A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network Metadata
This work addresses image annotation problems for social media users by providing a more robust method, though it is incremental as it builds on existing CNN-RNN and metadata integration approaches.
The paper tackles the challenge of annotating unclear or non-common images by blending visual features and social network metadata to improve accuracy, showing that their CNN-RNN framework outperforms state-of-the-art methods on the NUS-WIDE dataset and reduces sensory and semantic gaps.
Images represent a commonly used form of visual communication among people. Nevertheless, image classification may be a challenging task when dealing with unclear or non-common images needing more context to be correctly annotated. Metadata accompanying images on social-media represent an ideal source of additional information for retrieving proper neighborhoods easing image annotation task. To this end, we blend visual features extracted from neighbors and their metadata to jointly leverage context and visual cues. Our models use multiple semantic embeddings to achieve the dual objective of being robust to vocabulary changes between train and test sets and decoupling the architecture from the low-level metadata representation. Convolutional and recurrent neural networks (CNNs-RNNs) are jointly adopted to infer similarity among neighbors and query images. We perform comprehensive experiments on the NUS-WIDE dataset showing that our models outperform state-of-the-art architectures based on images and metadata, and decrease both sensory and semantic gaps to better annotate images.