Saved in:
Bibliographic Details
Main Authors: Abusaleh, Ali, Verma, Bhuvanesh, Mehler, Alexander
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.29765
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918529193738240
author Abusaleh, Ali
Verma, Bhuvanesh
Mehler, Alexander
author_facet Abusaleh, Ali
Verma, Bhuvanesh
Mehler, Alexander
contents We introduce MMTM, a modular pipeline for topic discovery in long-form video that integrates speech recognition, audio and visual embeddings, and BERTopic clustering through a deterministic similarity-gated fusion. Evaluated cross-lingually on German (Tagesschau) and English (NBC) broadcast news, joint tri-modal modeling substantially improves topic quality: noise drops from 0.27 to 0.06, transition rate from 0.70 to 0.21, and normalized entropy rises from 0.84 to 0.92, indicating more coherent and temporally stable topics. Cluster validity (Calinski-Harabasz) improves by 5-12X across embedding spaces. Lexical coherence (NPMI) rises from 0.77 to 0.86 on German but is corpus-dependent and does not transfer to the shorter NBC broadcasts. We release the pipeline code and a human-validated 54-hour multimodal video topic corpus with dual-annotator visual evaluation and LLM-assisted labeling.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29765
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion
Abusaleh, Ali
Verma, Bhuvanesh
Mehler, Alexander
Machine Learning
We introduce MMTM, a modular pipeline for topic discovery in long-form video that integrates speech recognition, audio and visual embeddings, and BERTopic clustering through a deterministic similarity-gated fusion. Evaluated cross-lingually on German (Tagesschau) and English (NBC) broadcast news, joint tri-modal modeling substantially improves topic quality: noise drops from 0.27 to 0.06, transition rate from 0.70 to 0.21, and normalized entropy rises from 0.84 to 0.92, indicating more coherent and temporally stable topics. Cluster validity (Calinski-Harabasz) improves by 5-12X across embedding spaces. Lexical coherence (NPMI) rises from 0.77 to 0.86 on German but is corpus-dependent and does not transfer to the shorter NBC broadcasts. We release the pipeline code and a human-validated 54-hour multimodal video topic corpus with dual-annotator visual evaluation and LLM-assisted labeling.
title MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion
topic Machine Learning
url https://arxiv.org/abs/2605.29765