# Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity

arXiv: https://arxiv.org/abs/2111.01677 · HTML: https://mlsanity.com/paper/2111.01677/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 30 Oct 2021.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2002.06353/) (2020)
- [UNITER: UNiversal Image-TExt Representation Learning](https://mlsanity.com/paper/1909.11740/) (2019)
- [VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding](https://mlsanity.com/paper/2105.09996/) (2021)
- [Survey: Transformer based Video-Language Pre-training](https://mlsanity.com/paper/2109.09920/) (2021)

## Built on by (most cited first, 1 of 1)

- [MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling](https://mlsanity.com/paper/2303.05707/) (2023)

## Abstract (arXiv)

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.