paper-with-me

홈 › Papers

MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion

2026-05-28 · Ali Abusaleh, Bhuvanesh Verma, Alexander Mehler arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.29765

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

2023-02-02 · NeurIPS 2023 11 · Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang 외

Time series analysis is widely used in extensive areas. Recently, to reduce labeling expenses and benefit various tasks, self-supervised pre-training has attracted immense interest. One mainstream paradigm is masked mode…

Representation LearningTime SeriesTime Series Analysis

MMTM: Multimodal Transfer Module for CNN Fusion

2019-11-20 · CVPR 2020 6 · Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L. Iuzzolino, Kazuhito Koishida

In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end. Due to its simplicity late fusion is still the predominant…

Action RecognitionAction Recognition In VideosGesture RecognitionHand Gesture Recognition+3

Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding

2023-03-02 · Zefa Hu, Xiuyi Chen, Haoran Wu, Minglun Han 외

Medical Slot Filling (MSF) task aims to convert medical queries into structured information, playing an essential role in diagnosis dialogue systems. However, the lack of sufficient term semantics learning makes existing…

slot-fillingSlot Filling

MMTM: Multi-Tasking Multi-Decoder Transformer for Math Word Problems

2022-06-02 · Keyur Faldu, Amit Sheth, Prashant Kikani, Darshan Patel

Recently, quite a few novel neural architectures were derived to solve math word problems by predicting expression trees. These architectures varied from seq2seq models, including encoders leveraging graph relationships …

DecoderMathMathematical Reasoning

CEMTM: Contextual Embedding-based Multimodal Topic Modeling

2025-09-14 · Amirhossein Abaskohi, Raymond Li, Chuyuan Li, Shafiq Joty 외 arxiv

We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and images. CEMTM builds on fine-tuned large …