Abstract--Alcohol consumption is a significant public health concern and a major cause of accidents and fatalities worldwide. This study introduces a novel video-based facial sequence analysis approach dedicated to the detection of alcohol intoxication. The method integrates facial landmark analysis via a Graph Attention Network (GA T) with spatiotemporal visual features extracted using a 3D ResNet. These features are dynamically fused with adaptive prioritization to enhance classification performance. Additionally, we introduce a curated dataset comprising 3,542 video segments derived from 202 individuals to support training and evaluation. Our model is compared against two baselines: a custom 3D-CNN and a VGGFace+LSTM architecture. Experimental results show that our approach achieves 95.82% accuracy, 0.977 precision, and 0.97 recall, outperforming prior methods. The findings demonstrate the model's potential for practical deployment in public safety systems for non-invasive, reliable alcohol intoxication detection. Alcohol consumption remains a significant public safety challenge, particularly when it negatively affects cognitive functions, physical coordination, and judgment.

Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Following the paradigm introduced by DUSt3R, which unifies an image pair densely into a shared coordinate system, subsequent methods maintain an implicit memory to achieve dense 3D reconstruction from more images. However, such implicit memory is limited in capacity and may suffer from information loss of earlier frames. We propose Point3R, an online framework targeting dense streaming 3D reconstruction. To be specific, we maintain an explicit spatial pointer memory directly associated with the 3D structure of the current scene. Each pointer in this memory is assigned a specific 3D position and aggregates scene information nearby in the global coordinate system into a changing spatial feature. Information extracted from the latest frame interacts explicitly with this pointer memory, enabling dense integration of the current observation into the global coordinate system. We design a 3D hierarchical position embedding to promote this interaction and design a simple yet effective fusion mechanism to ensure that our pointer memory is uniform and efficient. Our method achieves competitive or state-of-the-art performance on various tasks with low training costs.

Experiment results are shown in Table 5.

Multimodal sentiment analysis (MSA) leverages information fusion from diverse modalities (e.g., text, audio, visual) to enhance sentiment prediction. However, simple fusion techniques often fail to account for variations in modality quality, such as those that are noisy, missing, or semantically conflicting. This oversight leads to suboptimal performance, especially in discerning subtle emotional nuances. To mitigate this limitation, we introduce a simple yet efficient \textbf{A}daptive \textbf{G}ated \textbf{F}usion \textbf{N}etwork that adaptively adjusts feature weights via a dual gate fusion mechanism based on information entropy and modality importance. This mechanism mitigates the influence of noisy modalities and prioritizes informative cues following unimodal encoding and cross-modal interaction. Experiments on CMU-MOSI and CMU-MOSEI show that AGFN significantly outperforms strong baselines in accuracy, effectively discerning subtle emotions with robust performance. Visualization analysis of feature representations demonstrates that AGFN enhances generalization by learning from a broader feature distribution, achieved by reducing the correlation between feature location and prediction error, thereby decreasing reliance on specific locations and creating more robust multimodal feature representations.

Multimodal surface material classification plays a critical role in advancing tactile perception for robotic manipulation and interaction. In this paper, we present Surformer v2, an enhanced multi-modal classification architecture designed to integrate visual and tactile sensory streams through a late(decision level) fusion mechanism. Building on our earlier Surformer v1 framework [1], which employed handcrafted feature extraction followed by mid-level fusion architecture with multi-head cross-attention layers, Surformer v2 integrates the feature extraction process within the model itself and shifts to late fusion. The vision branch leverages a CNN-based classifier(Efficient V-Net), while the tactile branch employs an encoder-only transformer model, allowing each modality to extract modality-specific features optimized for classification. Rather than merging feature maps, the model performs decision-level fusion by combining the output logits using a learnable weighted sum, enabling adaptive emphasis on each modality depending on data context and training dynamics. We evaluate Surformer v2 on the Touch and Go dataset [2], a multi-modal benchmark comprising surface images and corresponding tactile sensor readings. Our results demonstrate that Surformer v2 performs well, maintaining competitive inference speed, suitable for real-time robotic applications. These findings underscore the effectiveness of decision-level fusion and transformer-based tactile modeling for enhancing surface understanding in multi-modal robotic perception.

Suicide is one of the leading causes of death among adolescents. Previous suicide risk prediction studies have primarily focused on either textual or acoustic information in isolation, the integration of multimodal signals, such as speech and text, offers a more comprehensive understanding of an individual's mental state. Motivated by this, and in the context of the 1st SpeechWellness detection challenge, we explore a lightweight multi-branch multimodal system based on a dynamic fusion mechanism for speechwellness detection. To address the limitation of prior approaches that rely on time-domain waveforms for acoustic analysis, our system incorporates both time-domain and time-frequency (TF) domain acoustic features, as well as semantic representations. In addition, we introduce a dynamic fusion block to adaptively integrate information from different modalities. Specifically, it applies learnable weights to each modality during the fusion process, enabling the model to adjust the contribution of each modality. To enhance computational efficiency, we design a lightweight structure by simplifying the original baseline model. Experimental results demonstrate that the proposed system exhibits superior performance compared to the challenge baseline, achieving a 78% reduction in model parameters and a 5% improvement in accuracy.

Body-conduction microphone signals (BMS) bypass airborne sound, providing strong noise resistance. However, a complementary modality is required to compensate for the inherent loss of high-frequency information. In this study, we propose a novel multi-modal framework that combines BMS and acoustic microphone signals (AMS) to achieve both noise suppression and high-frequency reconstruction. Unlike conventional multi-modal approaches that simply merge features, our method employs two specialized networks: a mapping-based model to enhance BMS and a masking-based model to denoise AMS. These networks are integrated through a dynamic fusion mechanism that adapts to local noise conditions, ensuring the optimal use of each modality's strengths. We performed evaluations on the T APS dataset, augmented with DNS-2023 noise clips, using objective speech quality metrics. The results clearly demonstrate that our approach outperforms single-modal solutions in a wide range of noisy environments.

--The advent of blockchain technology has facilitated the widespread adoption of smart contracts in the financial sector . However, current fraud detection methodologies exhibit limitations in capturing both global structural patterns within transaction networks and local semantic relationships embedded in transaction data. Most existing models focus on either structural information or semantic features individually, leading to suboptimal performance in detecting complex fraud patterns.In this paper, we propose a dynamic feature fusion model that combines graph-based representation learning and semantic feature extraction for blockchain fraud detection. Specifically, we construct global graph representations to model account relationships and extract local contextual features from transaction data. A dynamic multimodal fusion mechanism is introduced to adaptively integrate these features, enabling the model to capture both structural and semantic fraud patterns effectively. We further develop a comprehensive data processing pipeline, including graph construction, temporal feature enhancement, and text preprocessing. Experimental results on large-scale real-world blockchain datasets demonstrate that our method outperforms existing benchmarks across accuracy, F1 score, and recall metrics. This work highlights the importance of integrating structural relationships and semantic similarities for robust fraud detection and offers a scalable solution for securing blockchain systems. LOCKCHAIN technology has developed rapidly in recent years and has triggered far-reaching changes in several fields, especially in the financial industry [1]. However, as the popularity of blockchain applications grows, so does the significant increase in fraudulent behaviors it has brought about, with serious implications for society [2]. Blockchain technology, due to its decentralization and transparency, has become a tool for unscrupulous individuals to exploit, although it provides greater security and efficiency in financial transactions [3]. For example, the application of blockchain technology in the supply chain is seen as an effective means to enhance transparency and traceability, but it also faces a crisis of social trust due to fraudulent behavior [4].

Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates Knowledge Distillation (KD) from Large Visual Language Models (LVLMs) and knowledge infusion to enhance the performance of toxicity detection in hateful memes. Our approach extracts sub-knowledge graphs from ConceptNet, a large-scale commonsense Knowledge Graph (KG) to be infused within a compact VLM framework. The relational context between toxic phrases in captions and memes, as well as visual concepts in memes enhance the model's reasoning capabilities. Experimental results from our study on two hate speech benchmark datasets demonstrate superior performance over the state-of-the-art baselines across AU-ROC, F1, and Recall with improvements of 1.1%, 7%, and 35%, respectively. Given the contextual complexity of the toxicity detection task, our approach showcases the significance of learning from both explicit (i.e. KG) as well as implicit (i.e. LVLMs) contextual cues incorporated through a hybrid neurosymbolic approach. This is crucial for real-world applications where accurate and scalable recognition of toxic content is critical for creating safer online environments.