Machine Learning for Video Processing

Video Question Answering

 

Title

Progressive Attention Memory Network for Movie Story Question Answering

Author

Junyeong Kim, Minuk Ma, Kyungsu Kim, Sunjin Kim, and Chang D. Yoo

Abstract


This paper proposes the progressive attention memory network (PAMN) for movie story question answering (QA). Movie story QA is challenging compared to VQA in two aspects: (1) pinpointing the temporal parts relevant to answer the question is difficult as the movies are typically longer than an hour, (2) it has both video and subtitle where different questions require different modality to infer the answer. To overcome these challenges, PAMN involves three main features: (1) progressive attention mechanism that utilizes cues from both question and answer to progressively prune out irrelevant temporal parts in memory, (2) dynamic modality fusion that adaptively determines the contribution of each modality for answering the current question, and (3) belief correction answering scheme that successively corrects the prediction score on each candidate answer. Experiments on publicly available benchmark datasets, MovieQA and TVQA, demonstrate that each feature contributes to our movie story QA architecture, PAMN, and improves performance to achieve the state-of-the-art result. Qualitative analysis by visualiz


VQA.PNG

Related Papers

1. Sunghun Kang, Junyeong Kim, Hyunsoo Choi, Sungjin Kim and Chang D. Yoo, "Pivot Correlational Neural Network for Multimodal Video Categorization", European Conference on Computer Vision, 2018

2. Junyeong Kim, Minuk Ma, Trung X, Kyungsu Kim and Chang D. Yoo, "Modality Shifting Attention Network for Multi-modal Video Question Answering", Computer Vision and Pattern Recognition, 2020