论文检索

Zeyuan An, Yanghang Xiao, Zhiying Leng, Frederick W. B. Li, Xiaohui Liang

Maintaining consistent 3D scene representations over time is a significant challenge in computer vision. Updating 3D scenes from sparse-view observations is crucial for various real-world applications, including urban planning, disaster assessment, and historical site preservation, where dense scans are often unavailable or impractical. In this paper, we propose Cross-Temporal 3D Gaussian Splatting (Cross-Temporal 3DGS), a novel framework for efficiently reconstructing and updating 3D scenes across different time periods, using sparse images and previously captured scene priors. Our approach comprises three stages: 1) Cross-temporal camera alignment for estimating and aligning camera poses across different timestamps; 2) Interference-based confidence initialization to identify unchanged regions between timestamps, thereby guiding updates; and 3) Progressive cross-temporal optimization, which iteratively integrates historical prior information into the 3D scene to enhance reconstruction quality. Our method supports non-continuous capture, enabling not only updates using new sparse views to refine existing scenes, but also recovering past scenes from limited data with the help of current captures. Furthermore, we demonstrate the potential of this approach to achieve temporal changes using only sparse images, which can later be reconstructed into detailed 3D representations as needed. Experimental results show significant improvements over baseline methods in reconstruction quality and data efficiency, making this approach a promising solution for scene versioning, cross-temporal digital twins, and long-term spatial documentation.

Wenbin An, Jiahao Nie, Feng Tian, Mingxiang Cai, Yaqiang Wu, Xiaoqin Zhang, Shijian Lu

Multimodal Retrieval-Augmented Generation (MRAG) has recently been explored to empower Large Vision Language Models (LVLMs) with more comprehensive and up-to-date contextual knowledge, aiming to compensate for their limited and coarse-grained parametric knowledge in knowledge-intensive tasks. However, the retrieved contextual knowledge is usually not aligned with LVLMs’ internal parametric knowledge, leading to knowledge conflicts and further unreliable responses. To tackle this issue, we design KCM, a training-free and plug-and-play framework that can effectively mitigate knowledge conflicts while incorporating MRAG for more accurate LVLM responses. KCM enhances contextual knowledge utilization by modifying the LVLM architecture from three key perspectives. First, KCM adaptively adjusts attention distributions among multiple attention heads, encouraging LVLMs to focus on contextual knowledge with reduced distraction. Second, KCM identifies and prunes knowledge-centric LVLM neurons that encode coarse-grained parametric knowledge, thereby suppressing interferences and enabling more effective integration of contextual knowledge. Third, KCM amplifies the information flow from the input context by injecting supplementary context logits, reinforcing its contribution to the final output. Extensive experiments over multiple LVLMs and benchmarks show that KCM outperforms the state-of-the-art consistently by large margins, incurring neither extra training nor external tools.

Hongyu An, Xinfeng Zhang, Shijie Zhao, Li Zhang, Ruiqin Xiong

Omnidirectional videos (ODVs) provide an immersive visual experience by capturing the 360° scene. With the rapid advancements in virtual/augmented reality, metaverse, and generative artificial intelligence, the demand for high-quality ODVs is surging. However, ODVs often suffer from low resolution due to their wide field of view and limitations in capturing devices and transmission bandwidth. Although video super-resolution (SR) is a capable video quality enhancement technique, the performance ceiling and practical generalization of existing methods are limited when applied to ODVs due to their unique attributes. To alleviate spatial projection distortions and temporal flickering of ODVs, we propose a Spatio-Temporal Distortion Aware Network (STDAN) with joint spatio-temporal alignment and reconstruction. Specifically, we incorporate a spatio-temporal continuous alignment (STCA) to mitigate discrete geometric artifacts in parallel with temporal alignment. Subsequently, we introduce an interlaced multi-frame reconstruction (IMFR) to enhance temporal consistency. Furthermore, we employ latitude-saliency adaptive (LSA) weights to focus on regions with higher texture complexity and human-watching interest. By exploring a spatio-temporal jointly framework and real-world viewing strategies, STDAN effectively reinforces spatio-temporal coherence on a novel ODV-SR dataset and ensures affordable computational costs. Extensive experimental results demonstrate that STDAN outperforms state-of-the-art methods in improving visual fidelity and dynamic smoothness of ODVs.

Niki Amini-Naieni, Andrew Zisserman

We introduce a new task of open-world object counting in videos: given a text description, or an image example, that specifies the target object, the objective is to enumerate all the unique instances of the target objects in the video. This task is especially challenging in crowded scenes with occlusions and objects of similar appearance, where avoiding double counting and identifying reappearances is crucial. To this end, we make the following contributions: we introduce a model, CountVid, for this task. It leverages an image-based counting model, and a promptable video segmentation and tracking model, to enable automated open-world object counting across video frames. To evaluate its performance, we introduce VideoCount, a new dataset for this novel task built from the TAO and MOT20 tracking datasets, as well as from videos of penguins and metal alloy crystallization captured by x-rays. Using this dataset, we demonstrate that CountVid provides accurate object counts, and significantly outperforms strong baselines.

Yohanes Yudhi Adikusuma, Qixing Huang, Ying He

Computing geodesic distances on 3D surfaces is fundamental to many tasks in 3D vision and geometry processing, with deep connections to tasks such as shape correspondence. Recent learning-based methods achieve strong performance but rely on large 3D backbones, leading to high memory usage and latency, which limit their use in interactive or resource-constrained settings. We introduce LiteGE, a lightweight approach that constructs compact, category-aware shape descriptors by applying PCA to unsigned distance field (UDFs) samples at informative voxels. This descriptor is efficient to compute and removes the need for high-capacity networks. LiteGE remains robust on sparse point clouds, supporting inputs with as few as 300 points, where prior methods fail. Extensive experiments show that LiteGE reduces memory usage and inference time by up to 300x compared to existing neural approaches. In addition, by exploiting the intrinsic relationship between geodesic distance and shape correspondence, LiteGE enables fast and accurate shape matching. Our method achieves up to 1000x speedup over state-of-the-art mesh-based approaches while maintaining comparable accuracy on non-isometric shape pairs, including evaluations on point-cloud inputs.

Yan Zhuang, Minhao Liu, Yanru Zhang, Jiawen Deng, Fuji Ren

Multimodal Sentiment Analysis (MSA) aims to infer human sentiment by integrating information from multiple modalities such as text, audio, and video. In real-world scenarios, however, the presence of missing modalities and noisy signals significantly hinders the robustness and accuracy of existing models. While prior works have made progress on these issues, they are typically addressed in isolation, limiting overall effectiveness in practical settings. To jointly mitigate the challenges posed by missing and noisy modalities, we propose a framework called Two-stage Modality Denoising and Complementation (TMDC). TMDC comprises two sequential training stages. In the Intra-Modality Denoising Stage, denoised modality-specific and modality-shared representations are extracted from complete data using dedicated denoising modules, reducing the impact of noise and enhancing representational robustness. In the Inter-Modality Complementation Stage, these representations are leveraged to compensate for missing modalities, thereby enriching the available information and further improving robustness. Extensive evaluations on MOSI, MOSEI, and IEMOCAP demonstrate that TMDC consistently achieves superior performance compared to existing methods, establishing new state-of-the-art results.

Shijing Zhu, Zhuang Chen, Guanqun Bi, Binghang Li, Yaxi Deng, Dazhen Wan, Libiao Peng, Xiyao Xiao, Rongsheng Zhang, Tangjie Lv 等

Large language models (LLMs) have shown promise in providing scalable mental health support, while evaluating their counseling capability remains crucial to ensure both efficacy and safety. Existing evaluations are limited by the static assessment that focuses on knowledge tests, the single perspective that centers on user experience, and the open-loop framework that lacks actionable feedback. To address these issues, we propose Ψ-Arena, an interactive framework for comprehensive assessment and optimization of LLM-based counselors, featuring three key characteristics: (1) Realistic arena interactions that simulate real-world counseling through multi-stage dialogues with psychologically profiled NPC clients; (2) Tripartite evaluation that integrates assessments from the client, supervisor, and counselor perspectives; (3) Closed-loop optimization that iteratively improves LLM counselors using diagnostic feedback. Experiments across eight state-of-the-art LLMs show significant performance variations in different real-world scenarios and evaluation perspectives. Moreover, reflection-based optimization results in up to a 141% improvement in counseling performance. We hope Ψ-Arena provides a foundational resource for advancing reliable and human-aligned LLM applications in mental healthcare.

Zhiyuan Zhou, Yanrong Guo, Shijie Hao

Emotional and cognitive factors are essential for understanding mental health disorders. However, existing methods often treat multi-modal data as classification tasks, limiting interpretability especially for emotion and cognition. Although large language models (LLMs) offer opportunities for mental health analysis, they mainly rely on textual semantics and overlook fine-grained emotional and cognitive cues in multi-modal inputs. While some studies incorporate emotional features via transfer learning, their connection to mental health conditions remains implicit. To address these issues, we propose ECMC, a novel task that aims at generating natural language descriptions of emotional and cognitive states from multi-modal data, and producing emotion–cognition profiles that improve both the accuracy and interpretability of mental health assessments. We adopt an encoder–decoder architecture, where modality-specific encoders extract features, which are fused by a dual-stream BridgeNet based on Q-former. Contrastive learning enhances the extraction of emotional and cognitive features. A LLaMA decoder then aligns these features with annotated captions to produce detailed descriptions. Extensive objective and subjective evaluations demonstrate that: 1) ECMC outperforms existing multi-modal LLMs and mental health models in generating emotion–cognition captions; 2) the generated emotion–cognition profiles significantly improve assistive diagnosis and interpretability in mental health analysis.

Yujia Zhou, Hexi Wang, Qingyao Ai, Zhen Wu, Yiqun Liu

As large language models (LLMs) increasingly operate as autonomous agents in social contexts, evaluating their capacity for prosocial behavior is both theoretically and practically critical. However, existing research has primarily relied on static, economically framed paradigms, lacking models that capture the dynamic evolution of prosociality and its sensitivity to structural inequities. To address these gaps, we introduce ProSim, a simulation framework for modeling the prosocial behavior in LLM agents across diverse social conditions. We conduct three progressive studies to assess prosocial alignment. First, we demonstrate that LLM agents can exhibit human-like prosocial behavior across a broad range of real-world scenarios and adapt to normative policy interventions. Second, we find that agents engage in fairness-based third-party punishment and respond systematically to variations in inequity magnitude and enforcement cost. Third, we show that policy-induced inequities suppress prosocial behavior, propagate norm erosion through social networks. These findings advance prosocial behavior theory by elucidating how institutional dynamics shape the emergence, decay, and diffusion of prosocial norms in agent-driven societies.

Deming Zhou, Yuetong Fang, Zhaorui Wang, Renjing Xu

The primate visual cortex exhibits topographic organization, where functionally similar neurons are spatially clustered, a structure widely believed to enhance neural processing efficiency. While prior works have demonstrated that conventional deep ANNs can develop topographic representations, these models largely neglect crucial temporal dynamics. This oversight often leads to significant performance degradation in tasks like object recognition and compromises their biological fidelity. To address this, we leverage spiking neural networks (SNNs), which inherently capture spike-based temporal dynamics and offer enhanced biological plausibility. We propose a novel Spatio-Temporal Constraints (STC) loss function for topographic deep spiking neural networks (TDSNNs), successfully replicating the hierarchical spatial functional organization observed in the primate visual cortex from low-level sensory input to high-level abstract representations. Our results show that STC effectively generates representative topographic features across simulated visual cortical areas. While introducing topography typically leads to significant performance degradation in ANNs, our spiking architecture exhibits a remarkably small performance drop (No drop in ImageNet top-1 accuracy, compared to a 3% drop observed in TopoNet, which is the best-performing topographic ANN so far) and outperforms topographic ANNs in brain-likeness. We also reveal that topographic organization facilitates efficient and stable temporal information processing via the spike mechanism in TDSNNs, contributing to model robustness. These findings suggest that TDSNNs offer a compelling balance between computational performance and brain-like features, providing not only a framework for interpreting neural science phenomena but also novel insights for designing more efficient and robust deep learning models.

Chenlin Zhou, Liutao Yu, Zhaokun Zhou, Han Zhang, Jiaqi Wang, Huihui Zhou, Zhengyu Ma, Yonghong Tian

Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial neural networks, due to their event-driven spiking computation. However, some foundation SNN backbones (including Spikformer and SEW ResNet) suffer from non-spike computations (integer-float multiplications) caused by the structure of their residual connections. These non-spike computations increase SNNs' power consumption and make them unsuitable for deployment on mainstream neuromorphic hardware. In this paper, we analyze the spike-driven behavior of the residual connection methods in SNNs. We then present Spikingformer, a novel spiking transformer backbone that merges the MS Residual connection with Self-Attention in a biologically plausible way to address the non-spike computation challenge in Spikformer while maintaining global modeling capabilities. We evaluate Spikingformer across 13 datasets spanning large static images, neuromorphic data, and natural language tasks, and demonstrate the effectiveness and universality of Spikingformer, setting a vital benchmark for spiking neural networks. In addition, with the spike-driven features and global modeling capabilities, Spikingformer is expected to become a more efficient general-purpose SNN backbone towards energy-efficient artificial intelligence.

Wenhan Zhang, Zihan Huang, Tong Bu, Tiejun Huang, Zhaofei Yu

Spiking Neural Networks(SNNs) are a promising paradigm designed to emulate the brain's energy efficient by incorporating the timing of spikes. Conversion is an efficient way to obtain high-performance SNNs from Artificial Neural Networks(ANNs). Existing conversion methods often face a trade-off between accuracy and time steps, which is largely caused by the incomplete release of residual membrane potentials. To minimize the conversion error, this paper proposed a harmonious mathematical property-based neuron, called Harmony Multi-Threshold Neurons (H-MT Neuron), which utilizes multiple spikes to minimize residual membrane potentials. The proposed neuron is further enhanced with an optional effective communication mechanism to achieve more accurate conversion. In addition, we propose a threshold optimization method applicable to a broader range cases of spiking neurons to to find the optimal neuron thresholds. Experiment results demonstrate that our method achieve superior accuracy on ImageNet benchmark datasets while significantly reducing the required time steps and energy consumption.

Hao-Long Yin, Jian-Ming Zhang, Ren-Jie Dai, Wei-Long Zheng, Qinyu Lv, Zhenghui Yi, Bao-Liang Lu

Depression is a prevalent mental health disorder characterized by persistent sadness and a diminished interest in daily activities, early detection of depression facilitates timely intervention, mitigating its adverse effects. Electroencephalography (EEG) signals and eye movements are emerging as promising biomarkers for depression detection due to their non-invasive nature and cost-effectiveness. Nevertheless, existing studies suffer from methodological constraints, including low specificity, insufficient sample sizes, limited generalizability, and difficulties in large-scale replication, which collectively undermine their clinical utility. To address these challenges, we collected a large-scale depression dataset comprising EEG and eye movements from 1,060 individuals diagnosed with depression and 1,308 healthy controls. To efficiently leverage multimodal data for automatic depression detection, we propose the EEG-Eye Movements Model (E2Mo). E2Mo employs modality-specific encoders to extract discriminative multi-view features from each modality and incorporates a mixture-of-modality-experts architecture with multi pretraining tasks to achieve efficient and robust modality alignment and fusion. Our approach achieves a 70.06% balanced accuracy by leveraging multi-modal data, demonstrating the effectiveness of integrating EEG signals and eye movements for automatic depression detection.

Yi Yang, Haowen Li, Tianxiang Li, Boyu Cao, Xiaohan Zhang, Liqun Chen, Qi Liu

Text-to-music generation technology is progressing rapidly, creating new opportunities for musical composition and editing. However, existing music editing methods often fail to preserve the source music's temporal structure, including melody and rhythm, when altering particular attributes like instrument, genre, and mood. To address this challenge, this paper conducts an in-depth probing analysis on attention maps within AudioLDM 2, a diffusion-based model commonly used as the backbone for existing music editing methods. We reveal a key finding: cross-attention maps encompass details regarding distinct musical characteristics, and interventions on these maps frequently result in ineffective modifications. In contrast, self-attention maps are essential for preserving the temporal structure of the source music during its conversion into the target music. Building upon this understanding, we present Melodia, a training-free technique that selectively manipulates self-attention maps in particular layers during the denoising process and leverages an attention repository to store source music information, achieving accurate modification of musical characteristics while preserving the original structure without requiring textual descriptions of the source music. Additionally, we propose two novel metrics to better evaluate music editing methods. Both objective and subjective experiments demonstrate that our approach achieves superior results in terms of textual adherence and structural integrity across various datasets. This research enhances comprehension of internal mechanisms within music generation models and provides improved control for music creation.

Xikang Yang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

Large Language Models (LLMs) demonstrate impressive capabilities across diverse tasks, yet their safety mechanisms remain susceptible to adversarial exploitation of cognitive biases---systematic deviations from rational judgment. Unlike prior studies focusing on isolated biases, this work highlights the overlooked power of multi-bias interactions in undermining LLM safeguards. Specifically, we propose CognitiveAttack, a novel red-teaming framework that adaptively selects optimal ensembles from 154 human social psychology-defined cognitive biases, engineering them into adversarial prompts to effectively compromise LLM safety mechanisms. Experimental results reveal systemic vulnerabilities across 30 mainstream LLMs, particularly open-source variants. CognitiveAttack achieves a substantially higher attack success rate than the SOTA black-box method PAP (60.1% vs. 31.6%), exposing critical limitations in current defenses. Through quantitative analysis of successful jailbreaks, we further identify vulnerability patterns in safety-aligned LLMs under synergistic cognitive biases, validating multi-bias interactions as a potent yet underexplored attack vector. This work introduces a novel interdisciplinary perspective by bridging cognitive science and LLM safety, paving the way for more robust and human-aligned AI systems.

Heng Xie, Kang Zhu, Zhengqi Wen, Jianhua Tao, Xuefei Liu, Ruibo Fu, Changsheng Li

Multimodal sentiment analysis (MSA) is a research field that recognizes human sentiments by combining textual, visual, and audio modalities. The main challenge lies in integrating sentiment-related information from different modalities, which typically arises during the unimodal feature extraction phase and the multimodal feature fusion phase. Existing methods extract only shallow information from unimodal features during the extraction phase, neglecting sentimental differences across different personalities. During the fusion phase, they directly merge the feature information from each modality without considering differences at the feature level. This ultimately affects the model's recognition performance. To address this problem, we propose a personality-sentiment aligned multi-level fusion framework. We introduce personality traits during the feature extraction phase and propose a novel personality-sentiment alignment method to obtain personalized sentiment embeddings from the textual modality for the first time. In the fusion phase, we introduce a novel multi-level fusion method. This method gradually integrates sentimental information from textual, visual, and audio modalities through multimodal pre-fusion and a multi-level enhanced fusion strategy. Our method has been evaluated through multiple experiments on two commonly used datasets, achieving state-of-the-art results.

Haiying Xia, Zhongyi Huang, Yumei Tan, Shuxiang Song

Music emotion recognition is a key task in symbolic music understanding (SMER). Recent approaches have shown promising results by fine-tuning large-scale pre-trained models (e.g., MIDIBERT, a benchmark in symbolic music understanding) to map musical semantics to emotional labels. While these models effectively capture distributional musical semantics, they often overlook tonal structures, particularly musical modes, which play a critical role in emotional perception according to music psychology. In this paper, we investigate the representational capacity of MIDIBERT and identify its limitations in capturing mode-emotion associations. To address this issue, we propose a Mode-Guided Enhancement (MoGE) strategy that incorporates psychological insights on mode into the model. Specifically, we first conduct a mode augmentation analysis, which reveals that MIDIBERT fails to effectively encode emotion-mode correlations. Motivated by this observation, we further identify the MIDIBERT layer that shows the weakest emotion relevance and introduce a Mode-guided Feature-wise linear modulation injection (MoFi) framework to inject explicit mode features, thereby enhancing the model's capability in emotional representation and inference. Extensive experiments on the EMOPIA and VGMIDI datasets demonstrate that our mode injection strategy significantly improves SMER performance, achieving accuracies of 75.2% and 59.1%, respectively. These results validate the effectiveness of mode-guided modeling in symbolic music emotion recognition.

Jiesheng Wu, Shengrong Li

Existing Image-Text Sentiment Analysis (ITSA) methods may suffer from inconsistent intra-modal and inter-modal sentiment relationships. Therefore, we develop a method that balances before fusing to solve the issue of vision-language imbalance intra-modal and inter-modal sentiment relationships; that is, a Semi-Push-Pull Supervised Contrastive Learning (SPP-SCL) method is proposed. Specifically, the method is implemented using a novel two-step strategy, namely first using the proposed intra-modal supervised contrastive learning to pull the relationships between the intra-modal and then performing a well-designed conditional execution statement. If the statement result is false, our method will perform the second step, which is inter-modal supervised contrastive learning to push away the relationships between inter-modal. The two-step strategy will balance the intra-modal and inter-modal relationships to achieve the purpose of relationship consistency and finally perform cross-modal feature fusion for sentiment analysis and detection. Experimental studies on three public image-text sentiment and sarcasm detection datasets demonstrate that SPP-SCL significantly outperforms state-of-the-art methods by a large margin and is more discriminative in sentiment.

Baiqiang Wu, Yang Li

Multimodal emotion recognition plays a crucial role in enhancing the intelligence of human-computer interaction and emotional understanding. However, conventional approaches face challenges such as scarcity of annotated data, significant modality heterogeneity, and temporal misalignment. To address these issues, we propose DHCM-CACL, a novel self-supervised emotion recognition framework integrating EEG and facial expressions. During the pre-training phase, we propose a Dynamic Hierarchical Cross-modal Mamba module (DHCM), which models long-term dependencies through dynamic state matrices, incorporates forgetting gates for noise suppression, and constructs a hierarchical cross-modal interaction structure, effectively achieving cross-modal temporal alignment and mitigating modality heterogeneity. Subsequently, we propose a Confidence-Adaptive Contrastive Learning module (CACL) that dynamically adjusts sample weights using gated confidence signals derived from DHCM to compute loss, prioritizing reliable samples while suppressing noisy instances through adaptive weighting, thereby enhancing representation reliability and generalization in data-scarce scenarios. During the fine-tuning phase, we integrate a cross-modal attention gating mechanism to reinforce temporal associations and adopt an evidence-aware joint optimization objective, providing probabilistic credibility outputs for emotion prediction. Experimental results on the DEAP and MAHNOB-HCI datasets demonstrate that our approach achieves state-of-the-art performance in emotion classification under both subject-dependent and subject-independent settings.

Ziquan Wei, Tingting Dan, Guorong Wu

A reliable foundation model of functional neuroimages is critical to promote clinical applications where the performance of current AI models is significantly impeded by a limited sample size. To that end, tremendous efforts have been made to pretraining large models on extensive unlabeled fMRI data using scalable self-supervised learning. Since self-supervision is not necessarily aligned with the brain-to-outcome relationship, most foundation models are suboptimal to the downstream task, such as predicting disease outcomes. By capitalizing on rich environmental variables and demographic data along with an unprecedented amount of functional neuroimages, we form the brain modeling as a multitask learning and present a scalable model architecture for (i) multitask pretraining by tokenizing multiple brain-environment interactions (BEI) and (ii) semi-supervised finetuning by assigning pseudo-labels of default BEI. We have evaluated our foundation model on a variety of applications, including sex prediction, human behavior recognition, and disease early diagnosis of Autism, Parkinson's disease, Alzheimer's disease, and Schizophrenia, where promising results indicate the great potential to facilitate current neuroimaging applications in clinical routines.