Recognizing Characters and Relationships from Videos via Spatial-Temporal and Multimodal Cues

• Published in: 2021 IEEE International Conference on Big Knowledge (ICBK) pp. 174 - 181
• Main Authors: Cao, Chenyu, Yan, Chenghao, Li, Fangtao, Liu, Zihe, Wang, Zheng, Wu, Bin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2021
• Subjects: Convolution; Feature extraction; Fuses; Graph neural networks; multi-modal; person recognition; Representation learning; Semantics; social relation extraction; temporal; video understanding; Visualization

Video contains rich semantic knowledge of multiple modalities related to a person. Mining deep or potential semantic knowledge in the video could help artificial intelligence better understand the behavior and emotion of humans in the video. The researches for deep and context semantic knowledge in...