scFusionTTT: Single-cell transcriptomics and proteomics fusion with Test-Time Training layers

Single-cell multi-omics (scMulti-omics) refers to the paired multimodal data, such as Cellular Indexing of Transcriptomes and Epitopes by Sequencing (CITE-seq), where the regulation of each cell was measured from different modalities, i.e. genes and proteins. scMulti-omics can reveal heterogeneity inside tumors and understand the distinct genetic properties of diverse cell types, which is crucial to targeted therapy. Currently, deep learning methods based on attention structures in the bioinformatics area face two challenges. The first challenge is the vast number of genes in a single cell. Traditional attention-based modules struggled to effectively leverage all gene information due to their limited capacity for long-context learning and high-complexity computing. The second challenge is that genes in the human genome are ordered and influence each other's expression. Most of the methods ignored this sequential information. The recently introduced Test-Time Training (TTT) layer is a novel sequence modeling approach, particularly suitable for handling long contexts like genomics data because TTT layer is a linear complexity sequence modeling structure and is better suited to data with sequential relationships. In this paper, we propose scFusionTTT, a novel method for Single-Cell multimodal omics Fusion with TTT-based masked autoencoder. Of note, we combine the order information of genes and proteins in the human genome with the TTT layer, fuse multimodal omics, and enhance unimodal omics analysis. Finally, the model employs a three-stage training strategy, which yielded the best performance across most metrics in four multimodal omics datasets and four unimodal omics datasets, demonstrating the superior performance of our model. The dataset and code will be available on https://github.com/DM0815/scFusionTTT.

PhysMamba: Efficient Remote Physiological Measurement with SlowFast Temporal Difference Mamba

Facial-video based Remote photoplethysmography (rPPG) aims at measuring physiological signals and monitoring heart activity without any contact, showing significant potential in various applications. Previous deep learning based rPPG measurement are primarily based on CNNs and Transformers. However, the limited receptive fields of CNNs restrict their ability to capture long-range spatio-temporal dependencies, while Transformers also struggle with modeling long video sequences with high complexity. Recently, the state space models (SSMs) represented by Mamba are known for their impressive performance on capturing long-range dependencies from long sequences. In this paper, we propose the PhysMamba, a Mamba-based framework, to efficiently represent long-range physiological dependencies from facial videos. Specifically, we introduce the Temporal Difference Mamba block to first enhance local dynamic differences and further model the long-range spatio-temporal context. Moreover, a dual-stream SlowFast architecture is utilized to fuse the multi-scale temporal features. Extensive experiments are conducted on three benchmark datasets to demonstrate the superiority and efficiency of PhysMamba. The codes are available at https://github.com/Chaoqi31/PhysMamba

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://github.com/XieYiping66/SFDA-rPPG

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations.

DiffFAS: Face Anti-Spoofing via Generative Diffusion Models

Face anti-spoofing (FAS) plays a vital role in preventing face recognition (FR) systems from presentation attacks. Nowadays, FAS systems face the challenge of domain shift, impacting the generalization performance of existing FAS methods. In this paper, we rethink about the inherence of domain shift and deconstruct it into two factors: image style and image quality. Quality influences the purity of the presentation of spoof information, while style affects the manner in which spoof information is presented. Based on our analysis, we propose DiffFAS framework, which quantifies quality as prior information input into the network to counter image quality shift, and performs diffusion-based high-fidelity cross-domain and cross-attack types generation to counter image style shift. DiffFAS transforms easily collectible live faces into high-fidelity attack faces with precise labels while maintaining consistency between live and spoof face identities, which can also alleviate the scarcity of labeled data with novel type attacks faced by nowadays FAS system. We demonstrate the effectiveness of our framework on challenging cross-domain and cross-attack FAS datasets, achieving the state-of-the-art performance. Available at https://github.com/murphytju/DiffFAS.

Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis

Face Anti-Spoofing (FAS) research is challenged by the cross-domain problem, where there is a domain gap between the training and testing data. While recent FAS works are mainly model-centric, focusing on developing domain generalization algorithms for improving cross-domain performance, data-centric research for face anti-spoofing, improving generalization from data quality and quantity, is largely ignored. Therefore, our work starts with data-centric FAS by conducting a comprehensive investigation from the data perspective for improving cross-domain generalization of FAS models. More specifically, at first, based on physical procedures of capturing and recapturing, we propose task-specific FAS data augmentation (FAS-Aug), which increases data diversity by synthesizing data of artifacts, such as printing noise, color distortion, moir\'e pattern, \textit{etc}. Our experiments show that using our FAS augmentation can surpass traditional image augmentation in training FAS models to achieve better cross-domain performance. Nevertheless, we observe that models may rely on the augmented artifacts, which are not environment-invariant, and using FAS-Aug may have a negative effect. As such, we propose Spoofing Attack Risk Equalization (SARE) to prevent models from relying on certain types of artifacts and improve the generalization performance. Last but not least, our proposed FAS-Aug and SARE with recent Vision Transformer backbones can achieve state-of-the-art performance on the FAS cross-domain generalization protocols. The implementation is available at https://github.com/RizhaoCai/FAS_Aug.

TRRG: Towards Truthful Radiology Report Generation With Cross-modal Disease Clue Enhanced Large Language Model

The vision-language modeling capability of multi-modal large language models has attracted wide attention from the community. However, in medical domain, radiology report generation using vision-language models still faces significant challenges due to the imbalanced data distribution caused by numerous negated descriptions in radiology reports and issues such as rough alignment between radiology reports and radiography. In this paper, we propose a truthful radiology report generation framework, namely TRRG, based on stage-wise training for cross-modal disease clue injection into large language models. In pre-training stage, During the pre-training phase, contrastive learning is employed to enhance the ability of visual encoder to perceive fine-grained disease details. In fine-tuning stage, the clue injection module we proposed significantly enhances the disease-oriented perception capability of the large language model by effectively incorporating the robust zero-shot disease perception. Finally, through the cross-modal clue interaction module, our model effectively achieves the multi-granular interaction of visual embeddings and an arbitrary number of disease clue embeddings. This significantly enhances the report generation capability and clinical effectiveness of multi-modal large language models in the field of radiology reportgeneration. Experimental results demonstrate that our proposed pre-training and fine-tuning framework achieves state-of-the-art performance in radiology report generation on datasets such as IU-Xray and MIMIC-CXR. Further analysis indicates that our proposed method can effectively enhance the model to perceive diseases and improve its clinical effectiveness.

EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning

Facial expression recognition (FER) is an important research topic in emotional artificial intelligence. In recent decades, researchers have made remarkable progress. However, current FER paradigms face challenges in generalization, lack semantic information aligned with natural language, and struggle to process both images and videos within a unified framework, making their application in multimodal emotion understanding and human-computer interaction difficult. Multimodal Large Language Models (MLLMs) have recently achieved success, offering advantages in addressing these issues and potentially overcoming the limitations of current FER paradigms. However, directly applying pre-trained MLLMs to FER still faces several challenges. Our zero-shot evaluations of existing open-source MLLMs on FER indicate a significant performance gap compared to GPT-4V and current supervised state-of-the-art (SOTA) methods. In this paper, we aim to enhance MLLMs' capabilities in understanding facial expressions. We first generate instruction data for five FER datasets with Gemini. We then propose a novel MLLM, named EMO-LLaMA, which incorporates facial priors from a pretrained facial analysis network to enhance human facial information. Specifically, we design a Face Info Mining module to extract both global and local facial information. Additionally, we utilize a handcrafted prompt to introduce age-gender-race attributes, considering the emotional differences across different human groups. Extensive experiments show that EMO-LLaMA achieves SOTA-comparable or competitive results across both static and dynamic FER datasets. The instruction dataset and code are available at https://github.com/xxtars/EMO-LLaMA.

DAAD: Dynamic Analysis and Adaptive Discriminator for Fake News Detection

In current web environment, fake news spreads rapidly across online social networks, posing serious threats to society. Existing multimodal fake news detection (MFND) methods can be classified into knowledge-based and semantic-based approaches. However, these methods are overly dependent on human expertise and feedback, lacking flexibility. To address this challenge, we propose a Dynamic Analysis and Adaptive Discriminator (DAAD) approach for fake news detection. For knowledge-based methods, we introduce the Monte Carlo Tree Search (MCTS) algorithm to leverage the self-reflective capabilities of large language models (LLMs) for prompt optimization, providing richer, domain-specific details and guidance to the LLMs, while enabling more flexible integration of LLM comment on news content. For semantic-based methods, we define four typical deceit patterns: emotional exaggeration, logical inconsistency, image manipulation, and semantic inconsistency, to reveal the mechanisms behind fake news creation. To detect these patterns, we carefully design four discriminators and expand them in depth and breadth, using the soft-routing mechanism to explore optimal detection models. Experimental results on three real-world datasets demonstrate the superiority of our approach. The code will be available at: https://github.com/SuXinqi/DAAD.

G$^2$V$^2$former: Graph Guided Video Vision Transformer for Face Anti-Spoofing

In videos containing spoofed faces, we may uncover the spoofing evidence based on either photometric or dynamic abnormality, even a combination of both. Prevailing face anti-spoofing (FAS) approaches generally concentrate on the single-frame scenario, however, purely photometric-driven methods overlook the dynamic spoofing clues that may be exposed over time. This may lead FAS systems to conclude incorrect judgments, especially in cases where it is easily distinguishable in terms of dynamics but challenging to discern in terms of photometrics. To this end, we propose the Graph Guided Video Vision Transformer (G$^2$V$^2$former), which combines faces with facial landmarks for photometric and dynamic feature fusion. We factorize the attention into space and time, and fuse them via a spatiotemporal block. Specifically, we design a novel temporal attention called Kronecker temporal attention, which has a wider receptive field, and is beneficial for capturing dynamic information. Moreover, we leverage the low-semantic motion of facial landmarks to guide the high-semantic change of facial expressions based on the motivation that regions containing landmarks may reveal more dynamic clues. Extensive experiments on nine benchmark datasets demonstrate that our method achieves superior performance under various scenarios. The codes will be released soon.