@misc{li2020hero,
author = {Li, Linjie and Chen, Yen-Chun and Cheng, Yu and Gan, Zhe and Yu, Licheng and Liu, JJ (Jingjing)},
title = {HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training},
howpublished = {ArXiv},
year = {2020},
month = {May},
abstract = {We present HERO, a Hierarchical EncodeR for Omni-representation learning, for large-scale video+language pre-training. HERO encodes multimodal inputs in a hierarchical fashion, where local textual context of a video frame
is captured by a Cross-modal Transformer via multimodal fusion, and global video context is captured by a Temporal Transformer. Besides standard Masked Language Modeling (MLM) and Masked Frame Modeling (MFM) objectives, we design two new pre-training tasks: (i) Video-Subtitle Matching (VSM), where the model predicts both global and local temporal alignment; and (ii) Frame Order Modeling (FOM), where the model predicts the right order of shuffled video frames. Different from previous work that mostly focused on cooking or narrated instructional videos, HERO is jointly trained on HowTo100M and largescale TV show datasets to learn complex social scenes, dynamics backdrop transitions and multi-character interactions. Extensive experiments demonstrate that HERO achieves new state of the art on both text-based video moment retrieval and video question answering tasks across different domains.},
url = {http://approjects.co.za/?big=en-us/research/publication/hero-hierarchical-encoder-for-videolanguage-omni-representation-pre-training/},
}