Inproceedings3598: Unterschied zwischen den Versionen
Nk6388 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Mogadala |ErsterAutorVorname=Aditya }} {{Publikation Author |Rank=Bhargav Kanuparthi |Author=Achim Rettinger }} {{…“) |
Nk6388 (Diskussion | Beiträge) |
||
Zeile 4: | Zeile 4: | ||
}} | }} | ||
{{Publikation Author | {{Publikation Author | ||
− | |Rank=Bhargav Kanuparthi | + | |Rank=2 |
+ | |Author=Bhargav Kanuparthi | ||
+ | }} | ||
+ | {{Publikation Author | ||
+ | |Rank=3 | ||
|Author=Achim Rettinger | |Author=Achim Rettinger | ||
+ | }} | ||
+ | {{Publikation Author | ||
+ | |Rank=4 | ||
+ | |Author=York Sure-Vetter | ||
}} | }} | ||
{{Inproceedings | {{Inproceedings |
Version vom 9. Januar 2018, 12:11 Uhr
Discovering Connotations as Labels for Weakly Supervised Image-Sentence Data
Discovering Connotations as Labels for Weakly Supervised Image-Sentence Data
Published: 2018
April
Buchtitel: The Web Conference (Cognitive Computing Track)
Verlag: ACM
Referierte Veröffentlichung
BibTeX
Kurzfassung
We address the task of labeling image-sentence pair at large-scale
with varied concepts representing connotations. That is for any
given query image-sentence, we aim to annotate them with the
connotations that capture intrinsic intension. To achieve it, we pro-
pose a Connotation multimodal embedding model (CMEM) with a
novel loss function. Its unique characteristics over previous models
include (i) can leverage multimodal data as opposed to only visual
information, (ii) robust to outlier labels in a multi-label scenario
and (iii) works well 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 images
with connotation labels, our byproduct of the model inherently
supports cross-modal retrieval.
Information Retrieval, Maschinelles Lernen, Künstliche Intelligenz, WWW Systeme