Benchmarking VLM Scene Understanding: How Well Do Vision-Language Models Interpret Video Narratives?

This study benchmarks three vision-language models Gemini 1.5 Pro, LLaMA 3.1 70B (via Groq), and LLaVA-NeXT-Video 7B , on structured video scene annotation across six dimensions: subject identification, action description, emotional tone, spatial relationships, scene transitions, and lighting/atmosphere. Results show proprietary models lead on temporal tasks, but all models struggle with emotional tone and spatial reasoning.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-09-25
DOI
https://doi.org/10.5281/zenodo.22964601
Primary Topic
Multimodal Machine Learning Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
preprint

Benchmarking VLM Scene Understanding: How Well Do Vision-Language Models Interpret Video Narratives?

Aurangzaib Shehzad Awan
Zenodo (CERN European Organization for Nuclear Research)
Multimodal Machine Learning Applications
preprint

Benchmarking VLM Scene Understanding: How Well Do Vision-Language Models Interpret Video Narratives?

Aurangzaib Shehzad Awan
preprint en

Abstract

This study benchmarks three vision-language models Gemini 1.5 Pro, LLaMA 3.1 70B (via Groq), and LLaVA-NeXT-Video 7B , on structured video scene annotation across six dimensions: subject identification, action description, emotional tone, spatial relationships, scene transitions, and lighting/atmosphere. Results show proprietary models lead on temporal tasks, but all models struggle with emotional tone and spatial reasoning.

Zenodo (CERN European Organization for Nuclear Research)
National University of Computer and Emerging Sciences (PK)
Multimodal Machine Learning Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.