A Video Question Answering Model Based on Knowledge Distillation
Video question answering (QA) is a cross-modal task that requires understanding the video content to answer questions. Current techniques address this challenge by employing stacked modules, such as attention mechanisms and graph convolutional networks. These methods reason about the semantics of vi...
Main Authors: | Zhuang Shao, Jiahui Wan, Linlin Zong |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2078-2489/14/6/328 |
Similar Items
-
TASTA: Text‐Assisted Spatial and Temporal Attention Network for Video Question Answering
by: Tian Wang, et al.
Published: (2023-04-01) -
Advancements in Complex Knowledge Graph Question Answering: A Survey
by: Yiqing Song, et al.
Published: (2023-10-01) -
Language Bias-Driven Self-Knowledge Distillation with Generalization Uncertainty for Reducing Language Bias in Visual Question Answering
by: Desen Yuan, et al.
Published: (2022-07-01) -
Standard refrigeration and air conditioning : questions and answers/
by: 247465 Elonka, Stephen Michael, et al.
Published: (1973) -
A survey on complex factual question answering
by: Lingxi Zhang, et al.
Published: (2023-01-01)