semantics for Large-Scale Video Classification

2018 24th International Conference on Pattern Recognition (ICPR) • 2018
View 1 Excerpt

Structured Summarization of Social Web for Smart Emergency Services by Uncertain Concept Graph

2018 IEEE International Science of Smart City Operations and Platforms Engineering in Partnership with Global City Teams Challenge (SCOPE-GCTC) • 2018
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 40 references

Self-Paced Learning with Diversity

NIPS • 2014
View 9 Excerpts
Highly Influenced

Learning Sample Specific Weights for Late Fusion

IEEE Transactions on Image Processing • 2015
View 3 Excerpts
Highly Influenced

Video Event Detection by Inferring Temporal Instance Labels

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 4 Excerpts
Highly Influenced

Action Recognition with Improved Trajectories

2013 IEEE International Conference on Computer Vision • 2013
View 5 Excerpts
Highly Influenced

Dynamic Pooling for Complex Event Recognition

2013 IEEE International Conference on Computer Vision • 2013
View 4 Excerpts
Highly Influenced