A Read-Write Memory Network for Movie Story Understanding

ICCV 2017 Seil NaSangho LeeJisung KimGunhee Kim

We propose a novel memory network model named Read-Write Memory Network (RWMN) to perform question and answering tasks for large-scale, multimodal movie story understanding. The key focus of our RWMN model is to design the read network and the write network that consist of multiple convolutional layers, which enable memory read and write operations to have high capacity and flexibility... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Video Story QA MovieQA RWMN Accuracy 36.25 # 2