The rapid development of large language models (LLMs) has prompted researchers to explore the potential applications, especially for human interaction scenarios.Among these, facilitating meaningful and efficient communication stands out as a critical area, which is especially relevant in elder care. Meanwhile The increasing ratio of elder population highlights the urgent need for personalized care for elders. In this paper, we propose a multi-LLM approach to combine the strengths of multiple LLMs, where LLMs generate complementary answers to the same question, and the final answer is selected based on the combined relevance scores. To assist the answer selection, we provide a comprehensive evaluation of the current state-of-the-art LLMs on elderly care, incorporating real-world feedback from 30 elderly participants on various types of questions. We summarize LLMs’ strengths and weaknesses facing distinct elderly care scenarios, and highlight potential challenges and opportunities for future research.

Pre-trained language models are trained on large-scale unsupervised data, and they can fine-tune the model only on small-scale labeled datasets, and achieve good results. Multilingual pre-trained language models can be trained on multiple languages, and the model can understand multiple languages at the same time. At present, the search on pre-trained models mainly focuses on rich resources, while there is relatively little research on low-resource languages such as minority languages, and the public multilingual pre-trained language model can not work well for minority languages. Therefore, this paper constructs a multilingual pre-trained model named MiLMo that performs better on minority language tasks, including Mongolian, Tibetan, Uyghur, Kazakh and Korean. To solve the problem of scarcity of datasets on minority languages and verify the effectiveness of the MiLMo model, this paper constructs a minority multilingual text classification dataset named MiTC, and trains a word2vec model for each language. By comparing the word2vec model and the pre-trained model in the text classification task, this paper provides an optimal scheme for the downstream task research of minority languages. The final experimental results show that the performance of the pre-trained model is better than the word2vec model, and it has achieved the best results in minority multilingual text classification. The multilingual pre-trained model MiLMo, multilingual word2vec model and multilingual text classification dataset MiTC are published on https://milmo.cmli-nlp.com/.

We propose a simple yet effective technique that significantly improves the performance of the current state-of-the-art background matting model without compromising its original speed. We achieve this by carefully exciting the proper neural activations using an excitation map in the training phase and performing recursive inference in the testing phase. To avoid being over-reliant on perfect excitations, we follow the idea of curriculum learning to divide the training phase into three easy-to-hard stages and gradually shift the excitation map from GT alpha matte to pseudo GT alpha matte. In the testing phase, we propose a recursive inference mechanism that uses the output alpha matte as the excitation map to further refine the output alpha matte. Our method is a simple plug-in for arbitrary matting models. Compared with the original ones, the enhanced models alleviate the problem of performance degradation with complex background and thus boosts the matting accuracy.

The pre-trained language model is trained on large-scale unlabeled text and can achieve state-of-the-art results in many different downstream tasks. However, the current pre-trained language model is mainly concentrated in the Chinese and English fields. For low resource language such as Tibetan, there is lack of a monolingual pre-trained model. To promote the development of Tibetan natural language processing tasks, this paper collects the large-scale training data from Tibetan websites and constructs a vocabulary that can cover 99.95% of the words in the corpus by using Sentencepiece. Then, we train the Tibetan monolingual pre-trained language model named TiBERT on the data and vocabulary. Finally, we apply TiBERT to the downstream tasks of text classification and question generation, and compare it with classic models and multilingual pre-trained models, the experimental results show that TiBERT can achieve the best performance. Our model is published in http://tibert.cmli-nlp.con

Delay-sensitive multimedia streaming applications require their data to be delivered before a deadline to be useful. The data transmitted by these applications can usually be partitioned into blocks with different priorities, assigned based on the impact of a block on the Quality of Experience (QoE) if it misses its delivery deadline. Meet their deadline requirements is challenging due to the dynamics of the network and these applications' high demand on network resources. To encourage the research community to address this challenge, we organize the "Meet Deadline Requirements" Grand Challenge at ACM Multimedia 2021. This grand challenge provides a simulation platform onto which the participants can implement their block scheduler and bandwidth estimator and then benchmark against each other using a common set of application traces and network traces.

Underwater image enhancement algorithms improve image quality and indirectly enhance underwater visibility. Although many underwater image enhancement neural networks have been proposed, they require large amounts of data. To reduce the amount of data required while providing better image enhancement, this study proposes an underwater image colour transfer generative adversarial network (UCT‐GAN). The authors first design a non‐linear mapping function to generate colour cast images according to original images. Then, the authors utilise these image pairs (i.e. colour cast images and corresponding original images) to guide the UCT‐GAN in learning the inverse function of the designed non‐linear mapping function. Finally, colour cast images are restored via the inverse function. A data augmentation method based on Poisson fusion and block combination is also proposed to overcome the problem of requiring a large amount of training data. Moreover, the authors extend UCT‐GAN into a multi‐class colour transfer network to achieve an array of underwater image enhancements. Experimental results indicate that the proposed UCT‐GAN can more effectively resolve underwater image colour cast compared to existing algorithms.