Human action recognition based on the depth maps is an important yet challenging task. In this paper, a new framework based on the 3D motion trail model (3DMTM) and Pyramid Histograms of Oriented Gradient (PHOG) is proposed to recognize human actions from sequences of depth maps. Specifically, a discriminative descriptor called 3DMTM-PHOG is proposed for depth-based human action recognition. The 3DMTM is generated through the entire depth video sequence to encode additional motion information from three projected orthogonal planes. By adding pyramid representation, Histograms of Oriented Gradient (HOG) descriptor is extended to PHOG which can well characterize local shapes at different spatial grid sizes for action recognition. PHOG is then computed from the 3DMTM as the 3DMTM-PHOG descriptor for the representation of an action. The proposed approach based on 3DMTM-PHOG descriptor is evaluated on MSR Action3D dataset captured by depth cameras. Experimental results show that the proposed approach outperforms the state-of-the-art methods and demonstrate the effectiveness and robustness of the proposed 3DMTM-PHOG descriptor.

In this paper an effective method is presented to recognize human gestures from sequences of depth images. Specifically, we propose a three dimensional motion trail model (3D-MTM) to explicitly represent the dynamics and statics of gestures in 3D space. In 2D space, the motion trail model (2D-MTM) consists of both motion information and static posture information over the gesture sequence along the xoy-plane. Considering gestures are performed in 3D space, depth images are projected onto two other planes to encode additional gesture information. The 2D-MTM is then extensively combined with complementary motion information from additional two planes to generate the 3D-MTM. Furthermore, the Histogram of Oriented Gradient (HOG) feature vector is extracted from the proposed 3D-MTM as the representation of a gesture sequence. The experiment results show that the proposed method achieves better results on two publicly available datasets namely MSR Action3D dataset and ChaLearn gesture dataset.

Auditability and regulatory compliance are increasingly required for deploying large language models (LLMs). Prior work typically targets isolated stages such as training or unlearning and lacks a unified mechanism for verifiable accountability across model updates. This paper presents AuditableLLM, a lightweight framework that decouples update execution from an audit-and-verification layer and records each update as a hash-chain-backed, tamper-evident audit trail. The framework supports parameter-efficient fine-tuning such as Low-Rank Adaptation (LoRA) and Quantized LoRA (QLoRA), full-parameter optimization, continual learning, and data unlearning, enabling third-party verification without access to model internals or raw logs. Experiments on LLaMA-family models with LoRA adapters and the MovieLens dataset show negligible utility degradation (below 0.2% in accuracy and macro-F1) with modest overhead (3.4 ms/step; 5.7% slowdown) and sub-second audit validation in the evaluated setting. Under a simple loss-based membership inference attack on the forget set, the audit layer does not increase membership leakage relative to the underlying unlearning algorithm. Overall, the results indicate that hash-chain-backed audit logging can be integrated into practical LLM adaptation, update, and unlearning workflows with low overhead and verifiable integrity.

This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods. Our analysis reveals that GNNs cannot effectively learn structural information related to the number of common neighbors between two nodes, primarily due to the nature of set-based pooling of the neighborhood aggregation scheme. Also, our extensive experiments indicate that trainable node embeddings can improve the performance of GNN-based link prediction models. Importantly, we observe that the denser the graph, the greater such the improvement. We attribute this to the characteristics of node embeddings, where the link state of each link sample could be encoded into the embeddings of nodes that are involved in the neighborhood aggregation of the two nodes in that link sample. In denser graphs, every node could have more opportunities to attend the neighborhood aggregation of other nodes and encode states of more link samples to its embedding, thus learning better node embeddings for link prediction. Lastly, we demonstrate that the insights gained from our research carry important implications in identifying the limitations of existing link prediction methods, which could guide the future development of more robust algorithms.