Towards semantic knowledge propagation from text corpus to web images

By Guo-Jun Qi, Charu C. Aggarwal, Thomas S. Huang. 2011

119 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

Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “e.g. images). While this assumption essentially differentiates the multi-view learning from HDA, we have seen in Section 3.3 that HDA methods often rely on an auxiliary intermediate multi-view domain [104, 106, 103, 101, 107, 109]. Hence, HDA/HTL can strongly beneﬁt from multi-view learning techniqu”
Heterogeneous Network Embedding via Deep Architectures (2015, background): “In particular, images are given as a squared tensor format as P R d I ˆ d I ˆ 3 for every v i P V I , while texts are represented by a d T -dimensional feature vector as P R d T for all P V T . could format For example, the content representations be a raw pixel in RGB color space for images, or it ”
On the Role of Correlation and Abstraction in Cross-Modal Multimedia Retrieval (2014, background): “This allows assessments of image similarity in terms of weighted combinations of vocabulary words and substantially extends the range of concepts that can effectively be retrieved.”
Human Reidentification with Transferred Metric Learning (2012, methodology): “Transfer learning has been widely applied to various vision problems such as object recognition [25], object detection [26], image and video retrieval [27], and visual concept classification [28, 24, 29, 30].”
Cross-Modality Submodular Dictionary Learning for Information Retrieval (2014, unknown): “Cross-modality information retrieval approaches [ 8 ] , [ 29 ] , [ 30 ] , [ 32 ] , [ 43 ] On the top of the above scenarios, we introduce a novel framework which aims at enhancing the classical unimodal information retrieval systems with unlabeled training data in a different media form.”
Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation (2015, background): “The performance of the compared transfer learning algorithms, including TTI, HTL and the proposed DTNs, is improved to different degrees.”
Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation (2018, methodology): “These categories can provide enough data to support our experiment and are also used by (Shu et al. 2015; Qi, Aggarwal, and Huang 2011).”
A Decade Survey of Transfer Learning (2010–2020) (2020, unknown): “Todecreasethecomputationalcost,[65]proposedanother methodfortext-to-image(TTI)classiﬁcation.”
Understanding web images by object relation network (2012, background): “Transfer learning from text to images [19] builds a semantic linkage between text and image based on their co-occurrence.”