Diving deep into sentiment: understanding fine-tuned CNNs for visual sentiment prediction
Visualitza/Obre
Cita com:
hdl:2117/82547
Tipus de documentComunicació de congrés
Data publicació2015
EditorAssociation for Computing Machinery (ACM)
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
Visual media are powerful means of expressing emotions and sentiments. The constant generation of new content in social networks highlights the need of automated visual sentiment analysis tools. While Convolutional Neural Networks (CNNs) have established a new state-of-the-art in several vision problems, their application to the task of sentiment analysis is mostly unexplored and there are few studies regarding how to design CNNs for this purpose. In this work, we study the suitability of fine-tuning a CNN for visual sentiment prediction as well as explore performance boosting techniques within this deep learning setting. Finally, we provide a deep-dive analysis into a benchmark, state-of-the-art network architecture to gain insight about how to design patterns for CNNs on the task of visual sentiment prediction.
CitacióCampos, V., Salvador, A., Jou, B., Giro, X. Diving deep into sentiment: understanding fine-tuned CNNs for visual sentiment prediction. A: International Workshop on Affect & Sentiment in Multimedia. "ASM '15 Proceedings of the 1st International Workshop on Affect & Sentiment in Multimedia". Brisbane: Association for Computing Machinery (ACM), 2015, p. 57-62.
ISBN978-1-4503-3750-2
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
1508.05056v2.pdf | Preprint published on arXiv | 506,2Kb | Visualitza/Obre |