Multiple Hypothesis Video Relation Detection

• Published in: 2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM) pp. 287 - 291
• Main Authors: Di, Donglin, Shang, Xindi, Zhang, Weinan, Yang, Xun, Chua, Tat-Seng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2019
• Subjects: Feature extraction; Proposals; relational association; Robustness; Tagging; Task analysis; Trajectory; video relation detection; visual relationship; Visualization
• DOI: 10.1109/BigMM.2019.000-9

Video relation in the form of triplet〈subject, predicate, object〉plays a vital role in video content understanding. Existing works on video relation detection are limited to associating short-term relations into long-term relations throughout the video, because of the inaccurate and missing problem of short-term proposals. To alleviate the weakness of existing video relation detection methods, this work proposes a novel approach called Multi-Hypothesis Relational Association (MHRA), that can generate multiple hypotheses for video relation instances for more robust long-term relation prediction. Experiments on the benchmark dataset show that MHRA is able to outperform the state-of-the-art methods.