Image captioning is one of the primary goals in computer vision which aims to automatically generate natural descriptions for images. Intuitively, human visual system can notice some stimulating regions at first glance, and then volitionally focus on interesting objects within the region. For example, to generate a free-form sentence about “boy-catch-baseball”, the visual region involving “boy” and “baseball” could be first attended and then guide the salient object discovery for the word-by-word generation. Till now, previous captioning works mainly rely on the object-wise modeling and ignore the rich regional patterns. To mitigate the drawback, this paper proposes the region-aware interaction learning method, which aims to explicitly capture the semantic correlations in the region and object dimensions for the word inference. First, given an image, we extract a set of regions which contain diverse objects and their relations. Second, we present the spatial-GCN interaction refining structure which can establish the connection between regions and objects to effectively capture contextual information. Third, we design the dual-attention interaction inference procedure, which enables attention to be calculated in region and object dimensions jointly for the word generation. Specifically, the guidance mechanism is proposed to selectively emphasize semantic inter-dependencies from region to object attentions. Extensive experiments on the MSCOCO dataset demonstrate the superiority of the proposed method. Additional ablation studies and visualization further validate its effectiveness.

Image captioning is one of the most challenging tasks in AI because it requires an understanding of both complex visuals and natural language. Because image captioning is essentially a sequential prediction task, recent advances in image captioning have used reinforcement learning (RL) to better explore the dynamics of word-by-word generation. However, the existing RL-based image captioning methods rely primarily on a single policy network and reward function–an approach that is not well matched to the multi-level (word and sentence) and multi-modal (vision and language) nature of the task. To solve this problem, we propose a novel multi-level policy and reward RL framework for image captioning that can be easily integrated with RNN-based captioning models, language metrics, or visual-semantic functions for optimization. Specifically, the proposed framework includes two modules: 1) a multi-level policy network that jointly updates the word- and sentence-level policies for word generation; and 2) a multi-level reward function that collaboratively leverages both a vision-language reward and a language-language reward to guide the policy. Furthermore, we propose a guidance term to bridge the policy and the reward for RL optimization. The extensive experiments on the MSCOCO and Flickr30k datasets and the analyses show that the proposed framework achieves competitive performances on a variety of evaluation metrics. In addition, we conduct ablation studies on multiple variants of the proposed framework and explore several representative image captioning models and metrics for the word-level policy network and the language-language reward function to evaluate the generalization ability of the proposed framework.

Recent progress in using Recurrent Neural Networks (RNNs) for video description has attracted an increasing interest, due to its capability to encode a sequence of frames for caption generation. While existing methods have studied various features (e.g., CNN, 3D CNN, and semantic attributes) for visual encoding, the representation and fusion of heterogeneous information from multi-modal spaces have not fully explored. Consider that the different modalities are often asynchronous, frame-level multi-modal fusion (e.g., concatenation, linear fusion) will negatively influence each modality. In this paper, we propose a Dual-Stream RNN (DS-RNN) framework to jointly discover and integrate the hidden states of both visual and semantic streams for video caption generation. First, an encoding RNN is used for each stream to flexibly exploit the hidden states of respective modality. Specifically, we proposed an Attentive Multi-Grained Encoder (AMGE) module to enhance the local feature learning with global semantics feature. Then, a dualstream decoder is deployed to integrate the asynchronous yet complementary sequential hidden states from both streams for caption generation. Extensive experiments on three benchmark datasets, namely MSVD, MSR-VTT and MPII-MD, show that DS-RNN achieves competitive performance against the state-ofthe- art. Additional ablation studies were conducted on various variants of the proposed DS-RNN.

With the development of both hardware and deep neural network technologies, tremendous improvements have been achieved in the performance of automatic emotion recognition (AER) based on the video data. However, AER is still a challenging task due to subtle expression, the abstract concept of emotion, and the representation of multi-modal information. Most proposed approaches focus on the multi-modal feature learning and fusion strategy, which pay more attention to the characteristic of a single video and ignore the correlation among the videos. To explore this correlation, in this paper, we propose a novel correlation-based graph convolutional network (C-GCN) for AER, which can comprehensively consider the correlation of the intra-class and inter-class videos for feature learning and information fusion. More specififically, we introduce the graph model to represent the correlation among the videos. This correlated information can help to improve the discrimination of node features in the progress of graph convolutional network. Meanwhile, the multi-head attention mechanism is applied to predict the hidden relationship among the videos, which can strengthen the inter-class correlation to improve the performance of classifiers. The C-GCN is evaluated on the AFEW datasets and eNTERFACE’ 05 dataset. The final experimental results demonstrate the superiority of our proposed method over the state-of-the-art methods.

As an intersection of artificial intelligence and human communication analysis, Emotion Recognition in Conversation (ERC) has attracted much research attention in recent years. Existing studies, however, are limited in adequately exploiting latent relations among the constituent utterances. In this paper, we address this issue by proposing a novel approach named Latent Relation-Aware Graph Convolutional Network (LR-GCN), where both speaker dependency of the interlocutors is leveraged and latent correlations among the utterances are captured for ERC. Specifically, we first establish a graph model to incorporate the context information and speaker dependency of the conversation. Afterward, the multi-head attention mechanism is introduced to explore the latent correlations among the utterances and generate a set of all-linked graphs. Here, aiming to simultaneously exploit the original modeled speaker dependency and the explored correlation information, we introduce a dense connection layer to capture more structural information of the generated graphs. Through a multi-branch graph network, we achieve a unified representation of each utterance for final prediction. Detailed evaluations on two benchmark datasets demonstrate LR-GCN outperforms the state-of-the-art approaches.

Dialogue emotion detection is always challenging due to human subjectivity and the randomness of dialogue content. In a conversation, the emotion of each person often develops via a cumulative process, which can be influenced by many elements of uncertainty. Much commonsense knowledge influences people's emotions imperceptibly, such as experiential or habitual knowledge. In the process of conversation, this commonsense knowledge information can be used to enrich the semantic information of each utterance and improve the accuracy of emotion recognition. In this paper, we propose a growing graph model for dialogues emotion detection based on retrieval of external knowledge atlas ATOMIC from local and global respectively, which can effectively represent the dialogues as a process variable in a sequence and the correlation among utterances also can be represented by the graph model. In particular, 1) we introduce a common sense knowledge graph for linking the commonsense knowledge retrieved from external knowledge atlas ATOMIC, which can effectively add auxiliary information to improve the performance of each utterance's representation. 2) We propose a novel self-supervised learning method for extracting the latent topic of each dialogue. Based on this design, we also propose an effective optimization mechanism to make the representation (embedding) of latent topic has a better distinction for the next operation. 3) Finally, the cross-attention module is utilized to combine the utterances' features and the latent conversation topic information. The attention mechanism can effectively use topic information to supplement the representation of utterances and improve recognition performance. The model is tested on three popular datasets in dialogue emotion detection and is empirically demonstrated to outperform the state-of-the-art approaches. Meanwhile, to demonstrate the performance of our approach, we also build a long dialogue dataset. The average length of each conversation is over 50 utterances. The final experimental results also demonstrate the superior performance of our approach.