Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification
This addresses the problem of improving accuracy in multi-label classification for computer vision applications, though it appears incremental as it builds on existing attention and graph-based techniques.
The paper tackles multi-label image and video classification by proposing a method using cross-modality attention with semantic graph embedding to capture label dependencies and locate discriminative features, achieving state-of-the-art results on datasets like MS-COCO, NUS-WIDE, and YouTube-8M Segments.
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.