Huimin Liu

Huimin Liu, Jing Gao, Daria Baran et al.

Cattle behaviour is a crucial indicator of an individual animal health, productivity and overall well-being. Video-based monitoring, combined with deep learning techniques, has become a mainstream approach in animal biometrics, and it can offer high accuracy in some behaviour recognition tasks. We present Cattle-CLIP, a multimodal deep learning framework for cattle behaviour recognition, using semantic cues to improve the performance of video-based visual feature recognition. It is adapted from the large-scale image-language model CLIP by adding a temporal integration module. To address the domain gap between web data used for the pre-trained model and real-world cattle surveillance footage, we introduce tailored data augmentation strategies and specialised text prompts. Cattle-CLIP is evaluated under both fully-supervised and few-shot learning scenarios, with a particular focus on data-scarce behaviour recognition - an important yet under-explored goal in livestock monitoring. To evaluate the proposed method, we release the CattleBehaviours6 dataset, which comprises six types of indoor behaviours: feeding, drinking, standing-self-grooming, standing-ruminating, lying-self-grooming and lying-ruminating. The dataset consists of 1905 clips collected from our John Oldacre Centre dairy farm research platform housing 200 Holstein-Friesian cows. Experiments show that Cattle-CLIP achieves 96.1% overall accuracy across six behaviours in a supervised setting, with nearly 100% recall for feeding, drinking and standing-ruminating behaviours, and demonstrates robust generalisation with limited data in few-shot scenarios, highlighting the potential of multimodal learning in agricultural and animal behaviour analysis.

Junyuan Fang, Huimin Liu, Yueqi Peng et al.

Community detection in graphs is crucial for understanding the organization of nodes into densely connected clusters. While numerous strategies have been developed to identify these clusters, the success of community detection can lead to privacy and information security concerns, as individuals may not want their personal information exposed. To address this, community deception methods have been proposed to reduce the effectiveness of detection algorithms. Nevertheless, several limitations, such as the rationality of evaluation metrics and the unnoticeability of attacks, have been ignored in current deception methods. Therefore, in this work, we first investigate the limitations of the widely used deception metric, i.e., the decrease of modularity, through empirical studies. Then, we propose a new deception metric, and combine this new metric together with the attack budget to model the unnoticeable community deception task as a multi-objective optimization problem. To further improve the deception performance, we propose two variant methods by incorporating the degree-biased and community-biased candidate node selection mechanisms. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed community deception strategies.

Yanlin Li, Hao Liu, Huimin Liu et al.

Theory of Mind (ToM) in Large Language Models (LLMs) refers to their capacity for reasoning about mental states, yet failures in this capacity often manifest as systematic implicit bias. Evaluating this bias is challenging, as conventional direct-query methods are susceptible to social desirability effects and fail to capture its subtle, multi-dimensional nature. To this end, we propose an evaluation framework that leverages the Stereotype Content Model (SCM) to reconceptualize bias as a multi-dimensional failure in ToM across Competence, Sociability, and Morality. The framework introduces two indirect tasks: the Word Association Bias Test (WABT) to assess implicit lexical associations and the Affective Attribution Test (AAT) to measure covert affective leanings, both designed to probe latent stereotypes without triggering model avoidance. Extensive experiments on 8 State-of-the-Art LLMs demonstrate our framework's capacity to reveal complex bias structures, including pervasive sociability bias, multi-dimensional divergence, and asymmetric stereotype amplification, thereby providing a more robust methodology for identifying the structural nature of implicit bias.

Junyuan Fang, Huimin Liu, Han Yang et al.

In recent years, graph neural networks (GNNs) have shown great potential in addressing various graph structure-related downstream tasks. However, recent studies have found that current GNNs are susceptible to malicious adversarial attacks. Given the inevitable presence of adversarial attacks in the real world, a variety of defense methods have been proposed to counter these attacks and enhance the robustness of GNNs. Despite the commendable performance of these defense methods, we have observed that they tend to exhibit a structural bias in terms of their defense capability on nodes with low degree (i.e., tail nodes), which is similar to the structural bias of traditional GNNs on nodes with low degree in the clean graph. Therefore, in this work, we propose a defense strategy by including hetero-homo augmented graph construction, $k$NN augmented graph construction, and multi-view node-wise attention modules to mitigate the structural bias of GNNs against adversarial attacks. Notably, the hetero-homo augmented graph consists of removing heterophilic links (i.e., links connecting nodes with dissimilar features) globally and adding homophilic links (i.e., links connecting nodes with similar features) for nodes with low degree. To further enhance the defense capability, an attention mechanism is adopted to adaptively combine the representations from the above two kinds of graph views. We conduct extensive experiments to demonstrate the defense and debiasing effect of the proposed strategy on benchmark datasets.