Automatic real personality recognition (RPR) aims to evaluate human real personality traits from their expressive behaviours. However, most existing solutions generally act as external observers to infer observers' personality impressions based on target individuals' expressive behaviours, which significantly deviate from their real personalities and consistently lead to inferior recognition performance. Inspired by the association between real personality and human internal cognition underlying the generation of expressive behaviours, we propose a novel RPR approach that efficiently simulates personalised internal cognition from external short audio-visual behaviours expressed by target individual. The simulated personalised cognition, represented as a set of network weights that enforce the personalised network to reproduce the individual-specific facial reactions, is further encoded as a graph containing two-dimensional node and edge feature matrices, with a novel 2D Graph Neural Network (2D-GNN) proposed for inferring real personality traits from it. To simulate real personality-related cognition, an end-to-end (E2E) strategy is designed to jointly train our cognition simulation, 2D graph construction, and personality recognition modules. Experiments show our approach’s effectiveness in capturing real personality traits with superior computational efficiency.

Amid recent advances for multivariate time series forecasting, self-supervised learning has emerged as a promising paradigm for deriving transferable knowledge from multi-domain data. Despite its effectiveness, existing approaches exhibit two critical limitations: (1) Underestimating the significance of multivariate dependencies in learning generalizable representations and (2) Failing to reconcile the complementary strengths of autoregressive and one-shot generative paradigms. In this work, we propose TimeCAP, a novel channel-aware pre-training framework that internalizes latent causal relationships among variables inherent in multi-domain data, and effectively transfers the acquired knowledge to downstream applications. Technically, we present a flexible channel-grouping learning approach, complemented by an adaptive meta-routing mechanism, enabling TimeCAP to parallel recognize intra-group local patterns while maintaining global coherence. Intra- and inter-group multivariate dependencies are captured through the self- and cross-attention with channel-aware mask, which strictly confine interactions among time-aligned, fine-grained multivariate tokens. To seamlessly unify two advanced generative paradigms, we propose a novel dynamic dual-head decoding and optimization strategy, empowering TimeCAP to leverage critical dependencies in the output series while avoiding cumulative errors over time. In the few-shot evaluation, TimeCAP achieves average MSE and MAE reductions of 11.8% and 6% over leading baselines, while also outperforming state-of-the-art models in full-shot and zero-shot settings by large margins.

In dyadic human-human interactions, individuals may express multiple different facial reactions in response to the same/similar behaviours expressed by their conversational partners depending on their personalised behaviour patterns. As a result, frequently-employed reconstruction loss-based strategies lead the training of previous automatic facial reaction generation (FRG) models to not only suffer from the 'one-to-many mapping' problem, but also fail to comprehensively consider the quality of the generated facial reactions. Besides, none of them considered such personalised behaviour patterns in generating facial reactions. In this paper, we propose the first adversarial FRG model training strategy which jointly learns appropriateness and realism discriminators to provide comprehensive task-specific supervision for training the target facial reaction generators, and reformulates the 'one-to-many (facial reactions) mapping' training problem as a 'one-to-one (distribution) mapping' training task, i.e., the FRG model is trained to output a distribution representing multiple appropriate/plausible facial reaction from each input human behaviour. In addition, our approach also serves as the first offline FRG approach that considers personalised behaviour patterns in generating of target individuals' facial reactions. Experiments show that our PerReactor not only largely outperformed all existing offline solutions for generating more appropriate, diverse and realistic facial reactions, but also is the first approach that can effectively generate personalised appropriate facial reactions.

In dyadic interactions, a broad spectrum of human facial reactions might be appropriate for responding to each human speaker behaviour. Following the successful organisation of the REACT 2023 and REACT 2024 challenges, we are proposing the REACT 2025 challenge encouraging the development and benchmarking of Machine Learning (ML) models that can be used to generate multiple appropriate, diverse, realistic and synchronised human-style facial reactions expressed by human listeners in response to an input stimulus (i.e., audio-visual behaviours expressed by their corresponding speakers). As a key of the challenge, we provide challenge participants with the first natural and large-scale multi-modal Multiple Appropriate Facial Reaction Generation (MAFRG) dataset (called MARS) recording 136 human-human dyadic interactions containing a total of 2856 interaction sessions covering five different topics. In addition, this paper also presents the challenge guidelines and the performance of our baselines on the two proposed sub-challenges: Offline MAFRG and Online MAFRG, respectively. The challenge baseline code is publicly available at https://github.com/reactmultimodalchallenge/baseline_react2025

In dyadic interactions, humans communicate their intentions and state of mind using verbal and non-verbal cues, where multiple different facial reactions might be appropriate in response to a specific speaker behaviour. Then, how to develop a machine learning (ML) model that can automatically generate multiple appropriate, diverse, realistic and synchronised human facial reactions from an previously unseen speaker behaviour is a challenging task. Following the successful organisation of the first REACT challenge (REACT 2023), this edition of the challenge (REACT 2024) employs a subset used by the previous challenge, which contains segmented 30-secs dyadic interaction clips originally recorded as part of the NOXI and RECOLA datasets, encouraging participants to develop and benchmark Machine Learning (ML) models that can generate multiple appropriate facial reactions (including facial image sequences and their attributes) given an input conversational partner's stimulus under various dyadic video conference scenarios. This paper presents: (i) the guidelines of the REACT 2024 challenge; (ii) the dataset utilized in the challenge; and (iii) the performance of the baseline systems on the two proposed sub-challenges: Offline Multiple Appropriate Facial Reaction Generation and Online Multiple Appropriate Facial Reaction Generation, respectively. The challenge baseline code is publicly available at https://github.com/reactmultimodalchallenge/baseline_react2024.

Human facial reactions play crucial roles in dyadic human-human interactions, where individuals (i.e., listeners) with varying cognitive process styles may display different but appropriate facial reactions in response to an identical behaviour expressed by their conversational partners. While several existing facial reaction generation approaches are capable of generating multiple appropriate facial reactions (AFRs) in response to each given human behaviour, they fail to take human's personalised cognitive process in AFRs generation. In this paper, we propose the first online personalised multiple appropriate facial reaction generation (MAFRG) approach which learns a unique personalised cognitive style from the target human listener's previous facial behaviours and represents it as a set of network weight shifts. These personalised weight shifts are then applied to edit the weights of a pre-trained generic MAFRG model, allowing the obtained personalised model to naturally mimic the target human listener's cognitive process in its reasoning for multiple AFRs generations. Experimental results show that our approach not only largely outperformed all existing approaches in generating more appropriate and diverse generic AFRs, but also serves as the first reliable personalised MAFRG solution. Our code is made available at https://github.com/xk0720/PerFRDiff.

Deep learning has become a primary choice in medical image analysis due to its powerful representation capability. However, most existing deep learning models designed for medical image classification can only perform well on a specific disease. The performance drops dramatically when it comes to other diseases. Generalizability remains a challenging problem. In this paper, we propose an evolutionary attention-based network (EDCA-Net), which is an effective and robust network for medical image classification tasks. To extract task-related features from a given medical dataset, we first propose the densely connected attentional network (DCA-Net) where feature maps are automatically channel-wise weighted, and the dense connectivity pattern is introduced to improve the efficiency of information flow. To improve the model capability and generalizability, we introduce two types of evolution: intra- and inter-evolution. The intra-evolution optimizes the weights of DCA-Net, while the inter-evolution allows two instances of DCA-Net to exchange training experience during training. The evolutionary DCA-Net is referred to as EDCA-Net. The EDCA-Net is evaluated on four publicly accessible medical datasets of different diseases. Experiments showed that the EDCA-Net outperforms the state-of-the-art methods on three datasets and achieves comparable performance on the last dataset, demonstrating good generalizability for medical image classification.

Inspired by the biological evolution, this paper proposes an evolutionary synthesis mechanism to automatically evolve DenseNet towards high sparsity and efficiency for medical image classification. Unlike traditional automatic design methods, this mechanism generates a sparser offspring in each generation based on its previous trained ancestor. Concretely, we use a synaptic model to mimic biological evolution in the asexual reproduction. Each generation’s knowledge is passed down to its descendant, and an environmental constraint limits the size of the descendant evolutionary DenseNet, moving the evolution process towards high sparsity. Additionally, to address the limitation of ensemble learning that requires multiple base networks to make decisions, we propose an evolution-based ensemble learning mechanism. It utilises the evolutionary synthesis scheme to generate highly sparse descendant networks, which can be used as base networks to perform ensemble learning in inference. This is specially useful in the extreme case when there is only a single network. Finally, we propose the MEEDNets (Medical Image Classification via Ensemble Bio-inspired Evolutionary DenseNets) model which consists of multiple evolutionary DenseNet-121s synthesised in the evolution process. Experimental results show that our bio-inspired evolutionary DenseNets are able to drop less important structures and compensate for the increasingly sparse architecture. In addition, our proposed MEEDNets model outperforms the state-of-the-art methods on two publicly accessible medical image datasets. All source code of this study is available at https://github.com/hengdezhu/MEEDNets.

Deep ensemble learning, where we combine knowledge learned from multiple individual neural networks, has been widely adopted to improve the performance of neural networks in deep learning. This field can be encompassed by committee learning, which includes the construction of neural network cascades. This study focuses on the high-dimensional low-sample-size (HDLS) domain and introduces multiple instance ensemble (MIE) as a novel stacking method for ensembles and cascades. In this study, our proposed approach reformulates the ensemble learning process as a multiple-instance learning problem. We utilise the multiple-instance learning solution of pooling operations to associate feature representations of base neural networks into joint representations as a method of stacking. This study explores various attention mechanisms and proposes two novel committee learning strategies with MIE. In addition, we utilise the capability of MIE to generate pseudo-base neural networks to provide a proof-of-concept for a "growing" neural network cascade that is unbounded by the number of base neural networks. We have shown that our approach provides (1) a class of alternative ensemble methods that performs comparably with various stacking ensemble methods and (2) a novel method for the generation of high-performing "growing" cascades. The approach has also been verified across multiple HDLS datasets, achieving high performance for binary classification tasks in the low-sample size regime.