paper-with-me

Papers

MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching

2026-06-10 · David Yuchen Wang, Haoying Li, Hailun Xu, Wei Chee Yew, Zirui Zhu, Sanjay Saha, Hao Hei, Kanchan Sarkar, Kun Xu arxiv

The explosive growth of user-generated video content on online platforms is accompanied by the emergence of numerous near-duplicate videos--videos that are identical or highly similar but differ by partial edits. These duplicates degrade user experience and increase storage and bandwidth costs, making large-scale video deduplication a critical task. Existing video deduplication frameworks face a fundamental challenge in retrieving sufficient high-quality candidates under a limited index budget, as well as trade-offs between efficiency and precision. To address these issues, we propose MLT-Dedup, an efficient large-scale online video deduplication framework with Multi-Level representations and spatial-Temporal matching. Our approach employs a Multi-Level Video Encoder (ML-VE) to extract both fine-grained frame-level and sparse clip-level embeddings: sparse embeddings support efficient candidate retrieval, while fine-grained embeddings are loaded for precise pairwise matching. During matching, we introduce DiF-SiM, a Differential Feature-enhanced Similarity Module capable of locating duplicated temporal segments and providing reliable similarity evidence to support policy-driven deduplication decisions. Extensive experiments on a real-world large-scale platform demonstrate that MLT-Dedup reduces online repetition rates by 91% at 90% precision. Furthermore, our sparse retrieval design achieves a 5x increase in indexing capacity, enabling broader candidate coverage in real-world deployment.

📄 PDF Abstract BibTeX arXiv:2606.12215

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)

2024-07-11 · Aydin Abadi, Vishnu Asutosh Dasu, Sumanta Sarkar

Deduplication is a vital preprocessing step that enhances machine learning model performance and saves training time and energy. However, enhancing federated learning through deduplication poses challenges, especially re…

Federated LearningPrivacy Preserving

LSHBloom: Memory-efficient, Extreme-scale Document Deduplication

2024-11-06 · Arham Khan, Robert Underwood, Carlo Siebenschuh, Yadu Babuji 외

Deduplication is a major focus for assembling and curating training datasets for large language models (LLM) -- detecting and eliminating additional instances of the same content -- in large collections of technical docu…

Memorization

A Robust and Efficient Pipeline for Enterprise-Level Large-Scale Entity Resolution

2025-08-05 · Sandeepa Kannangara, Arman Abrahamyan, Daniel Elias, Thomas Kilby 외 arxiv

Entity resolution (ER) remains a significant challenge in data management, especially when dealing with large datasets. This paper introduces MERAI (Massive Entity Resolution using AI), a robust and efficient pipeline de…

Entity Resolution

FED: Fast and Efficient Dataset Deduplication Framework with GPU Acceleration

2025-01-02 · YoungJun Son, Chaewon Kim, Jaejin Lee

Dataset deduplication plays a crucial role in enhancing data quality, ultimately improving training performance and efficiency of LLMs. A commonly used method for data deduplication is the MinHash LSH algorithm. Recently…

CPUGPU

Large scale deduplication based on fingerprints

2021-01-13 · Jean Aymar Biyiha Nlend, Ibrahim Moukouop Nguena, Thomas Bouetou Bouetou

In fingerprint-based systems, the size of databases increases considerably with population growth. In developing countries, because of the difficulty in using a central system when enlisting voters, it often happens that…