Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity
2021-10-30Code Available1· sign in to hype
Zhuoran Ma, Majing Lou, Xuan Ouyang
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/zr2021/2021_qq_aiac_tack1_1stOfficialIn paperpytorch★ 264
Abstract
In this paper, we describe the solution to the QQ Browser 2021 Ai Algorithm Competition (AIAC) Track 1. We use the multi-modal transformer model for the video embedding extraction. In the pretrain phase, we train the model with three tasks, (1) Video Tag Classification (VTC), (2) Mask Language Modeling (MLM) and (3) Mask Frame Modeling (MFM). In the finetune phase, we train the model with video similarity based on rank normalized human labels. Our full pipeline, after ensembling several models, scores 0.852 on the leaderboard, which we achieved the 1st place in the competition. The source codes have been released at Github.