Assistive tagging: A survey of multimedia tagging with human-computer joint exploration
Along with the explosive growth of multimedia data, automatic multimedia tagging has
attracted great interest of various research communities, such as computer vision …
attracted great interest of various research communities, such as computer vision …
Learning to detect unseen object classes by between-class attribute transfer
CH Lampert, H Nickisch… - 2009 IEEE conference on …, 2009 - ieeexplore.ieee.org
We study the problem of object classification when training and test classes are disjoint, ie
no training examples of the target classes are available. This setup has hardly been studied …
no training examples of the target classes are available. This setup has hardly been studied …
New trends and ideas in visual concept detection: The mir flickr retrieval evaluation initiative
MJ Huiskes, B Thomee, MS Lew - Proceedings of the international …, 2010 - dl.acm.org
The MIR Flickr collection consists of 25000 high-quality photographic images of thousands
of Flickr users, made available under the Creative Commons license. The database includes …
of Flickr users, made available under the Creative Commons license. The database includes …
Event driven web video summarization by tag localization and key-shot identification
With the explosive growth of web videos on the Internet, it becomes challenging to efficiently
browse hundreds or even thousands of videos. When searching an event query, users are …
browse hundreds or even thousands of videos. When searching an event query, users are …
Optimized CNN based image recognition through target region selection
W Hao, R Bie, J Guo, X Meng, S Wang - Optik, 2018 - Elsevier
Image recognition has plateaued in the last few years. According to this research field, some
complicated models typically combined feature extraction and classification models …
complicated models typically combined feature extraction and classification models …
Aspect-oriented sentiment analysis of customer reviews using distant supervision techniques
J Broß - 2013 - refubium.fu-berlin.de
Kundenrezensionen im Internet spielen heutzutage eine wichtige Rolle bei unseren
alltäglichen Kaufentscheidungen. Ebenso sind die unzähligen Produktbewertungen von …
alltäglichen Kaufentscheidungen. Ebenso sind die unzähligen Produktbewertungen von …
Learning automatic concept detectors from online video
Concept detection is targeted at automatically labeling video content with semantic concepts
appearing in it, like objects, locations, or activities. While concept detectors have become …
appearing in it, like objects, locations, or activities. While concept detectors have become …
Using one-class SVM outliers detection for verification of collaboratively tagged image training sets
H Lukashevich, S Nowak… - 2009 IEEE International …, 2009 - ieeexplore.ieee.org
Supervised learning requires adequately labeled training data. In this paper, we present an
approach for automatic detection of outliers in image training sets using an one-class …
approach for automatic detection of outliers in image training sets using an one-class …
Optimized recognition with few instances based on semantic distance
In this paper, we present a new object recognition model with few instances based on
semantic distance. Learning objects with many instances have been studied in computer …
semantic distance. Learning objects with many instances have been studied in computer …
Sampling and ontologically pooling web images for visual concept learning
Sufficient training examples are essential for effective learning of semantic visual concepts.
In practice, however, acquiring noise-free training examples has always been expensive …
In practice, however, acquiring noise-free training examples has always been expensive …