Towards cross-category knowledge propagation for learning visual concepts

By Guo-Jun Qi, Charu C. Aggarwal, Yong Rui, Qi Tian, Shiyu Chang, Thomas S. Huang. 2011

83 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Zero-Shot Learning Through Cross-Modal Transfer (2013, background): “They are able to predict semantic features even for words for which they have not seen scans and experiment with differentiating between several zero-shot classes.”
Zero-Shot Object Detection (2018, background): “This problem is solved within the framework of transfer learning [13, 40], where visual models for seen classes are transferred to the unknown classes by exploiting semantic relationships between the two.”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “4] was often used by DA to learn how to bridge the relatedness between the source and target while exploiting class labels. Such supervised feature transformation methods were proposed for example in [270, 185, 272, 129, 169, 52]. Indeed, [270] proposes a new distance metric for the target domain by”
Harnessing Lab Knowledge for Real-World Action Recognition (2014, background): “In Qi et al. (2011) have investigated the feasibility to use cross-category knowledge for improving the learning process by exploring the knowledge in correlated categories.”
Data Classification: Algorithms and Applications (2014, background): “This general principle can also be applied to cross-category or cross-domain scenarios where knowledge from one classification category is used to enhance the learning of another category [71], or the knowledge from one data domain (e.”
Visual event recognition in videos by learning from web data (2010, background): “Besides the adaption between the web domain and consumer domain studied in this work and [29], other examples that vision researchers are recently working on include the adaptation of crosscategory knowledge to a new category domain [36], the knowledge transfer by mining semantic relatedness [38], a”
Generalized Transfer Subspace Learning Through Low-Rank Constraint (2014, background): “More and more research effort is being devoted to visual domain adaptation (Yang et al. 2007; Jiang et al. 2008; Wang et al. 2008; Duan et al. 2009, 2012a,b,c; Si et al. 2010; Saenko et al. 2010; Gopalan et al. 2011; Kulis et al. 2011; Aytar and Zisserman 2011; Qi et al. 2011; Lim et al. 2011; Gong ”