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

Yingzhe Peng, Yixiao Yuan, Zitian Ao, Huapeng Zhou, Kangqi Wang +2 more
9/20/2024
cs.CVcs.AIcs.LG

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark

85% match2024

Perception Test 2025: Challenge Summary and a Unified VQA Extension

82% match2026

Lost in Time: A New Temporal Benchmark for VideoLLMs

82% match2024

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process

81% match2025

STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering

80% match2026

Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering

80% match2024

Cite this paper

@article{peng2024first,
  title  = {First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge},
  author = {Yingzhe Peng and Yixiao Yuan and Zitian Ao and Huapeng Zhou and Kangqi Wang and Qipeng Zhu and Xu Yang},
  year   = {2024},
  eprint = {2409.13538},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.13538v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.13538.svg)](https://codeofpaper.com/paper/2409.13538)

Discussion