Hanwei Liu

Annotation ambiguity caused by the inherent subjectivity of visual judgment has always been a major challenge for Facial Expression Recognition (FER) tasks, particularly for largescale datasets from in-the-wild scenarios. A potential solution is the evaluation of relatively objective emotional distributions to help mitigate the ambiguity of subjective annotations. To this end, this paper proposes a novel Prior-based Objective Inference (POI) network. This network employs prior knowledge to derive a more objective and varied emotional distribution and tackles the issue of subjective annotation ambiguity through dynamic knowledge transfer. POI comprises two key networks: Firstly, the Prior Inference Network (PIN) utilizes the prior knowledge of AUs and emotions to capture intricate motion details. To reduce over-reliance on priors and facilitate objective emotional inference, PIN aggregates inferential knowledge from various key facial subregions, encouraging mutual learning. Secondly, the Target Recognition Network (TRN) integrates subjective emotion annotations and objective inference soft labels provided by the PIN, fostering an understanding of inherent facial expression diversity, thus resolving annotation ambiguity. Moreover, we introduce an uncertainty estimation module to quantify and balance facial expression confidence. This module enables a flexible approach to dealing with the uncertainties of subjective annotations. Extensive experiments show that POI exhibits competitive performance on both synthetic noisy datasets and multiple real-world datasets. All codes and training logs will be publicly available at https://github.com/liuhw01/POI.

Facial Expression Analysis remains a challenging task due to unexpected task-irrelevant noise, such as identity, head pose, and background. To address this issue, this paper proposes a novel framework, called Norface, that is unified for both Action Unit (AU) analysis and Facial Emotion Recognition (FER) tasks. Norface consists of a normalization network and a classification network. First, the carefully designed normalization network struggles to directly remove the above task-irrelevant noise, by maintaining facial expression consistency but normalizing all original images to a common identity with consistent pose, and background. Then, these additional normalized images are fed into the classification network. Due to consistent identity and other factors (e.g. head pose, background, etc.), the normalized images enable the classification network to extract useful expression information more effectively. Additionally, the classification network incorporates a Mixture of Experts to refine the latent representation, including handling the input of facial representations and the output of multiple (AU or emotion) labels. Extensive experiments validate the carefully designed framework with the insight of identity normalization. The proposed method outperforms existing SOTA methods in multiple facial expression analysis tasks, including AU detection, AU intensity estimation, and FER tasks, as well as their cross-dataset tasks. For the normalized datasets and code please visit {https://norface-fea.github.io/}.

With the introduction of ChatGPT, the public's perception of AI-generated content (AIGC) has begun to reshape. Artificial intelligence has significantly reduced the barrier to entry for non-professionals in creative endeavors, enhancing the efficiency of content creation. Recent advancements have seen significant improvements in the quality of symbolic music generation, which is enabled by the use of modern generative algorithms to extract patterns implicit in a piece of music based on rule constraints or a musical corpus. Nevertheless, existing literature reviews tend to present a conventional and conservative perspective on future development trajectories, with a notable absence of thorough benchmarking of generative models. This paper provides a survey and analysis of recent intelligent music generation techniques, outlining their respective characteristics and discussing existing methods for evaluation. Additionally, the paper compares the different characteristics of music generation techniques in the East and West as well as analysing the field's development prospects.

Domain adaptation has driven the progress of Facial Expression Recognition (FER). Existing cross-domain FER methods focus only on the domain alignment of a single source domain to the target domain, ignoring the importance of multisource domains that contain richer knowledge. However, Cross-Multidomain FER (CMFER)needs to combat the domain conflicts caused by the uncertainty of intradomain annotations and the inconsistency of interdomain distributions. To this end, this paper proposes a Domain-Uncertain Mutual Learning (DUML) method to deal with the more challenging CMFER problem. Specifically, we consider a domain-specific global perspective for domain-invariance representation and domain fusion for facial generic detail representation to mitigate cross-domain distribution differences. Further, we develop Intra-Domain Uncertainty (Intra-DU) and Inter-Domain Uncertainty (Inter-DU) to combat the large dataset shifts caused by annotation uncertainty. Finally, extensive experimental results on multiple benchmark across multidomain FER datasets demonstrate the remarkable effectiveness of DUML against CMFER uncertainty. All codes and training logs are publicly available at https://github.com/liuhw01/DUML.

Studies have shown that illuminance and correlated colour temperature (CCT) are strongly correlated with body responses such as circadian rhythm, alertness, and mood. It is worth noting that these responses show a complex and variable coupling, which needs to be solved using accurate mathematical models for the regulation of indoor light parameters. Therefore, in this study, by weighing the evaluations of visual comfort, alertness, valence, and arousal of mood, a multi-objective optimisation mathematical model was developed with constraints conducive to the healthy rhythm. The problem was solved with the multi-objective evolutionary algorithm based on the decomposition differential evolution (MOEA/D-DE) algorithm. Taking educational space as the analysis goal, a dual-parameter setting strategy for illuminance and CCT covering four modes was proposed: focused learning, comfortable learning, soothing learning, and resting state, which could provide a scientific basis for the regulation of the lighting control system. The alertness during class time reached 3.01 compared to 2.34 during break time, showing a good light facilitation effect. The proposed mathematical model and analysis method also have the potential for application in the lighting design and control in other spaces to meet the era of intelligent, highly flexible, and sustainable buildings.

In order to promote the development and construction of smart cities, the massive equipment requirements of sensing terminals increased the pressure on urban site resource allocation. The light pole is suitable for carrying various urban functional equipment to form a smart street lighting system, which can provide rich site resources for the large-scale construction of urban functional facilities such as 5G micro base stations. However, the selection and combination of equipment mounted in the smart street lighting system only focus on the functional superposition at the physical level, without considering the relevance of each subsystem in practical application scenarios. Therefore, this study proposed a 5G micro base station location model based on a smart street lighting system. The correlation and cooperativity between 5G micro base stations and mounted devices were fully considered, and a universal system-level location selection index was developed to realize rational utilization of urban space site resources and intelligent linkage between subsystems. The results showed that the model is significantly effective for functional areas with different road network characteristics and provides practical, robust, effective, and accurate help for similar location selection problems.

In complex real-world situations, problems such as illumination changes, facial occlusion, and variant poses make facial expression recognition (FER) a challenging task. To solve the robustness problem, this paper proposes an adaptive multilayer perceptual attention network (AMP-Net) that is inspired by the facial attributes and the facial perception mechanism of the human visual system. AMP-Net extracts global, local, and salient facial emotional features with different fine-grained features to learn the underlying diversity and key information of facial emotions. Different from existing methods, AMP-Net can adaptively guide the network to focus on multiple finer and distinguishable local patches with robustness to occlusion and variant poses, improving the effectiveness of learning potential facial diversity information. In addition, the proposed global perception module can learn different receptive field features in the global perception domain, and AMP-Net also supplements salient facial region features with high emotion correlation based on prior knowledge to capture key texture details and avoid important information loss. Many experiments show that AMP-Net achieves good generalizability and state-of-the-art results on several real-world datasets, including RAF-DB, AffectNet-7, AffectNet-8, SFEW 2.0, FER-2013, and FED-RO, with accuracies of 89.25%, 64.54%, 61.74%, 61.17%, 74.48%, and 71.75%, respectively. All codes and training logs are publicly available at https://github.com/liuhw01/AMP-Net .