Multimodal large language models (MLLMs) have shown remarkable progress in high-level semantic tasks such as visual question answering, image captioning, and emotion recognition. However, despite advancements, there remains a lack of standardized benchmarks for evaluating MLLMs performance in multi-object sentiment analysis, a key task in semantic understanding. To address this gap, we introduce MOSABench, a novel evaluation dataset designed specifically for multi-object sentiment analysis.

DOI Link: 
10.21227/q94c-c298
Read more

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Subscribe now or login.

[1] Shezheng Song, "MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image", IEEE Dataport, 2024. [Online]. Available: http://dx.doi.org/10.21227/q94c-c298. Accessed: Feb. 05, 2025.
@data{q94c-c298-24,
doi = {10.21227/q94c-c298},
url = {http://dx.doi.org/10.21227/q94c-c298},
author = {Shezheng Song },
publisher = {IEEE Dataport},
title = {MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image},
year = {2024} }
TY - DATA
T1 - MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image
AU - Shezheng Song
PY - 2024
PB - IEEE Dataport
UR - 10.21227/q94c-c298
ER -
Shezheng Song. (2024). MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image. IEEE Dataport. http://dx.doi.org/10.21227/q94c-c298
Shezheng Song, 2024. MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image. Available at: http://dx.doi.org/10.21227/q94c-c298.
Shezheng Song. (2024). "MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image." Web.
1. Shezheng Song. MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image [Internet]. IEEE Dataport; 2024. Available from : http://dx.doi.org/10.21227/q94c-c298
Shezheng Song. "MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image." doi: 10.21227/q94c-c298