Multimodal Emotion Recognition (MER) aims to understand complex human emotions by jointly analyzing visual and textual data. However, in real-world scenarios, emotional cues from different modalities often contain conflict information, such as a smiling face paired with negative text, which poses great challenges for existing multimodal language models (MLLMs). Existing emotion MLLMs and multimodal emotion benchmarks often overlook or even intentionally avoid scenarios involving multimodal emotion conflicts, limiting their ability to reason about complex and contradictory affective cues. By addressing this, we propose Conflict-Explicit Reflective Agent (CERA), a training-free, conflict-aware, and language-driven agentic framework for MER. The concept of CERA is to treat modality emotion conflicts as meaningful signals and resolve them via a three-stage perception–evaluation–reflection reasoning loop. Firstly, the agent’s conflict-perceptive emotion graph construction module builds emotion graphs from fine-grained cues to reveal conflicts, and progressively refines them through iterative updates. Secondly, a reward model evaluates these graphs and produces natural language feedback that identifies unresolved conflicts. Lastly, the language-driven conflict refinement module generates graph editing signals from the feedback without any parameter tuning, enabling the overall CERA to refine its reasoning without training. Extensive experiments on two multimodal emotion datasets, MAFW and CH-SIMS, demonstrate that CERA significantly outperforms state-of-the-art training-free methods in both recognition accuracy and conflict interpretability, providing an effective training-free solution for complex emotional reasoning.

Audio-visual emotion recognition (AVER) is crucial in various AI applications, such as digital humans. However, due to the incomplete and heterogeneity in emotional expression between the audio and visual modalities, challenges remain in achieving effective emotion interaction and fusion. To address these issues, we propose a novel approach, Emotion-Aware Text Generation for Instructing Audio-Visual Emotion Recognition (ETG-AVER). This method generates emotion-Aware text from audio-visual modalities to explicitly capture emotional cues, and utilizes the generated text to guide emotional feature extraction and fusion, thereby improving the performance of AVER. Specifically, ETG-AVER consists of three key components: (1) Emotion-Aware Text Generation module, which first generates Emotion-Aware texts from audio and video modalities, compensating for the limitations of audio-visual modalities in emotional expression; (2) Text-Instruct Multimodal Feature Extraction and Fusion module, which uses the generated Emotion-Aware texts to precisely guide the extraction and fusion of audio-visual features, effectively enhancing cross-modal emotion interaction; (3) Hierarchical Loss Optimization module, which uses hierarchical loss functions to align emotional features across unimodal and multimodal sources, ensuring consistency in both semantic and representational levels, thereby improving cross-modal emotion recognition accuracy. Experimental results demonstrate that ETG-AVER significantly outperforms existing methods in terms of accuracy and fine-grained classification, achieving 60.78% WAR on MAFW and 78.36% WAR on DFEW, validating the effectiveness of our approach in refining emotion information transfer and recognition.

Video-based facial expression recognition (VFER) is challenging due to variations caused by cultural background and expression camouflage. To tackle these problems, researchers introduced eye movement signals to complement visual information. However, existing methods either require expensive devices to capture high-quality eye movements or can only extract low-quality eye movements visually, making them ineffective in the real world. To address this, we propose an eye movement-instructed VFER (EM-VFER) that leverages high-quality eye movements to instruct the visual learning, obtaining robust performance without requiring costly devices during inference. Specifically, our EM-VFER operates in two stages: the high-quality eye movement pre-training stage and the eye movement-instructed video fine-tuning stage. In the pre-training, we compile an Eye-behavior-aided Multimodal Emotion Recognition (EMER) dataset and use it to train a multimodal Transformer. During the fine-tuning, we propose a novel progressive eye movement-instructed learning to take better advantage of the prior knowledge about high-quality eye movement signals from EMER. The instructed fine-tuning model could then make more robust predictions on downstream facial expression datasets. We evaluate our approach on three macroexpression datasets (DFEW, MAFW and Aff-wild2) and two micro-expression datasets (CASME III and CASME II). The results demonstrate that EM-VFER significantly outperforms existing methods. The code will be available.

Despite advances in deep learning for remote sensing building extraction (RSBE), Multi-target Domain RSBE (MD-RSBE) remains challenging, as it requires transferring knowledge from a labeled source domain to multiple unlabeled target domains, with domain shifts in texture, style, and semantics. Existing domain adaptation (DA) and generalization (DG) methods face significant limitations: DA requires target-domain training, while DG needs multi-source training, leading to high training costs and low generalization in practical MD-RSBE scenarios. To address this, we propose a Multi-view Augmented Single-source Domain Generalization (MASDG) method, which effectively mitigates domain shifts across RS source and target domains for robust MD-RSBE performance by enriching the diversity of the source domain through multi-view augmentation and enforcing semantic consistency. Specifically, MASDG consists of three key components: Texture-level Domain Augmentation (TDA) module, Style-level Domain Augmentation (SDA) module and Semantic-invariant Representation Learning (SRL). To mitigate texture-level domain shift, TDA first introduces parameter-optimized multi-layer random convolution to modify the texture of source image, generating texture-augmented image pairs for simulating real-world texture diversity across various RS domains. Then, with each image pair from TDA, SDA employs two paralleled encoders, namely the general feature encoder and the batch-guided style encoder, to formulate multi-view building features, further mitigating style-level domain shift. Finally, SRL ensures semantic-invariant representation learning via a dual mechanism, including multi-view segmentation loss and semantic consistency loss. The former generates predictions from diverse feature views (original, texture-augmented, style-augmented, etc.), while the latter performs semantic alignment by minimizing distribution discrepancies among predictions, bridging semantic inconsistency to enable robust segmentation. Extensive experiments across three different MD-RSBE settings with 7 different target domains demonstrate that our MASDG outperforms existing state-of-the-art methods by a significant margin.

Multimodal remote sensing image segmentation (MRSIS) is important for intelligent remote sensing image (RS) interpretation, which encompasses three distinct tasks: semantic segmentation, instance segmentation, and panoptic segmentation. Existing methods typically address individual tasks with specialized models, limiting generalization and real-world applicability. Multi-task learning approaches have introduced separated task heads to unify tasks, yet we identify two key challenges when directly applying them to MRSIS: (1) the modality gap, arising from semantic discrepancies and granularity discrepancies across RS modalities, and (2) the task gap, due to varying preferences in learning different segmentation tasks. To overcome these challenges, we propose PMTSeg—a novel Prompt-driven Multimodal Transformer for task-adapted MRSIS. PMTSeg integrates three key components: (1) Task-common Multimodal Affinity Approximation (TMAA), (2) Task-common Multi-scale Semantic Fusion (TMSF), and (3) a unified Prompt-driven Segmentation Head (PSH). First, TMAA addresses the modality gap by approximating inter-modal affinity matrices, extracting task-common features across modalities and aligning semantic information. Then, TMSF further integrates these features using the scale-matched fusion at multiple scales to produce enriched, multi-scale task-common features. Moreover, to address the task gap, the PSH leverages task-adapted text prompts and task-adapted contrastive loss to model relationships across tasks, enabling adaptive optimization for robust and universal MRSIS performance. Extensive experiments on three MRSIS datasets—VALID, SEMCITY TOULOUSE, and UBCV2—demonstrate that PMTSeg significantly surpasses state-of-the-art methods in all three segmentation tasks, offering a unified and accurate solution to MRSIS.

Deep learning-based building instance extraction on remote sensing imagery (RSI) has achieved tremendous success under the large-scale labeled training data. However, multi-target domain adaptation building instance extraction (MD-BIE) is still a challenge task that involves transferring knowledge from a source domain to multiple unlabeled target domains, which poses various semantic gaps between and within multiple domains,e.g., style, illumination, resolution, density, scale, etc. Most current methods for single-target domain adaptation are not applicable to the more realistic MD-BIE task. To this end, we propose a novel Domain-common Approximation Learning (DAL) for both modelling intra-domain and inter-domain adaptation, thus obtaining robust MD-BIE. DAL contains three main modules: multi-domain style transfer (MST), multi-domain feature approximation (MFA), and multi-domain cascaded instance extraction (MCIE). To alleviate the semantic gaps between multiple domains for inter-domain adaptation, we first employ the MST to learn multiple target-domain-like features that preserve both the styles of target domains and the content of the source domain, and then use the MFA to approximate these features towards a central domain-common space, thus producing domain-common semantic representations. Moreover, we develop the MCIE with hierarchical extraction losses for intra-domain adaptation to extract precise building instance contours from the domain-common semantic representations, further eliminating the potential gaps within multiple domains. By co-learning these three modules in an end-to-end manner, the DAL bridges the semantic gaps between and within multiple domains. Extensive experiments on different popular MD-BIS tasks (SAB → Crowd & WHU, Crowd → SAB & WHU, SAB → Crowd & SAB & WHU and SAB → WHU) show that our DAL outperforms the current methods by a significant margin.

Self-supervised facial representation has recently attracted increasing attention due to its ability to perform face understanding without relying on large-scale annotated datasets heavily. However, analytically, current contrastive-based self-supervised learning (SSL) still performs unsatisfactorily for learning facial representation. More specifically, existing contrastive learning (CL) tends to learn pose-invariant features that cannot depict the pose details of faces, compromising the learning performance. To conquer the above limitation of CL, we propose a novel Pose-disentangled Contrastive Learning (PCL) method for general self-supervised facial representation. Our PCL first devises a pose-disentangled decoder (PDD) with a delicately designed orthogonalizing regulation, which disentangles the pose-related features from the face-aware features; therefore, pose-related and other pose-unrelated facial information could be performed in individual subnetworks and do not affect each other's training. Furthermore, we introduce a pose-related contrastive learning scheme that learns pose-related information based on data augmentation of the same image, which would deliver more effective face-aware representation for various downstream tasks. We conducted linear evaluation on four challenging downstream facial understanding tasks, i.e., facial expression recognition, face recognition, AU detection and head pose estimation. Experimental results demonstrate that PCL significantly outperforms cuttingedge SSL methods. Our Code is available at https://github.com/DreamMr/PCL.

Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (e.g., language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved.To alleviate this, we present Adaptive Language-guided Multimodal Transformer (ALMT), which incorporates an Adaptive Hyper-modality Learning (AHL) module to learn an irrelevance/conflict-suppressing representation from visual and audio features under the guidance of language features at different scales.With the obtained hypermodality representation, the model can obtain a complementary and joint representation through multimodal fusion for effective MSA.In practice, ALMT achieves state-of-the-art performance on several popular datasets (e.g., MOSI, MOSEI and CH-SIMS) and an abundance of ablation demonstrates the validity and necessity of our irrelevance/conflict suppression mechanism.

OBJECTIVE: To explore dermatomyositis signature genes as potential biomarkers of hepatocellular carcinoma and their associated molecular regulatory mechanisms. METHODS: Based on the mRNA-Seq data of dermatomyositis and hepatocellular carcinoma in public databases, five dermatomyositis signature genes were screened by LASSO regression analysis and support vector machine (SVM) algorithm, and their biological functions in dermatomyositis with hepatocellular carcinoma were investigated, and a nomogram risk prediction model for hepatocellular carcinoma was constructed and its predictive efficiency was initially evaluated. The immune profile in hepatocellular carcinoma was examined based on the CIBERSORT and ssGSEA algorithms, and the correlation between five dermatomyositis signature genes and tumor immune cell infiltration and immune checkpoints in hepatocellular carcinoma was investigated. RESULTS: The expression levels of five dermatomyositis signature genes were significantly altered in hepatocellular carcinoma and showed good diagnostic efficacy for hepatocellular carcinoma, suggesting that they may be potential predictive targets for hepatocellular carcinoma, and the risk prediction model based on five dermatomyositis signature genes showed good risk prediction efficacy for hepatocellular carcinoma and has good potential for clinical application. In addition, we also found that the upregulation of SPP1 expression may activate the PI3K/ART signaling pathway through integrin-mediated activation, which in turn regulates the development and progression of hepatocellular carcinoma. CONCLUSION: LY6E, IFITM1, GADD45A, MT1M, and SPP1 are potential predictive targets for new-onset hepatocellular carcinoma in patients with dermatomyositis, and the upregulation of SPP1 expression may activate the PI3K/ART signaling pathway through the mediation of integrins to promote the development and progression of hepatocellular carcinoma.

Advances in transcriptome sequencing (RNA-Seq) have revolutionized the way to characterize and quantify transcripts. The breakthroughs in RNA-Seq technologies give rise to the ever-increasing volumes of data, making data processing the bottleneck of transcriptome research. It becomes crucial to develop an efficient analysis pipeline to automate RNA-Seq data analysis. Based on Oshell environment, we present here an ultra-fast and powerful RNA-Seq analysis pipeline for quality control, sequence alignment, variation detection, expression quantification and junction discovery. The pipeline runs on both Linux and Windows operating systems, with either stand-alone or cluster computing environment. Parallel computing is also supported for improved processing speed. Oshell is free for non-commercial use at http://omicsoft.com/oshell.

UNLABELLED: Accurately mapping RNA-Seq reads to the reference genome is a critical step for performing downstream analysis such as transcript assembly, isoform detection and quantification. Many tools have been developed; however, given the huge size of the next generation sequencing datasets and the complexity of the transcriptome, RNA-Seq read mapping remains a challenge with the ever-increasing amount of data. We develop Omicsoft sequence aligner (OSA), a fast and accurate alignment tool for RNA-Seq data. Benchmarked with existing methods, OSA improves mapping speed 4-10-fold with better sensitivity and less false positives. AVAILABILITY: OSA can be downloaded from http://omicsoft.com/osa. It is free to academic users. OSA has been tested extensively on Linux, Mac OS X and Windows platforms.

MOTIVATION: Next generation sequencing technology generates high-throughput data, which allows us to detect fusion genes at both transcript and genomic levels. To detect fusion genes, the current bioinformatics tools heavily rely on paired-end approaches and overlook the importance of reads that span fusion junctions. Thus there is a need to develop an efficient aligner to detect fusion events by accurate mapping of these junction-spanning single reads, particularly when the read gets longer with the improvement in sequencing technology. RESULTS: We present a novel method, FusionMap, which aligns fusion reads directly to the genome without prior knowledge of potential fusion regions. FusionMap can detect fusion events in both single- and paired-end datasets from either RNA-Seq or gDNA-Seq studies and characterize fusion junctions at base-pair resolution. We showed that FusionMap achieved high sensitivity and specificity in fusion detection on two simulated RNA-Seq datasets, which contained 75 nt paired-end reads. FusionMap achieved substantially higher sensitivity and specificity than the paired-end approach when the inner distance between read pairs was small. Using FusionMap to characterize fusion genes in K562 chronic myeloid leukemia cell line, we further demonstrated its accuracy in fusion detection in both single-end RNA-Seq and gDNA-Seq datasets. These combined results show that FusionMap provides an accurate and systematic solution to detecting fusion events through junction-spanning reads. AVAILABILITY: FusionMap includes reference indexing, read filtering, fusion alignment and reporting in one package. The software is free for noncommercial use at (http://www.omicsoft.com/fusionmap).

We study routing misbehavior in MANETs (mobile ad hoc networks) in this paper. In general, routing protocols for MANETs are designed based on the assumption that all participating nodes are fully cooperative. However, due to the open structure and scarcely available battery-based energy, node misbehaviors may exist. One such routing misbehavior is that some selfish nodes will participate in the route discovery and maintenance processes but refuse to forward data packets. In this paper, we propose the 2ACK scheme that serves as an add-on technique for routing schemes to detect routing misbehavior and to mitigate their adverse effect. The main idea of the 2ACK scheme is to send two-hop acknowledgment packets in the opposite direction of the routing path. In order to reduce additional routing overhead, only a fraction of the received data packets are acknowledged in the 2ACK scheme. Analytical and simulation results are presented to evaluate the performance of the proposed scheme

SUMMARY: PowerMarker delivers a data-driven, integrated analysis environment (IAE) for genetic data. The IAE integrates data management, analysis and visualization in a user-friendly graphical user interface. It accelerates the analysis lifecycle and enables users to maintain data integrity throughout the process. An ever-growing list of more than 50 different statistical analyses for genetic markers has been implemented in PowerMarker. AVAILABILITY: www.powermarker.net