Transferring Domain-Agnostic Knowledge in Video Question Answering
This work addresses the challenge of improving video question answering efficiency and accuracy for AI researchers, but it is incremental as it builds on existing transfer learning concepts.
The paper tackles the problem of high training costs and subpar performance in video question answering by proposing a transfer learning method that uses domain-agnostic knowledge as a medium, and it shows that this approach effectively boosts performance, as validated on a new dataset of 21,412 samples.
Video question answering (VideoQA) is designed to answer a given question based on a relevant video clip. The current available large-scale datasets have made it possible to formulate VideoQA as the joint understanding of visual and language information. However, this training procedure is costly and still less competent with human performance. In this paper, we investigate a transfer learning method by the introduction of domain-agnostic knowledge and domain-specific knowledge. First, we develop a novel transfer learning framework, which finetunes the pre-trained model by applying domain-agnostic knowledge as the medium. Second, we construct a new VideoQA dataset with 21,412 human-generated question-answer samples for comparable transfer of knowledge. Our experiments show that: (i) domain-agnostic knowledge is transferable and (ii) our proposed transfer learning framework can boost VideoQA performance effectively.