_version_ 1866914064443113472
author Shafique, Bhuiyan Sanjid
Vayani, Ashmal
Maaz, Muhammad
Rasheed, Hanoona Abdul
Dissanayake, Dinura
Kurpath, Mohammed Irfan
Hmaiti, Yahya
Inoue, Go
Lahoud, Jean
Rashid, Md. Safirur
Quasem, Shadid Intisar
Fatima, Maheen
Vidal, Franco
Maslych, Mykola
More, Ketan Pravin
Baliah, Sanoojan
Watawana, Hasindri
Li, Yuhao
Farestam, Fabian
Schaller, Leon
Tymtsiv, Roman
Weber, Simon
Cholakkal, Hisham
Laptev, Ivan
Satoh, Shin'ichi
Felsberg, Michael
Shah, Mubarak
Khan, Salman
Khan, Fahad Shahbaz
author_facet Shafique, Bhuiyan Sanjid
Vayani, Ashmal
Maaz, Muhammad
Rasheed, Hanoona Abdul
Dissanayake, Dinura
Kurpath, Mohammed Irfan
Hmaiti, Yahya
Inoue, Go
Lahoud, Jean
Rashid, Md. Safirur
Quasem, Shadid Intisar
Fatima, Maheen
Vidal, Franco
Maslych, Mykola
More, Ketan Pravin
Baliah, Sanoojan
Watawana, Hasindri
Li, Yuhao
Farestam, Fabian
Schaller, Leon
Tymtsiv, Roman
Weber, Simon
Cholakkal, Hisham
Laptev, Ivan
Satoh, Shin'ichi
Felsberg, Michael
Shah, Mubarak
Khan, Salman
Khan, Fahad Shahbaz
contents Large multimodal models (LMMs) have recently gained attention due to their effectiveness to understand and generate descriptions of visual content. Most existing LMMs are in English language. While few recent works explore multilingual image LMMs, to the best of our knowledge, moving beyond the English language for cultural and linguistic inclusivity is yet to be investigated in the context of video LMMs. In pursuit of more inclusive video LMMs, we introduce a multilingual Video LMM benchmark, named ViMUL-Bench, to evaluate Video LMMs across 14 languages, including both low- and high-resource languages: English, Chinese, Spanish, French, German, Hindi, Arabic, Russian, Bengali, Urdu, Sinhala, Tamil, Swedish, and Japanese. Our ViMUL-Bench is designed to rigorously test video LMMs across 15 categories including eight culturally diverse categories, ranging from lifestyles and festivals to foods and rituals and from local landmarks to prominent cultural personalities. ViMUL-Bench comprises both open-ended (short and long-form) and multiple-choice questions spanning various video durations (short, medium, and long) with 8k samples that are manually verified by native language speakers. In addition, we also introduce a machine translated multilingual video training set comprising 1.2 million samples and develop a simple multilingual video LMM, named ViMUL, that is shown to provide a better tradeoff between high-and low-resource languages for video understanding. We hope our ViMUL-Bench and multilingual video LMM along with a large-scale multilingual video training set will help ease future research in developing cultural and linguistic inclusive multilingual video LMMs. Our proposed benchmark, video LMM and training data will be publicly released at https://mbzuai-oryx.github.io/ViMUL/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Culturally-diverse Multilingual Multimodal Video Benchmark & Model
Shafique, Bhuiyan Sanjid
Vayani, Ashmal
Maaz, Muhammad
Rasheed, Hanoona Abdul
Dissanayake, Dinura
Kurpath, Mohammed Irfan
Hmaiti, Yahya
Inoue, Go
Lahoud, Jean
Rashid, Md. Safirur
Quasem, Shadid Intisar
Fatima, Maheen
Vidal, Franco
Maslych, Mykola
More, Ketan Pravin
Baliah, Sanoojan
Watawana, Hasindri
Li, Yuhao
Farestam, Fabian
Schaller, Leon
Tymtsiv, Roman
Weber, Simon
Cholakkal, Hisham
Laptev, Ivan
Satoh, Shin'ichi
Felsberg, Michael
Shah, Mubarak
Khan, Salman
Khan, Fahad Shahbaz
Computation and Language
Computer Vision and Pattern Recognition
Large multimodal models (LMMs) have recently gained attention due to their effectiveness to understand and generate descriptions of visual content. Most existing LMMs are in English language. While few recent works explore multilingual image LMMs, to the best of our knowledge, moving beyond the English language for cultural and linguistic inclusivity is yet to be investigated in the context of video LMMs. In pursuit of more inclusive video LMMs, we introduce a multilingual Video LMM benchmark, named ViMUL-Bench, to evaluate Video LMMs across 14 languages, including both low- and high-resource languages: English, Chinese, Spanish, French, German, Hindi, Arabic, Russian, Bengali, Urdu, Sinhala, Tamil, Swedish, and Japanese. Our ViMUL-Bench is designed to rigorously test video LMMs across 15 categories including eight culturally diverse categories, ranging from lifestyles and festivals to foods and rituals and from local landmarks to prominent cultural personalities. ViMUL-Bench comprises both open-ended (short and long-form) and multiple-choice questions spanning various video durations (short, medium, and long) with 8k samples that are manually verified by native language speakers. In addition, we also introduce a machine translated multilingual video training set comprising 1.2 million samples and develop a simple multilingual video LMM, named ViMUL, that is shown to provide a better tradeoff between high-and low-resource languages for video understanding. We hope our ViMUL-Bench and multilingual video LMM along with a large-scale multilingual video training set will help ease future research in developing cultural and linguistic inclusive multilingual video LMMs. Our proposed benchmark, video LMM and training data will be publicly released at https://mbzuai-oryx.github.io/ViMUL/.
title A Culturally-diverse Multilingual Multimodal Video Benchmark & Model
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.07032