Image captioning generates descriptions in a natural language for a given image. Due to its great potential for a wide range of applications, many deep learning based-methods have been proposed. The co-occurrence of words such as mouse and keyboard, constitutes commonsense knowledge, which is referred to as consensus. However, it is challenging to consider commonsense knowledge in producing captions that have rich, natural, and meaningful semantics. In this paper, a Vision-enhanced and Consensus-aware Transformer (VCT) is proposed to exploit both visual information and consensus knowledge for image captioning with three key components: a vision-enhanced encoder, consensus-aware knowledge representation generator, and consensus-aware decoder. The vision-enhanced encoder extends the vanilla self-attention module with a memory-based attention module and a visual perception module for learning better visual representation of an image. Specifically, the relationships between regions in an image and the image’s global context are leveraged with scene memory in the memory-based attention module. The visual perception module further enhances the correlation among neighboring tokens in both the spatial and channel-wise dimensions. To learn consensus-aware representations, a word correlation graph is constructed by computing the statistical co-occurrence between semantic concepts. Then consensus knowledge can be acquired using a graph convolutional network in the consensus-aware knowledge representation generator. Finally, such consensus knowledge is integrated into the consensus-aware decoder through consensus memory and a knowledge-based control module to produce a caption. Experimental results on two popular benchmark datasets (MSCOCO and Flickr30k) demonstrate that our proposed model achieves state-of-the-art performance. Extensive ablation studies also validate the effectiveness of each component.

Convolutional neural networks (CNNs) have shown an effective way to learn spatiotemporal representation for action recognition in videos. However, most traditional action recognition algorithms do not employ the attention mechanism to focus on essential parts of video frames that are relevant to the action. In this article, we propose a novel global and local knowledge-aware attention network to address this challenge for action recognition. The proposed network incorporates two types of attention mechanism called statistic-based attention (SA) and learning-based attention (LA) to attach higher importance to the crucial elements in each video frame. As global pooling (GP) models capture global information, while attention models focus on the significant details to make full use of their implicit complementary advantages, our network adopts a three-stream architecture, including two attention streams and a GP stream. Each attention stream employs a fusion layer to combine global and local information and produces composite features. Furthermore, global-attention (GA) regularization is proposed to guide two attention streams to better model dynamics of composite features with the reference to the global information. Fusion at the softmax layer is adopted to make better use of the implicit complementary advantages between SA, LA, and GP streams and get the final comprehensive predictions. The proposed network is trained in an end-to-end fashion and learns efficient video-level features both spatially and temporally. Extensive experiments are conducted on three challenging benchmarks, Kinetics, HMDB51, and UCF101, and experimental results demonstrate that the proposed network outperforms most state-of-the-art methods.

Capsule neural network is a new and popular technique in deep learning. However, the traditional capsule neural network does not extract features sufficiently before the dynamic routing between capsules. In this study, one double enhanced capsule neural network (E2‐Capsnet) that uses AU‐aware attention for facial expression recognition (FER) is proposed. The E2‐Capsnet takes advantage of dynamic routing between capsules and has two enhancement modules which are beneficial to FER. The first enhancement module is the convolutional neural network with AU‐aware attention, which can focus on the active areas of the expression. The second enhancement module is the capsule neural network with multiple convolutional layers, which enhances the ability of the feature representation. Finally, the squashing function is used to classify the facial expression. The authors demonstrate the effectiveness of E2‐Capsnet on the two public benchmark datasets, RAF‐DB and EmotioNet. The experimental results show that their E2‐Capsnet is superior to the state‐of‐the‐art methods. The code is available at https://github.com/ShanCao18/E2‐Capsnet .

The feature pyramid has been widely used in many visual tasks, such as fine-grained image classification, instance segmentation, and object detection, and had been achieving promising performance. Although many algorithms exploit different-level features to construct the feature pyramid, they usually treat them equally and do not make an in-depth investigation on the inherent complementary advantages of different-level features. In this article, to learn a pyramid feature with the robust representational ability for action recognition, we propose a novel collaborative and multilevel feature selection network (FSNet) that applies feature selection and aggregation on multilevel features according to action context. Unlike previous works that learn the pattern of frame appearance by enhancing spatial encoding, the proposed network consists of the position selection module and channel selection module that can adaptively aggregate multilevel features into a new informative feature from both position and channel dimensions. The position selection module integrates the vectors at the same spatial location across multilevel features with positionwise attention. Similarly, the channel selection module selectively aggregates the channel maps at the same channel location across multilevel features with channelwise attention. Positionwise features with different receptive fields and channelwise features with different pattern-specific responses are emphasized respectively depending on their correlations to actions, which are fused as a new informative feature for action recognition. The proposed FSNet can be inserted into different backbone networks flexibly, and extensive experiments are conducted on three benchmark action datasets, Kinetics, UCF101, and HMDB51. Experimental results show that FSNet is practical and can be collaboratively trained to boost the representational ability of existing networks. FSNet achieves superior performance against most top-tier models on Kinetics and all models on UCF101 and HMDB51.