# Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval

arXiv: https://arxiv.org/abs/2510.09553 · HTML: https://mlsanity.com/paper/2510.09553/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [A Joint Sequence Fusion Model for Video Question Answering and Retrieval](https://mlsanity.com/paper/1808.02559/) (2018)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [CenterCLIP: Token Clustering for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2205.00823/) (2022)
- [Dual Encoding for Zero-Example Video Retrieval](https://mlsanity.com/paper/1809.06181/) (2018)
- [Biomedical Entity Representations with Synonym Marginalization](https://mlsanity.com/paper/2005.00239/) (2020)
- [Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video](https://mlsanity.com/paper/2203.06667/) (2022)
- [More but Correct: Generating Diversified and Entity-revised Medical Response](https://mlsanity.com/paper/2108.01266/) (2021)
- [Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training](https://mlsanity.com/paper/2211.10801/) (2022)
- [Detection of AI Deepfake and Fraud in Online Payments Using GAN-Based Models](https://mlsanity.com/paper/2501.07033/) (2025)
- [AltGen: AI-Driven Alt Text Generation for Enhancing EPUB Accessibility](https://mlsanity.com/paper/2501.00113/) (2024)
- [Learning to Locate Visual Answer in Video Corpus Using Question](https://mlsanity.com/paper/2210.05423/) (2022)
- [Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages](https://mlsanity.com/paper/2312.16159/) (2023)
- [Contextual Bandits for Unbounded Context Distributions](https://mlsanity.com/paper/2408.09655/) (2024)
- [Visual Answer Localization with Cross-modal Mutual Knowledge Transfer](https://mlsanity.com/paper/2210.14823/) (2022)
- [LLM-RM at SemEval-2023 Task 2: Multilingual Complex NER using XLM-RoBERTa](https://mlsanity.com/paper/2305.03300/) (2023)
- [Overview of the NLPCC 2025 Shared Task 4: Multi-modal, Multilingual, and Multi-hop Medical Instructional Video Question Answering Challenge](https://mlsanity.com/paper/2505.06814/) (2025)
- [Comparative Analysis of Large Language Models for Context-Aware Code Completion using SAFIM Framework](https://mlsanity.com/paper/2502.15243/) (2025)

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

- [Overview of the NLPCC 2026 Shared Task 1: Difficulty-Aware Multilingual and Multimodal Medical Instructional Video Understanding Evaluation](https://mlsanity.com/paper/2607.06618/) (2026)

## Abstract (arXiv)

Retrieving relevant instructional videos from multilingual medical archives is crucial for answering complex, multi-hop questions across language boundaries. However, existing systems either compress hour-long videos into coarse embeddings or incur prohibitive costs for fine-grained matching. We tackle the Multilingual Video Corpus Retrieval (mVCR) task in the NLPCC-2025 M4IVQA challenge with a multi-stage framework that integrates multilingual semantics, domain terminology, and efficient long-form processing. Video subtitles are divided into semantically coherent chunks, enriched with concise knowledge-graph (KG) facts, and organized into a hierarchical tree whose node embeddings are generated by a language-agnostic multilingual encoder. At query time, the same encoder embeds the input question; a coarse-to-fine tree search prunes irrelevant branches, and only the top-ranked chunks are re-scored by a lightweight large language model (LLM). This design avoids exhaustive cross-encoder scoring while preserving chunk-level precision. Experiments on the mVCR test set demonstrate state-of-the-art performance, and ablation studies confirm the complementary contributions of KG enrichment, hierarchical indexing, and targeted LLM re-ranking. The proposed method offers an accurate and scalable solution for multilingual retrieval in specialized medical video collections.