@inproceedings{ataallah-etal-2025-infinibench,
title = "{I}nfini{B}ench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and {TV} Shows",
author = "Ataallah, Kirolos and
Bakr, Eslam Mohamed and
Ahmed, Mahmoud and
Gou, Chenhui and
Pahwa, Khushbu and
Ding, Jian and
Elhoseiny, Mohamed",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.984/",
pages = "19496--19523",
ISBN = "979-8-89176-332-6",
abstract = "Understanding long-form videos, such as movies and TV episodes ranging from tens of minutes to two hours, remains a significant challenge for multi-modal models. Existing benchmarks often fail to test the full range of cognitive skills needed to process these temporally rich and narratively complex inputs. Therefore, we introduce InfiniBench, a comprehensive benchmark designed to evaluate the capabilities of models in long video understanding rigorously.InfiniBench offers:(1) Over 1,000 hours of video content, with an average video length of 53 minutes.(2) The largest set of question-answer pairs for long video comprehension, totaling around 87.7 K.(3) Eight diverse skills that span both grounding-based (e.g., scene transitions, character actions) and reasoning-based (e.g., deep context understanding, multi-event linking).(4) Rich annotation formats, including both multiple-choice and open-ended questions.We conducted an in-depth evaluation across both commercial (GPT-4o, Gemini 2.0 Flash) and most recent open-source vision-language models, such as Qwen2.5-VL, InternVL3.0). Results reveal that:(1) Models struggle across the board: Even the best model, GPT-4o, achieves only 47.1{\%} on grounding-based skills, with most models performing near or just above random chance.(2) Strong reliance on world knowledge: Models achieve surprisingly high scores using only metadata (e.g., video titles), highlighting a tendency to rely on pre-trained knowledge rather than actual visual or temporal understanding.(3) Multi-Modal Importance: When provided with full video and subtitle context, however, models show substantial improvements, confirming the critical role of multimodal input in video understanding.Our findings underscore the inherent challenges in long-video comprehension and point to the need for substantial advancements in both grounding and reasoning capabilities in MLLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ataallah-etal-2025-infinibench">
<titleInfo>
<title>InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kirolos</namePart>
<namePart type="family">Ataallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eslam</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Bakr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Gou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushbu</namePart>
<namePart type="family">Pahwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Elhoseiny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Understanding long-form videos, such as movies and TV episodes ranging from tens of minutes to two hours, remains a significant challenge for multi-modal models. Existing benchmarks often fail to test the full range of cognitive skills needed to process these temporally rich and narratively complex inputs. Therefore, we introduce InfiniBench, a comprehensive benchmark designed to evaluate the capabilities of models in long video understanding rigorously.InfiniBench offers:(1) Over 1,000 hours of video content, with an average video length of 53 minutes.(2) The largest set of question-answer pairs for long video comprehension, totaling around 87.7 K.(3) Eight diverse skills that span both grounding-based (e.g., scene transitions, character actions) and reasoning-based (e.g., deep context understanding, multi-event linking).(4) Rich annotation formats, including both multiple-choice and open-ended questions.We conducted an in-depth evaluation across both commercial (GPT-4o, Gemini 2.0 Flash) and most recent open-source vision-language models, such as Qwen2.5-VL, InternVL3.0). Results reveal that:(1) Models struggle across the board: Even the best model, GPT-4o, achieves only 47.1% on grounding-based skills, with most models performing near or just above random chance.(2) Strong reliance on world knowledge: Models achieve surprisingly high scores using only metadata (e.g., video titles), highlighting a tendency to rely on pre-trained knowledge rather than actual visual or temporal understanding.(3) Multi-Modal Importance: When provided with full video and subtitle context, however, models show substantial improvements, confirming the critical role of multimodal input in video understanding.Our findings underscore the inherent challenges in long-video comprehension and point to the need for substantial advancements in both grounding and reasoning capabilities in MLLMs.</abstract>
<identifier type="citekey">ataallah-etal-2025-infinibench</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.984/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>19496</start>
<end>19523</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows
%A Ataallah, Kirolos
%A Bakr, Eslam Mohamed
%A Ahmed, Mahmoud
%A Gou, Chenhui
%A Pahwa, Khushbu
%A Ding, Jian
%A Elhoseiny, Mohamed
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F ataallah-etal-2025-infinibench
%X Understanding long-form videos, such as movies and TV episodes ranging from tens of minutes to two hours, remains a significant challenge for multi-modal models. Existing benchmarks often fail to test the full range of cognitive skills needed to process these temporally rich and narratively complex inputs. Therefore, we introduce InfiniBench, a comprehensive benchmark designed to evaluate the capabilities of models in long video understanding rigorously.InfiniBench offers:(1) Over 1,000 hours of video content, with an average video length of 53 minutes.(2) The largest set of question-answer pairs for long video comprehension, totaling around 87.7 K.(3) Eight diverse skills that span both grounding-based (e.g., scene transitions, character actions) and reasoning-based (e.g., deep context understanding, multi-event linking).(4) Rich annotation formats, including both multiple-choice and open-ended questions.We conducted an in-depth evaluation across both commercial (GPT-4o, Gemini 2.0 Flash) and most recent open-source vision-language models, such as Qwen2.5-VL, InternVL3.0). Results reveal that:(1) Models struggle across the board: Even the best model, GPT-4o, achieves only 47.1% on grounding-based skills, with most models performing near or just above random chance.(2) Strong reliance on world knowledge: Models achieve surprisingly high scores using only metadata (e.g., video titles), highlighting a tendency to rely on pre-trained knowledge rather than actual visual or temporal understanding.(3) Multi-Modal Importance: When provided with full video and subtitle context, however, models show substantial improvements, confirming the critical role of multimodal input in video understanding.Our findings underscore the inherent challenges in long-video comprehension and point to the need for substantial advancements in both grounding and reasoning capabilities in MLLMs.
%U https://aclanthology.org/2025.emnlp-main.984/
%P 19496-19523
Markdown (Informal)
[InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows](https://aclanthology.org/2025.emnlp-main.984/) (Ataallah et al., EMNLP 2025)
ACL