EUVIMEDEUVIMED entdecken
Crossref

Contrastive Video Question Answering via Video Graph Transformer

Junbin Xiao, Pan Zhou, Angela Yao, Yicong Li, Richang Hong, Shuicheng Yan, Tat-Seng Chua

IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.11.2023 · 45 (11) · 13265-13280

DOI: 10.1109/tpami.2023.3292266 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.11.2023. Verfasst von Junbin Xiao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 61-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: Sea-NExT Joint Lab, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional cross-modal interaction modules. 3) It is optimized by the joint fully- and self-supervised contrastive objectives between the correct and incorrect answers, as well as the relevant and irrelevant questions respectively. With superior video encoding and QA solution, we show that CoVGT can achieve much better performances than previous arts on video reasoning tasks. Its performances even surpass those models that are pretrained with millions of external data. We further show that CoVGT can also benefit from cross-modal pretraining, yet with orders of magnitude smaller data. The results demonstrate the effectiveness and superiority of CoVGT, and additionally reveal its potential for more data-efficient pretraining.

Förderung

  • Sea-NExT Joint Lab
  • National Natural Science Foundation of China

Zitieren

APA

Xiao, J., Zhou, P., Yao, A., Li, Y., Hong, R., Yan, S., & Chua, T. S. (2023). Contrastive Video Question Answering via Video Graph Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 13265-13280. https://doi.org/10.1109/tpami.2023.3292266

Vancouver

Xiao J, Zhou P, Yao A, Li Y, Hong R, Yan S, et al. Contrastive Video Question Answering via Video Graph Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(11):13265-13280. doi:10.1109/tpami.2023.3292266

BibTeX
@article{Xiao2023,
  author = {Xiao, Junbin and Zhou, Pan and Yao, Angela and Li, Yicong and Hong, Richang and Yan, Shuicheng and Chua, Tat-Seng},
  title = {Contrastive Video Question Answering via Video Graph Transformer},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {11},
  pages = {13265--13280},
  doi = {10.1109/tpami.2023.3292266}
}
Kostenlos starten →