arXiv subjects

Xin Liu

Publications and source records attributed to Xin Liu.

At least 487 records · Page 27Linked to original sources

arXiv2024

In situ fully vectorial tomography and pupil function retrieval of tightly focused fields

Tightly focused optical fields are essential in nano-optics, but their applications have been limited by the challenges of accurate yet efficient characterization. In this article, we develop an in situ method for reconstructing the fully vectorial information of tightly focused fields in three-dimensional (3D) space, while simultaneously retrieving the pupil functions. Our approach encodes these fields using phase-modulated focusing and polarization-split detection, followed by decoding through an algorithm based on least-sampling matrix-based Fourier transform and analytically derived gradient. We further employ a focus scanning strategy. When combined with our decoding algorithm, this strategy mitigates the imperfections in the detection path. This approach requires only 10 frames of 2D measurements to realize approximate 90% accuracy in tomography and pupil function retrieval within 10s. Thus, it serves as a robust and convenient tool for the precise characterization and optimization of light at the nanoscale. We apply this technique to fully vectorial field manipulation, adaptive-optics-assisted nanoscopy, and addressing mixed-state problems.

physics.optics↗

arXiv2024

From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models

Passively collected behavioral health data from ubiquitous sensors holds significant promise to provide mental health professionals insights from patient's daily lives; however, developing analysis tools to use this data in clinical practice requires addressing challenges of generalization across devices and weak or ambiguous correlations between the measured signals and an individual's mental health. To address these challenges, we take a novel approach that leverages large language models (LLMs) to synthesize clinically useful insights from multi-sensor data. We develop chain of thought prompting methods that use LLMs to generate reasoning about how trends in data such as step count and sleep relate to conditions like depression and anxiety. We first demonstrate binary depression classification with LLMs achieving accuracies of 61.1% which exceed the state of the art. While it is not robust for clinical use, this leads us to our key finding: even more impactful and valued than classification is a new human-AI collaboration approach in which clinician experts interactively query these tools and combine their domain expertise and context about the patient with AI generated reasoning to support clinical decision-making. We find models like GPT-4 correctly reference numerical data 75% of the time, and clinician participants express strong interest in using this approach to interpret self-tracking data.

cs.AI↗

arXiv2024

Technical Report: Coopetition in Heterogeneous Cross-Silo Federated Learning

In cross-silo federated learning (FL), companies collaboratively train a shared global model without sharing heterogeneous data. Prior related work focused on algorithm development to tackle data heterogeneity. However, the dual problem of coopetition, i.e., FL collaboration and market competition, remains under-explored. This paper studies the FL coopetition using a dynamic two-period game model. In period 1, an incumbent company trains a local model and provides model-based services at a chosen price to users. In period 2, an entrant company enters, and both companies decide whether to engage in FL collaboration and then compete in selling model-based services at different prices to users. Analyzing the two-period game is challenging due to data heterogeneity, and that the incumbent's period one pricing has a temporal impact on coopetition in period 2, resulting in a non-concave problem. To address this issue, we decompose the problem into several concave sub-problems and develop an algorithm that achieves a global optimum. Numerical results on three public datasets show two interesting insights. First, FL training brings model performance gain as well as competition loss, and collaboration occurs only when the performance gain outweighs the loss. Second, data heterogeneity can incentivize the incumbent to limit market penetration in period 1 and promote price competition in period 2.

cs.GT↗

arXiv2024

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.

cs.CV↗

arXiv2024

MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learning

With the exponential growth of multimedia data, leveraging multimodal sensors presents a promising approach for improving accuracy in human activity recognition. Nevertheless, accurately identifying these activities using both video data and wearable sensor data presents challenges due to the labor-intensive data annotation, and reliance on external pretrained models or additional data. To address these challenges, we introduce Multimodal Masked Autoencoders-Based One-Shot Learning (Mu-MAE). Mu-MAE integrates a multimodal masked autoencoder with a synchronized masking strategy tailored for wearable sensors. This masking strategy compels the networks to capture more meaningful spatiotemporal features, which enables effective self-supervised pretraining without the need for external data. Furthermore, Mu-MAE leverages the representation extracted from multimodal masked autoencoders as prior information input to a cross-attention multimodal fusion layer. This fusion layer emphasizes spatiotemporal features requiring attention across different modalities while highlighting differences from other classes, aiding in the classification of various classes in metric-based one-shot learning. Comprehensive evaluations on MMAct one-shot classification show that Mu-MAE outperforms all the evaluated approaches, achieving up to an 80.17% accuracy for five-way one-shot multimodal classification, without the use of additional data.

cs.CV↗

arXiv2024

FacialPulse: An Efficient RNN-based Depression Detection via Temporal Facial Landmarks

Depression is a prevalent mental health disorder that significantly impacts individuals' lives and well-being. Early detection and intervention are crucial for effective treatment and management of depression. Recently, there are many end-to-end deep learning methods leveraging the facial expression features for automatic depression detection. However, most current methods overlook the temporal dynamics of facial expressions. Although very recent 3DCNN methods remedy this gap, they introduce more computational cost due to the selection of CNN-based backbones and redundant facial features. To address the above limitations, by considering the timing correlation of facial expressions, we propose a novel framework called FacialPulse, which recognizes depression with high accuracy and speed. By harnessing the bidirectional nature and proficiently addressing long-term dependencies, the Facial Motion Modeling Module (FMMM) is designed in FacialPulse to fully capture temporal features. Since the proposed FMMM has parallel processing capabilities and has the gate mechanism to mitigate gradient vanishing, this module can also significantly boost the training speed. Besides, to effectively use facial landmarks to replace original images to decrease information redundancy, a Facial Landmark Calibration Module (FLCM) is designed to eliminate facial landmark errors to further improve recognition accuracy. Extensive experiments on the AVEC2014 dataset and MMDA dataset (a depression dataset) demonstrate the superiority of FacialPulse on recognition accuracy and speed, with the average MAE (Mean Absolute Error) decreased by 21% compared to baselines, and the recognition speed increased by 100% compared to state-of-the-art methods. Codes are released at https://github.com/volatileee/FacialPulse.

cs.CV↗

arXiv2024

Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond

Non-exemplar class-incremental learning (NECIL) is to resist catastrophic forgetting without saving old class samples. Prior methodologies generally employ simple rules to generate features for replaying, suffering from large distribution gap between replayed features and real ones. To address the aforementioned issue, we propose a simple, yet effective \textbf{Diff}usion-based \textbf{F}eature \textbf{R}eplay (\textbf{DiffFR}) method for NECIL. First, to alleviate the limited representational capacity caused by fixing the feature extractor, we employ Siamese-based self-supervised learning for initial generalizable features. Second, we devise diffusion models to generate class-representative features highly similar to real features, which provides an effective way for exemplar-free knowledge memorization. Third, we introduce prototype calibration to direct the diffusion model's focus towards learning the distribution shapes of features, rather than the entire distribution. Extensive experiments on public datasets demonstrate significant performance gains of our DiffFR, outperforming the state-of-the-art NECIL methods by 3.0\% in average. The code will be made publicly available soon.

cs.CV↗

arXiv2024

From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation

The action anticipation task refers to predicting what action will happen based on observed videos, which requires the model to have a strong ability to summarize the present and then reason about the future. Experience and common sense suggest that there is a significant correlation between different actions, which provides valuable prior knowledge for the action anticipation task. However, previous methods have not effectively modeled this underlying statistical relationship. To address this issue, we propose a novel end-to-end video modeling architecture that utilizes attention mechanisms, named Anticipation via Recognition and Reasoning (ARR). ARR decomposes the action anticipation task into action recognition and sequence reasoning tasks, and effectively learns the statistical relationship between actions by next action prediction (NAP). In comparison to existing temporal aggregation strategies, ARR is able to extract more effective features from observable videos to make more reasonable predictions. In addition, to address the challenge of relationship modeling that requires extensive training data, we propose an innovative approach for the unsupervised pre-training of the decoder, which leverages the inherent temporal dynamics of video to enhance the reasoning capabilities of the network. Extensive experiments on the Epic-kitchen-100, EGTEA Gaze+, and 50salads datasets demonstrate the efficacy of the proposed methods. The code is available at https://github.com/linuxsino/ARR.

cs.CV↗

arXiv2024

Ultrafast bursts of tailored spatiotemporal vortex pulses

Orbital angular momentums (OAMs) of light can be categorized into longitudinal OAM (L-OAM) and transverse OAM (T-OAM). Light carrying time-varying L-OAM, known as self-torqued light, was recently discovered during harmonic generation and has been extensively developed within the context of optical frequency combs (OFCs). Meanwhile, ultrafast bursts of optical pulses, analogous to OFCs, are sought for various light-matter interaction, spectroscopic and nonlinear applications. However, achieving transiently switchable T-OAM of light on request, namely spatiotemporal vortex pulse bursts, with independently controlled spatiotemporal profile of each comb tooth, remain unrealized thus far. In this work, the experimental generation of spatiotemporal vortex bursts featured with controllable time-dependent characteristics is reported. The resultant bursts comprised of spatiotemporal optical vortex comb teeth have picosecond timescale switchable T-OAMs with defined arrangement, manifesting as spatiotemporal torquing of light. We also show ultrafast control of T-OAM chirality, yielding pulse bursts with staggered azimuthal local momentum density, resembling Kármán vortex streets. This approach enables the tailoring of more intricate spatiotemporal wavepacket bursts, such as high-purity modes variation in both radial and azimuthal quantum numbers of spatiotemporal Laguerre-Gaussian wavepackets over time, which may facilitate a host of novel applications in ultrafast light-mater interactions, high-dimensional quantum entanglements, space-time photonic topologies as well as spatiotemporal metrology and photography.

physics.optics↗

arXiv2024

Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter

Deep neural networks (DNNs) have been applied in many computer vision tasks and achieved state-of-the-art (SOTA) performance. However, misclassification will occur when DNNs predict adversarial examples which are created by adding human-imperceptible adversarial noise to natural examples. This limits the application of DNN in security-critical fields. In order to enhance the robustness of models, previous research has primarily focused on the unimodal domain, such as image recognition and video understanding. Although multi-modal learning has achieved advanced performance in various tasks, such as action recognition, research on the robustness of RGB-skeleton action recognition models is scarce. In this paper, we systematically investigate how to improve the robustness of RGB-skeleton action recognition models. We initially conducted empirical analysis on the robustness of different modalities and observed that the skeleton modality is more robust than the RGB modality. Motivated by this observation, we propose the \formatword{A}ttention-based \formatword{M}odality \formatword{R}eweighter (\formatword{AMR}), which utilizes an attention layer to re-weight the two modalities, enabling the model to learn more robust features. Our AMR is plug-and-play, allowing easy integration with multimodal models. To demonstrate the effectiveness of AMR, we conducted extensive experiments on various datasets. For example, compared to the SOTA methods, AMR exhibits a 43.77\% improvement against PGD20 attacks on the NTU-RGB+D 60 dataset. Furthermore, it effectively balances the differences in robustness between different modalities.

cs.CV↗

arXiv2024

Facial Affect Recognition based on Multi Architecture Encoder and Feature Fusion for the ABAW7 Challenge

In this paper, we present our approach to addressing the challenges of the 7th ABAW competition. The competition comprises three sub-challenges: Valence Arousal (VA) estimation, Expression (Expr) classification, and Action Unit (AU) detection. To tackle these challenges, we employ state-of-the-art models to extract powerful visual features. Subsequently, a Transformer Encoder is utilized to integrate these features for the VA, Expr, and AU sub-challenges. To mitigate the impact of varying feature dimensions, we introduce an affine module to align the features to a common dimension. Overall, our results significantly outperform the baselines.

cs.CV↗

arXiv2024

Non-Abelian line graph: A generalized approach to flat bands

Flat bands (FBs) in materials can enhance the correlation effects, resulting in exotic phenomena. Line graph (LG) lattices are well known for hosting FBs with isotropic hoppings in $s$-orbital models. Despite their prevalent application in the Kagome metals, there has been a lack of a general approach for incorporating higher-angular-momentum orbitals with spin-orbit couplings (SOCs) into LGs to achieve FBs. Here, we introduce a non-Abelian LG theory to construct FBs in realistic systems, which incorporates internal degrees of freedom and goes beyond $s$-orbital models. We modify the lattice edges and sites in the LG to be associated with arbitrary Hermitian matrices, referred to as the multiple LG. A fundamental aspect involves mapping the multiple LG Hamiltonian to a tight-binding (TB) model that respects the lattice symmetry through appropriate local non-Abelian transformations. We establish the general conditions to determine the local transformations. Based on this mechanism, we demonstrate the realization of $d$-orbital FBs in the Kagome lattice, which could serve as a minimal model for understanding the FBs in transition metal Kagome materials. Our approach bridges the gap between the known FBs in pure lattice models and their realization in multi-orbital systems.

cond-mat.mes-hall↗

arXiv2024

Multi-modal Attribute Prompting for Vision-Language Models

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet overlooking multi-modal attribute characteristics. This limitation hinders the model's ability to perceive fine-grained visual details and restricts its generalization ability to a broader range of unseen classes. To address this issue, we propose a Multi-modal Attribute Prompting method (MAP) by jointly exploring textual attribute prompting, visual attribute prompting, and attribute-level alignment. The proposed MAP enjoys several merits. First, we introduce learnable visual attribute prompts enhanced by textual attribute semantics to adaptively capture visual attributes for images from unknown categories, boosting fine-grained visual perception capabilities for CLIP. Second, the proposed attribute-level alignment complements the global alignment to enhance the robustness of cross-modal alignment for open-vocabulary objects. To our knowledge, this is the first work to establish cross-modal attribute-level alignment for CLIP-based few-shot adaptation. Extensive experimental results on 11 datasets demonstrate that our method performs favorably against state-of-the-art approaches.

cs.CV↗

arXiv2024

AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors

Facial Action Units (AU) is a vital concept in the realm of affective computing, and AU detection has always been a hot research topic. Existing methods suffer from overfitting issues due to the utilization of a large number of learnable parameters on scarce AU-annotated datasets or heavy reliance on substantial additional relevant data. Parameter-Efficient Transfer Learning (PETL) provides a promising paradigm to address these challenges, whereas its existing methods lack design for AU characteristics. Therefore, we innovatively investigate PETL paradigm to AU detection, introducing AUFormer and proposing a novel Mixture-of-Knowledge Expert (MoKE) collaboration mechanism. An individual MoKE specific to a certain AU with minimal learnable parameters first integrates personalized multi-scale and correlation knowledge. Then the MoKE collaborates with other MoKEs in the expert group to obtain aggregated information and inject it into the frozen Vision Transformer (ViT) to achieve parameter-efficient AU detection. Additionally, we design a Margin-truncated Difficulty-aware Weighted Asymmetric Loss (MDWA-Loss), which can encourage the model to focus more on activated AUs, differentiate the difficulty of unactivated AUs, and discard potential mislabeled samples. Extensive experiments from various perspectives, including within-domain, cross-domain, data efficiency, and micro-expression domain, demonstrate AUFormer's state-of-the-art performance and robust generalization abilities without relying on additional relevant data. The code for AUFormer is available at https://github.com/yuankaishen2001/AUFormer.

cs.CV↗

arXiv2024

DAVOS: Dwarf Active Galactic Nuclei from Variability for the Origins of Seeds: Properties of Variability-Selected Active Galactic Nuclei in the COSMOS Field and Expectations for the Rubin Observatory

We study the black hole mass $-$ host galaxy stellar mass relation, $M_{\rm{BH}}-M_{\ast}$, of a sample of $z<4$ optically-variable AGNs in the COSMOS field. The parent sample of 491 COSMOS AGNs were identified by optical variability from the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP) program. Using publicly-available catalogs and spectra, we consolidate their spectroscopic redshifts and estimate virial black hole masses using broad line widths and luminosities. We show that variability searches with deep, high precision photometry like the HSC-SSP can identity AGNs in low mass galaxies up to $z\sim1$. However, their black holes are more massive given their host galaxy stellar masses than predicted by the local relation for active galaxies. We report that $z\sim 0.5-4$ variability-selected AGNs are meanwhile more consistent with the $M_{\rm{BH}}-M_{\ast}$ relation for local inactive early-type galaxies. This result is consistent with most previous studies of the $M_{\rm{BH}}-M_{\ast}$ relation at similar redshifts and indicates that AGNs selected from variability are not intrinsically different from the broad-line Type 1 AGN population at similar luminosities. Our results demonstrate the need for robust black hole and stellar mass estimates for intermediate-mass black hole candidates in low-mass galaxies at similar redshifts. Assuming that these results do not reflect a selection bias, they appear to be consistent with self-regulated feedback models wherein the central black hole and stars in galaxies grow in tandem.

astro-ph.GA↗

arXiv2024

EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs

Narrative reasoning relies on the understanding of eventualities in story contexts, which requires a wealth of background world knowledge. To help machines leverage such knowledge, existing solutions can be categorized into two groups. Some focus on implicitly modeling eventuality knowledge by pretraining language models (LMs) with eventuality-aware objectives. However, this approach breaks down knowledge structures and lacks interpretability. Others explicitly collect world knowledge of eventualities into structured eventuality-centric knowledge graphs (KGs). However, existing research on leveraging these knowledge sources for free-texts is limited. In this work, we propose an initial comprehensive framework called EventGround, which aims to tackle the problem of grounding free-texts to eventuality-centric KGs for contextualized narrative reasoning. We identify two critical problems in this direction: the event representation and sparsity problems. We provide simple yet effective parsing and partial information extraction methods to tackle these problems. Experimental results demonstrate that our approach consistently outperforms baseline models when combined with graph neural network (GNN) or large language model (LLM) based graph reasoning models. Our framework, incorporating grounded knowledge, achieves state-of-the-art performance while providing interpretable evidence.

cs.CL↗

arXiv2024

Practical asynchronous measurement-device-independent quantum key distribution with advantage distillation

The advantage distillation (AD) method has proven effective in improving the performance of quantum key distribution (QKD). In this paper, we introduce the AD method into a recently proposed asynchronous measurement-device-independent (AMDI) QKD protocol, taking finite-key effects into account. Simulation results show that the AD method significantly enhances AMDIQKD, e.g., extending the transmission distance by 16 km with a total pulse count of N = 7.24*10^13, and enables AMDI-QKD, previously unable to generate keys, to generate keys with a misalignment error rate of 10%. As the AD method can be directly integrated into the current system through refined post-processing, our results facilitate the practical implementation of AMDI-QKD in various applications, particularly in scenarios with high channel losses and misalignment errors.

quant-ph↗

arXiv2024

DAVIS-Ag: A Synthetic Plant Dataset for Prototyping Domain-Inspired Active Vision in Agricultural Robots

In agricultural environments, viewpoint planning can be a critical functionality for a robot with visual sensors to obtain informative observations of objects of interest (e.g., fruits) from complex structures of plant with random occlusions. Although recent studies on active vision have shown some potential for agricultural tasks, each model has been designed and validated on a unique environment that would not easily be replicated for benchmarking novel methods being developed later. In this paper, we introduce a dataset, so-called DAVIS-Ag, for promoting more extensive research on Domain-inspired Active VISion in Agriculture. To be specific, we leveraged our open-source "AgML" framework and 3D plant simulator of "Helios" to produce 502K RGB images from 30K densely sampled spatial locations in 632 synthetic orchards. Moreover, plant environments of strawberries, tomatoes, and grapes are considered at two different scales (i.e., Single-Plant and Multi-Plant). Useful labels are also provided for each image, including (1) bounding boxes and (2) instance segmentation masks for all identifiable fruits, and also (3) pointers to other images of the viewpoints that are reachable by an execution of action so as to simulate active viewpoint selections at each time step. Using DAVIS-Ag, we visualize motivating examples where fruit visibility can dramatically change depending on the pose of the camera view primarily due to occlusions by other components, such as leaves. Furthermore, we present several baseline models with experiment results for benchmarking in the task of target visibility maximization. Transferability to real strawberry environments is also investigated to demonstrate the feasibility of using the dataset for prototyping real-world solutions. For future research, our dataset is made publicly available online: https://github.com/ctyeong/DAVIS-Ag.

cs.RO↗