Text multi-label learning method based on label-aware attention and semantic dependency

TL;DR: A hybrid model based on CNN and LSTM has been proposed to automatically classify all written social sharing content, both positive and negative, into defined target tags, and the obtained performance results show that the proposed method can be applied to different multilabel text analysis problems.

TL;DR: A novel Multi-Label Text Classification model, LAHA, integrates Label Attention and Historical Attention to address drawbacks of traditional DL models, including data imbalance and fine-grained matching issues, outperforming state-of-the-art baseline models on four benchmark datasets.

TL;DR: This paper proposes Knowledge Graph Convolutional Networks (KGCN), an end-to-end framework that captures inter-item relatedness effectively by mining their associated attributes on the KG.

TL;DR: Zhang et al. as mentioned in this paper proposed an attention enhanced graph convolutional LSTM network (AGC-LSTM) for human action recognition from skeleton data, which can not only capture discriminative features in spatial configuration and temporal dynamics but also explore the co-occurrence relationship between spatial and temporal domains.

TL;DR: This paper presents the first attempt at applying deep learning to XMTC, with a family of new Convolutional Neural Network models which are tailored for multi-label classification in particular.

TL;DR: This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos with the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being differentiable end-to-end.