Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity
This is an incremental solution for a specific competition track, addressing video similarity for AI algorithm benchmarking.
The paper tackled the problem of multimodal video similarity by using a multi-modal transformer model with pretraining on three tasks and fine-tuning on human-labeled similarity, achieving a score of 0.852 and first place in the competition.
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.