CNN-RNN: A Unified Framework for Multi-label Image Classification

Wang, Jiang; Yang, Yi; Mao, Junhua; Huang, Zhiheng; Huang, Chang; Xu, Wei

doi:10.1109/cvpr.2016.251

Cited by 1,049 publications

(769 citation statements)

References 37 publications

Supporting

Mentioning

712

Contrasting

Unclassified

Order By: Relevance

“…Some research employs a unified CNN-RNN framework learns a joint image-label embedding to characterize the semantic label dependency as well as the image-label relevance, and it can be trained end-to-end from scratch to integrate both information in one framework, the model achieves better performance than the state-of-the-art multi-label classification models [35]. The model for intelligent analysis in this paper is mainly composed of two parts, a CNN for learning styles detection and a RNN combined with gated recurrent unit for learning styles prediction.…”

Section: Intelligent Analysis Processmentioning

confidence: 99%

Enhancing the Efficiency of Massive Online Learning by Integrating Intelligent Analysis into MOOCs with an Application to Education of Sustainability

Zhou

2018

Sustainability

View full text Add to dashboard Cite

Massive Open Online Courses (MOOCs) is an innovative method in modern education, especially important for autonomous study and the sharing of global excellent education resources. However, it is not easy to implement the teaching process according to the specific characters of students by MOOCs because the number of participants is huge and the teacher cannot identify the characters of students through a face to face interaction. As a new subject combined with different areas, such as economics, sociology, environment, and even engineering, the education of sustainability-related courses requires elaborate consideration of individualized teaching for students from diverse backgrounds and with different learning styles. Although the major MOOC platforms or learning management systems (LMSs) have tried lots of efforts in the design of course system and the contents of the courses for sustainability education, the achievements are still unsatisfied, at least the issue of how to effectively take into account the individual characteristics of participants remains unsolved. A hybrid Neural Network (NN) model is proposed in this paper which integrates a Convolutional Neural Networks (CNN) and with a Gated Recurrent Unit (GRU) based Recurrent Neural Networks (RNN) in an effort to detect individual learning style dynamically. The model was trained by learners' behavior data and applied to predicting their learning styles. With identified learning style for each learner, the power of MOOC platform can be greatly enhanced by being able to offer the capabilities of recommending specific learning path and the relevant contents individually according to their characters. The efficiency of learning can thus be significantly improved. The proposed model was applied to the online study of sustainability-related course based on a MOOC platform with more than 9,400,000 learners. The results revealed that the learners could effectively increase their learning efficiency and quality for the courses when the learning styles are identified, and proper recommendations are made by using our method.

show abstract

Section: Intelligent Analysis Processmentioning

confidence: 99%

Enhancing the Efficiency of Massive Online Learning by Integrating Intelligent Analysis into MOOCs with an Application to Education of Sustainability

Zhou

2018

Sustainability

View full text Add to dashboard Cite

show abstract

“…It is worth noting that the recent progress in deep learning, especially the combination of convolution neural network (CNN) and recurrent neural network (RNN), has been shown to outperform most of the traditional approaches (which utilize human‐engineered feature representation and machine learning mapping) for a number of applications, such as speech recognition, text annotation, and image tagging (Bertero & Fung, ; Y. Kim, ; Li & Wu, ; Shen & Lee, ; Wang et al, ). However, the price for the increased predictive accuracy is the decreased interpretability of the feature representation used in deep learning methods.…”

mentioning

confidence: 99%

CPS‐Rater: Automated Sequential Annotation for Conversations in Collaborative Problem‐Solving Activities

Hao

Chen

Flor

et al. 2017

ETS Research Report Series

View full text Add to dashboard Cite

Conversations in collaborative problem‐solving activities can be used to probe the collaboration skills of the team members. Annotating the conversations into different collaboration skills by human raters is laborious and time consuming. In this report, we report our work on developing an automated annotation system, CPS‐rater, for conversational data from collaborative activities. The linear chain conditional random field method is used to model the sequential dependencies between the turns of the conversations, and the resulting automated annotation system outperforms those systems that do not model the sequential dependency.

show abstract

“…Bo Wang et al [19], proposed a dynamic label propagation (DLP), which improves multi-label classification using semi-supervised learning. Jiang Wang et al [10], proposed a combine CNN-RNN framework for multi-label classification for images. Advantages of CNN and RNN are use for joint image or label co-occurrence embedding.…”

Section: Related Workmentioning

confidence: 99%

A Survey on Multi-label Classification for Images

Devkar¹,

Shiravale²

2017

IJCA

View full text Add to dashboard Cite

The area of an image multi-label classification is increase continuously in last few years, in machine learning and computer vision. Multi-label classification has attracted significant attention from researchers and has been applied to an image annotation. In multi-label classification, each instance is assigned to multiple classes; it is a common problem in data analysis. In this paper, represent general survey on the research work is going on in the field of multilabel classification. Finally, paper is concluded towards challenges in multi-label classification for images for future research.

show abstract

CNN-RNN: A Unified Framework for Multi-label Image Classification

Cited by 1,049 publications

References 37 publications

Enhancing the Efficiency of Massive Online Learning by Integrating Intelligent Analysis into MOOCs with an Application to Education of Sustainability

Enhancing the Efficiency of Massive Online Learning by Integrating Intelligent Analysis into MOOCs with an Application to Education of Sustainability

CPS‐Rater: Automated Sequential Annotation for Conversations in Collaborative Problem‐Solving Activities

A Survey on Multi-label Classification for Images

Contact Info

Product

Resources

About