Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search

TL;DR

This paper introduces a Multi-Branch Collaborative Network (MBCN) for industrial video retrieval that effectively identifies various low-quality video issues, improving ranking performance and accuracy, especially for AI-generated videos.

Contribution

The paper presents a novel multi-branch network architecture specifically designed to detect diverse low-quality issues in industrial videos, a problem overlooked in prior research.

Findings

MBCN significantly improves video ranking performance.

All four evaluation branches positively contribute to quality assessment.

Enhanced recognition accuracy for AI-generated low-quality videos.

Abstract

Video Quality Assessment (VQA) is vital for large-scale video retrieval systems, aimed at identifying quality issues to prioritize high-quality videos. In industrial systems, low-quality video characteristics fall into four categories: visual-related issues like mosaics and black boxes, textual issues from video titles and OCR content, and semantic issues like frame incoherence and frame-text mismatch from AI-generated videos. Despite their prevalence in industrial settings, these low-quality videos have been largely overlooked in academic research, posing a challenge for accurate identification. To address this, we introduce the Multi-Branch Collaborative Network (MBCN) tailored for industrial video retrieval systems. MBCN features four branches, each designed to tackle one of the aforementioned quality issues. After each branch independently scores videos, we aggregate these scores using a weighted approach and a squeeze-and-excitation mechanism to dynamically address quality issues across different scenarios. We implement point-wise and pair-wise optimization objectives to ensure score stability and reasonableness. Extensive offline and online experiments on a world-level video search engine demonstrate MBCN's effectiveness in identifying video quality issues, significantly enhancing the retrieval system's ranking performance. Detailed experimental analyses confirm the positive contribution of all four evaluation branches. Furthermore, MBCN significantly improves recognition accuracy for low-quality AI-generated videos compared to the baseline.