Theory of Mind (ToM) is the ability to attribute mental states to others, an important component of human cognition. At present, there has been growing interest in the artificial intelligence (AI) with cognitive abilities, for example in healthcare and the motoring industry. Research indicates that infants exhibit early signs in cognitive and social understanding, including some basic abilities related to beliefs, desires, and intentions (BDIs). Thus, the ability to attribute BDIs to others is also crucial for the development of machine ToM. In this article, we review recent progress in machine ToM on BDIs. And we shall introduce the experiments, datasets, and methods of machine ToM on these three aspects, summarize the development of different tasks and datasets in recent years, and compare well-behaved models in aspects of advantages, limitations, and applicable conditions, hoping that this study can guide researchers to quickly keep up with latest trend in this field. Unlike other domains with a specific task and resolution framework, machine ToM lacks a unified instruction and a series of standard evaluation tasks, which make it difficult to formally compare the proposed models. And the existing models still cannot exhibit the same ToM reasoning ability as real humans, lack of transferability, interpretability, few-shot learning, etc. We argue that, one method to address this difficulty is now to present a standard assessment criteria and dataset, better a large-scale dataset covered multiple aspects of ToM. Besides, for developing an AI of ToM, it requires the cooperation of experts from various domains.

Referring expression comprehension aims to align natural language queries with visual scenes, which requires establishing fine-grained correspondence between vision and language. This has important applications in multi-modal reasoning systems. Existing methods typically use text-agnostic visual backbones to extract features independently without considering the specific text input. However, we argue that the extracted visual features can be inconsistent with the referring expression, which hurts multi-modal understanding. To address this, we first propose Query-modulated Refinement Network (QRNet) that leverages language guidance to guide visual feature extraction. However, it only focuses on the grounding task that can only provide coarse-grained annotations in the form of bounding box coordinates. The guidance for the visual backbone is indirect, and the inconsistent issue still exists. To this end, we further propose UniQRNet, a multi-task framework over the QRNet to learn referring expression grounding and segmentation jointly. The framework introduces a multi-task head that leverages fine-grained pixel-level supervision from the segmentation task to directly guide the intermediate layers of QRNet to learn text-consistent visual features. Besides, UniQRNet also includes a loss balance strategy that allows two types of supervision signals to cooperate and optimize the model together. We conduct the most comprehensive comparison experiment covering four major datasets, ten evaluation set and three evaluation metrics used in previous work. UniQRNet outperforms previous state-of-the-art methods by a large margin on both referring comprehensive grounding (1.8%~5.09%) and segmentation tasks (0.57%~5.56%). Ablation and analysis reveal that UniQRNet can improve the consistency of visual features with text input and can bring significant performance improvement.

Recently, multimodal sentiment analysis from social media posts has received increasing attention, as it can effectively improve single-modality-based sentiment analysis by leveraging the complementary information between text and images. Despite their success, current methods still suffer from two weaknesses: (1) the current methods for obtaining image representations do not obtain sentiment information, which leads to a significant gap between image representations and results; (2) the current methods ignore the sentiments expressed by the symbols (emoticons, emojis) in the text, but these symbols can effectively reflect the user's sentiments. To address these issues, we propose a sentimental prompt framework with visual text encoder (SPFVTE). Specifically, for the first problem, instead of using the image representation directly, we project the image representation as a prompt and utilize the prompt learning to capture sentimental information in images by learning a sentiment-specific prompt. For the second problem, considering that people get the meanings of emojis and emoticons from their graphics, we propose to render the text as an image and use a visual text encoder to capture the sentiments contained in emojis and emoticons. We have conducted experiments on three public multimodal sentiment datasets, and the experimental results show that our method can significantly and consistently outperform the state-of-the-art methods. The datasets and source code can be found at https://github.com/JinFish/SPFVTE.