Algorithm

Discriminative model

Exploit

Computer security

Theoretical computer science

Contextual image classification

Computer science

Embedding

Graph

Pattern recognition (psychology)

Mathematics

Image (mathematics)

Multi-label classification

Mathematical analysis

Artificial intelligence

Adjacency list

Graph embedding

Generalization

Machine learning

Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi-label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our novel cross-modality attention maps are generated with the guidance of learned label embeddings. Experiments on two multi-label image classification datasets (MS-COCO and NUS-WIDE) show our method outperforms other existing state-of-the-arts. In addition, we validate our method on a large multi-label video classification dataset (YouTube-8M Segments) and the evaluation results demonstrate the generalization capability of our method.

Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification