# First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge

arXiv: https://arxiv.org/abs/2409.13538 · HTML: https://mlsanity.com/paper/2409.13538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 3 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 3 of 3)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)

## Abstract (arXiv)

In this report, we present our first-place solution to the Multiple-choice Video Question Answering (QA) track of The Second Perception Test Challenge. This competition posed a complex video understanding task, requiring models to accurately comprehend and answer questions about video content. To address this challenge, we leveraged the powerful QwenVL2 (7B) model and fine-tune it on the provided training set. Additionally, we employed model ensemble strategies and Test Time Augmentation to boost performance. Through continuous optimization, our approach achieved a Top-1 Accuracy of 0.7647 on the leaderboard.