imatge-upc/sign-topic

Topic Detection in Continuous Sign Language Videos. Presented as an extended abstract to the "AVA: Accessibility, Vision, and Autonomy Meet" CVPR 2022 Workshop.

Topic Detection in Continuous Sign Language Videos

Welcome to the code repository for the extended abstract titled Topic Detection in Continuous Sign Language Videos, which was presented in the AVA: Accessibility, Vision, and Autonomy Meet CVPR 2022 Workshop.

               

For instructions on how to run our training pipelines, go to ./examples/SL_topic_detection/ in this repo.

This repo is a fork of the original Fairseq repository that we extended for our work.

---

Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks.

Join the fairseq community

• Twitter: https://twitter.com/fairseq
• Facebook page: https://www.facebook.com/groups/fairseq.users
• Google group: https://groups.google.com/forum/#!forum/fairseq-users

License

fairseq(-py) is MIT-licensed.

Citation to our extended abstract

@inproceedings{topicDetectionAVAW2022,
  title = {Topic Detection in Continuous Sign Language Videos},
  author = {Alvaro Budria and Laia Tarrés and Gerard I. Gállego and Francesc Moreno-Noguer and Jordi Torres and Xavier Giró-i-Nieto},
  booktitle = {AVA: Accessibility, Vision, and Autonomy Meet workshop at CVPR},
  year = {2022},
}

Citation to Fairseq

@inproceedings{ott2019fairseq,
  title = {fairseq: A Fast, Extensible Toolkit for Sequence Modeling},
  author = {Myle Ott and Sergey Edunov and Alexei Baevski and Angela Fan and Sam Gross and Nathan Ng and David Grangier and Michael Auli},
  booktitle = {Proceedings of NAACL-HLT 2019: Demonstrations},
  year = {2019},
}