EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TASTA: Text‐Assisted Spatial and Temporal Attention Network for Video Question Answering

Tian Wang, Boyao Hou, Jiakun Li, Peng Shi, Baochang Zhang, Hichem Snoussi

Advanced Intelligent Systems · 2023-04 · 5 (4)

DOI: 10.1002/aisy.202200131 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 22.02.2023. Verfasst von Tian Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 130-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Beijing.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video question answering (VideoQA) is a typical task that integrates language and vision. The key for VideoQA is to extract relevant and effective visual information for answering a specific question. Information selection is believed to be necessary for this task due to the large amount of irrelevant information in the video, and explicitly learning an attention model can be a reasonable and effective solution for the selection. Herein, a novel VideoQA model called Text‐Assisted Spatial and Temporal Attention Network (TASTA) is proposed, which shows the great potential of explicitly modeling attention. TASTA is made to be simple, small, clean, and efficient for clear performance justification and possible easy extension. Its success is mainly from two new strategies of better using the textual information. Experimental results on a large and most representative dataset, TGIF‐QA, show the significant superiority of TASTA w.r.t. the state‐of‐the‐art and demonstrate the effectiveness of its key components via ablation studies.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Beijing

Zitieren

APA

Wang, T., Hou, B., Li, J., Shi, P., Zhang, B., & Snoussi, H. (2023). TASTA: Text‐Assisted Spatial and Temporal Attention Network for Video Question Answering. Advanced Intelligent Systems, 5(4). https://doi.org/10.1002/aisy.202200131

Vancouver

Wang T, Hou B, Li J, Shi P, Zhang B, Snoussi H. TASTA: Text‐Assisted Spatial and Temporal Attention Network for Video Question Answering. Advanced Intelligent Systems. 2023;5(4). doi:10.1002/aisy.202200131

BibTeX
@article{Wang2023,
  author = {Wang, Tian and Hou, Boyao and Li, Jiakun and Shi, Peng and Zhang, Baochang and Snoussi, Hichem},
  title = {TASTA: Text‐Assisted Spatial and Temporal Attention Network for Video Question Answering},
  journal = {Advanced Intelligent Systems},
  year = {2023},
  volume = {5},
  number = {4},
  doi = {10.1002/aisy.202200131}
}
Kostenlos starten →