Stage-oe-small.jpg

Inproceedings3598

Aus Aifbportal
Version vom 28. August 2018, 13:45 Uhr von Cj2486 (Diskussion | Beiträge)
(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu:Navigation, Suche


Discovering Connotations as Labels for Weakly Supervised Image-Sentence Data


Discovering Connotations as Labels for Weakly Supervised Image-Sentence Data



Published: 2018 April

Buchtitel: WWW'18: Proceedings of The Web Conference 2018, Lyon, France, April 2018
Seiten: 379-386
Verlag: ACM

Referierte Veröffentlichung

BibTeX

Kurzfassung
Growth of multimodal content on the web and social media has generated abundant weakly aligned image-sentence pairs. However, it is hard to interpret them directly due to intrinsic “intension”. In this paper, we aim to annotate such image-sentence pairs with connotations as labels to capture the intrinsic “intension”. We achieve it with a connotation multimodal embedding model (CMEM) using a novel loss function. It’s unique characteristics over previous models include: (i) the exploitation of multimodal data as opposed to only visual information, (ii) robustness to outlier labels in a multi-label scenario and (iii) works effectively with large-scale weakly supervised data. With extensive quantitative evaluation, we exhibit the effectiveness of CMEM for detection of multiple labels over other state-of-the-art approaches. Also, we show that in addition to annotation of image-sentence pairs with connotation labels, byproduct of our model inherently supports cross-modal retrieval i.e. image query - sentence retrieval.

ISBN: 978-1-4503-5640-4
Weitere Informationen unter: Link
DOI Link: 10.1145/3184558.3186352



Forschungsgruppe

Web Science


Forschungsgebiet

Information Retrieval, Maschinelles Lernen, Künstliche Intelligenz, WWW Systeme