Search

Due to the challenges in acquiring paired Text-3D data and the inherent irregularity of 3D data structures, combined representation learning of 3D point clouds and text remains unexplored. In this paper, we propose a novel Riemann-based Multi-scale Attention Reasoning Network (RMARN) for text-3D retrieval. Specifically, the extracted text and point cloud features are refined by their respective Adaptive Feature Refiner (AFR). Furthermore, we introduce the innovative Riemann Local Similarity (RLS) module and the Global Pooling Similarity (GPS) module. However, as 3D point cloud data and text data often possess complex geometric structures in high-dimensional space, the proposed RLS employs a novel Riemann Attention Mechanism to reflect the intrinsic geometric relationships of the data. Without explicitly defining the manifold, RMARN learns the manifold parameters to better represent the distances between text-point cloud samples. To address the challenges of lacking paired text-3D data, we have created the large-scale Text-3D Retrieval dataset T3DR-HIT, which comprises over 3,380 pairs of text and point cloud data. T3DR-HIT contains coarse-grained indoor 3D scenes and fine-grained Chinese artifact scenes, consisting of 1,380 and over 2,000 text-3D pairs, respectively. Experiments on our custom datasets demonstrate the superior performance of the proposed method. Our code and proposed datasets are available at \url{https://github.com/liwrui/RMARN}.

Text-driven 3D scene generation has seen significant advancements recently. However, most existing methods generate single-view images using generative models and then stitch them together in 3D space. This independent generation for each view often results in spatial inconsistency and implausibility in the 3D scenes. To address this challenge, we proposed a novel text-driven 3D-consistent scene generation model: SceneDreamer360. Our proposed method leverages a text-driven panoramic image generation model as a prior for 3D scene generation and employs 3D Gaussian Splatting (3DGS) to ensure consistency across multi-view panoramic images. Specifically, SceneDreamer360 enhances the fine-tuned Panfusion generator with a three-stage panoramic enhancement, enabling the generation of high-resolution, detail-rich panoramic images. During the 3D scene construction, a novel point cloud fusion initialization method is used, producing higher quality and spatially consistent point clouds. Our extensive experiments demonstrate that compared to other methods, SceneDreamer360 with its panoramic image generation and 3DGS can produce higher quality, spatially consistent, and visually appealing 3D scenes from any text prompt. Our codes are available at \url{https://github.com/liwrui/SceneDreamer360}.

Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via adversarial attacks is crucial in this field. Most multimodal attacks are sample-specific, generating a unique perturbation for each sample to construct adversarial samples. To the best of our knowledge, it is the first work through multimodal decision boundaries to explore the creation of a universal, sample-agnostic perturbation that applies to any image. Initially, we explore strategies to move sample points beyond the decision boundaries of linear classifiers, refining the algorithm to ensure successful attacks under the top $k$ accuracy metric. Based on this foundation, in visual-language tasks, we treat visual and textual modalities as reciprocal sample points and decision hyperplanes, guiding image embeddings to traverse text-constructed decision boundaries, and vice versa. This iterative process consistently refines a universal perturbation, ultimately identifying a singular direction within the input space which is exploitable to impair the retrieval performance of VLP models. The proposed algorithms support the creation of global perturbations or adversarial patches. Comprehensive experiments validate the effectiveness of our method, showcasing its data, task, and model transferability across various VLP models and datasets. Code: https://github.com/LibertazZ/MUAP, Comment: 13 pages, 8 figures, published in ACMMM2024

With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal V+L downstream tasks. The security vulnerabilities of unimodal models have been extensively examined, whereas those of VLP models remain challenging. We note that in CV models, the understanding of images comes from annotated information, while VLP models are designed to learn image representations directly from raw text. Motivated by this discrepancy, we developed the Feature Guidance Attack (FGA), a novel method that uses text representations to direct the perturbation of clean images, resulting in the generation of adversarial images. FGA is orthogonal to many advanced attack strategies in the unimodal domain, facilitating the direct application of rich research findings from the unimodal to the multimodal scenario. By appropriately introducing text attack into FGA, we construct Feature Guidance with Text Attack (FGA-T). Through the interaction of attacking two modalities, FGA-T achieves superior attack effects against VLP models. Moreover, incorporating data augmentation and momentum mechanisms significantly improves the black-box transferability of FGA-T. Our method demonstrates stable and effective attack capabilities across various datasets, downstream tasks, and both black-box and white-box settings, offering a unified baseline for exploring the robustness of VLP models., Comment: 14 pages, 9 figures, published in ACMMM2024(oral)

The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is introduced to dynamically synthesis the subsequent inference information. To guide the formation of input membrane potentials and reduce the spike noise, we propose a global-local pooling (GLP) which combines the max and average pooling operations. Furthermore, the thresholds of the spiking neurons are dynamically adjusted based on semantic and temporal cues. Integrating the temporal and semantic information extracted by SNNs and Transformers are difficult due to the increased number of parameters in a straightforward bilinear model. To address this, we introduce a temporal-semantic Tucker fusion module, which achieves multi-scale fusion of SNN and Transformer outputs while maintaining full second-order interactions. Our experimental results demonstrate the effectiveness of the proposed approach in achieving state-of-the-art performance in three benchmark datasets. The harmonic mean (HM) improvement of VGGSound, UCF101 and ActivityNet are around 15.4\%, 3.9\%, and 14.9\%, respectively., Comment: Accepted by TIP

The Audio-Visual Question Answering (AVQA) task holds significant potential for applications. Compared to traditional unimodal approaches, the multi-modal input of AVQA makes feature extraction and fusion processes more challenging. Euclidean space is difficult to effectively represent multi-dimensional relationships of data. Especially when extracting and processing data with a tree structure or hierarchical structure, Euclidean space is not suitable as an embedding space. Additionally, the self-attention mechanism in Transformers is effective in capturing the dynamic relationships between elements in a sequence. However, the self-attention mechanism's limitations in window modeling and quadratic computational complexity reduce its effectiveness in modeling long sequences. To address these limitations, we propose SHMamba: Structured Hyperbolic State Space Model to integrate the advantages of hyperbolic geometry and state space models. Specifically, SHMamba leverages the intrinsic properties of hyperbolic space to represent hierarchical structures and complex relationships in audio-visual data. Meanwhile, the state space model captures dynamic changes over time by globally modeling the entire sequence. Furthermore, we introduce an adaptive curvature hyperbolic alignment module and a cross fusion block to enhance the understanding of hierarchical structures and the dynamic exchange of cross-modal information, respectively. Extensive experiments demonstrate that SHMamba outperforms previous methods with fewer parameters and computational costs. Our learnable parameters are reduced by 78.12\%, while the average performance improves by 2.53\%. Experiments show that our method demonstrates superiority among all current major methods and is more suitable for practical application scenarios.

Causal discovery based on observational data is important for deciphering the causal mechanism behind complex systems. However, the effectiveness of existing causal discovery methods is limited due to inferior prior knowledge, domain inconsistencies, and the challenges of high-dimensional datasets with small sample sizes. To address this gap, we propose a novel weakly-supervised fuzzy knowledge and data co-driven causal discovery method named KEEL. KEEL adopts a fuzzy causal knowledge schema to encapsulate diverse types of fuzzy knowledge, and forms corresponding weakened constraints. This schema not only lessens the dependency on expertise but also allows various types of limited and error-prone fuzzy knowledge to guide causal discovery. It can enhance the generalization and robustness of causal discovery, especially in high-dimensional and small-sample scenarios. In addition, we integrate the extended linear causal model (ELCM) into KEEL for dealing with the multi-distribution and incomplete data. Extensive experiments with different datasets demonstrate the superiority of KEEL over several state-of-the-art methods in accuracy, robustness and computational efficiency. For causal discovery in real protein signal transduction processes, KEEL outperforms the benchmark method with limited data. In summary, KEEL is effective to tackle the causal discovery tasks with higher accuracy while alleviating the requirement for extensive domain expertise.

This paper introduces a cooperative sensing framework designed for integrated sensing and communication cellular networks. The framework comprises one base station (BS) functioning as the sensing transmitter, while several nearby BSs act as sensing receivers. The primary objective is to facilitate cooperative target localization by enabling each receiver to share specific information with a fusion center (FC) over a limited capacity backhaul link. To achieve this goal, we propose an advanced cooperative sensing design that enhances the communication process between the receivers and the FC. Each receiver independently estimates the time delay and the reflecting coefficient associated with the reflected path from the target. Subsequently, each receiver transmits the estimated values and the received signal samples centered around the estimated time delay to the FC. To efficiently quantize the signal samples, a Karhunen-Lo\`eve Transform coding scheme is employed. Furthermore, an optimization problem is formulated to allocate backhaul resources for quantizing different samples, improving target localization. Numerical results validate the effectiveness of our proposed advanced design and demonstrate its superiority over a baseline design, where only the locally estimated values are transmitted from each receiver to the FC., Comment: This paper has been published in 2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)

Temporal video grounding (TVG) is a critical task in video content understanding, requiring precise alignment between video content and natural language instructions. Despite significant advancements, existing methods face challenges in managing confidence bias towards salient objects and capturing long-term dependencies in video sequences. To address these issues, we introduce SpikeMba: a multi-modal spiking saliency mamba for temporal video grounding. Our approach integrates Spiking Neural Networks (SNNs) with state space models (SSMs) to leverage their unique advantages in handling different aspects of the task. Specifically, we use SNNs to develop a spiking saliency detector that generates the proposal set. The detector emits spike signals when the input signal exceeds a predefined threshold, resulting in a dynamic and binary saliency proposal set. To enhance the model's capability to retain and infer contextual information, we introduce relevant slots which learnable tensors that encode prior knowledge. These slots work with the contextual moment reasoner to maintain a balance between preserving contextual information and exploring semantic relevance dynamically. The SSMs facilitate selective information propagation, addressing the challenge of long-term dependency in video content. By combining SNNs for proposal generation and SSMs for effective contextual reasoning, SpikeMba addresses confidence bias and long-term dependencies, thereby significantly enhancing fine-grained multimodal relationship capture. Our experiments demonstrate the effectiveness of SpikeMba, which consistently outperforms state-of-the-art methods across mainstream benchmarks.

Multimodal intent recognition poses significant challenges, requiring the incorporation of non-verbal modalities from real-world contexts to enhance the comprehension of human intentions. Existing benchmark datasets are limited in scale and suffer from difficulties in handling out-of-scope samples that arise in multi-turn conversational interactions. We introduce MIntRec2.0, a large-scale benchmark dataset for multimodal intent recognition in multi-party conversations. It contains 1,245 dialogues with 15,040 samples, each annotated within a new intent taxonomy of 30 fine-grained classes. Besides 9,304 in-scope samples, it also includes 5,736 out-of-scope samples appearing in multi-turn contexts, which naturally occur in real-world scenarios. Furthermore, we provide comprehensive information on the speakers in each utterance, enriching its utility for multi-party conversational research. We establish a general framework supporting the organization of single-turn and multi-turn dialogue data, modality feature extraction, multimodal fusion, as well as in-scope classification and out-of-scope detection. Evaluation benchmarks are built using classic multimodal fusion methods, ChatGPT, and human evaluators. While existing methods incorporating nonverbal information yield improvements, effectively leveraging context information and detecting out-of-scope samples remains a substantial challenge. Notably, large language models exhibit a significant performance gap compared to humans, highlighting the limitations of machine learning methods in the cognitive intent understanding task. We believe that MIntRec2.0 will serve as a valuable resource, providing a pioneering foundation for research in human-machine conversational interactions, and significantly facilitating related applications. The full dataset and codes are available at https://github.com/thuiar/MIntRec2.0., Comment: Accepted by ICLR 2024, Long Paper; The abstract is slightly modified due to the length limitation

Location awareness is a critical issue in wireless sensor network applications. For more accurate location estimation, the two issues should be considered extensively: 1) how to sufficiently utilize the connection information between multiple nodes and 2) how to select a suitable solution from multiple solutions obtained by the Euclidean distance loss. In this paper, a DV-Hop localization based on the distance estimation using multinode (DEMN) and the hop loss in WSNs is proposed to address the two issues. In DEMN, when multiple anchor nodes can detect an unknown node, the distance expectation between the unknown node and an anchor node is calculated using the cross-domain information and is considered as the expected distance between them, which narrows the search space. When minimizing the traditional Euclidean distance loss, multiple solutions may exist. To select a suitable solution, the hop loss is proposed, which minimizes the difference between the real and its predicted hops. Finally, the Euclidean distance loss calculated by the DEMN and the hop loss are embedded into the multi-objective optimization algorithm. The experimental results show that the proposed method gains 86.11\% location accuracy in the randomly distributed network, which is 6.05% better than the DEM-DV-Hop, while DEMN and the hop loss can contribute 2.46% and 3.41%, respectively.

Localization is one of the pivotal issues in wireless sensor network applications. In 3D localization studies, most algorithms focus on enhancing the location prediction process, lacking theoretical derivation of the detection distance of an anchor node at the varying hops, engenders a localization performance bottleneck. To address this issue, we propose a probability-based average distance estimation (PADE) model that utilizes the probability distribution of node distances detected by an anchor node. The aim is to mathematically derive the average distances of nodes detected by an anchor node at different hops. First, we develop a probability-based maximum distance estimation (PMDE) model to calculate the upper bound of the distance detected by an anchor node. Then, we present the PADE model, which relies on the upper bound obtained of the distance by the PMDE model. Finally, the obtained average distance is used to construct a distance loss function, and it is embedded with the traditional distance loss function into a multi-objective genetic algorithm to predict the locations of unknown nodes. The experimental results demonstrate that the proposed method achieves state-of-the-art performance in random and multimodal distributed sensor networks. The average localization accuracy is improved by 3.49\%-12.66\% and 3.99%-22.34%, respectively.

Image-text retrieval which associates different modalities has drawn broad attention due to its excellent research value and broad real-world application. However, most of the existing methods haven't taken the high-level semantic relationships ("style embedding") and common knowledge from multi-modalities into full consideration. To this end, we introduce a novel style transformer network with common knowledge optimization (CKSTN) for image-text retrieval. The main module is the common knowledge adaptor (CKA) with both the style embedding extractor (SEE) and the common knowledge optimization (CKO) modules. Specifically, the SEE uses the sequential update strategy to effectively connect the features of different stages in SEE. The CKO module is introduced to dynamically capture the latent concepts of common knowledge from different modalities. Besides, to get generalized temporal common knowledge, we propose a sequential update strategy to effectively integrate the features of different layers in SEE with previous common feature units. CKSTN demonstrates the superiorities of the state-of-the-art methods in image-text retrieval on MSCOCO and Flickr30K datasets. Moreover, CKSTN is constructed based on the lightweight transformer which is more convenient and practical for the application of real scenes, due to the better performance and lower parameters.

As computational tools for X-ray computed tomography (CT) become more quantitatively accurate, knowledge of the source-detector spectral response is critical for quantitative system-independent reconstruction and material characterization capabilities. Directly measuring the spectral response of a CT system is hard, which motivates spectral estimation using transmission data obtained from a collection of known homogeneous objects. However, the associated inverse problem is ill-conditioned, making accurate estimation of the spectrum challenging, particularly in the absence of a close initial guess. In this paper, we describe a dictionary-based spectral estimation method that yields accurate results without the need for any initial estimate of the spectral response. Our method utilizes a MAP estimation framework that combines a physics-based forward model along with an $L_0$ sparsity constraint and a simplex constraint on the dictionary coefficients. Our method uses a greedy support selection method and a new pair-wise iterated coordinate descent method to compute the above estimate. We demonstrate that our dictionary-based method outperforms a state-of-the-art method as shown in a cross-validation experiment on four real datasets collected at beamline 8.3.2 of the Advanced Light Source (ALS)., Comment: Document Release Number: LLNL-CONF-845171 Submitted to 2023 ICIP conference

Sparse-view CT reconstruction is important in a wide range of applications due to limitations on cost, acquisition time, or dosage. However, traditional direct reconstruction methods such as filtered back-projection (FBP) lead to low-quality reconstructions in the sub-Nyquist regime. In contrast, deep neural networks (DNNs) can produce high-quality reconstructions from sparse and noisy data, e.g. through post-processing of FBP reconstructions, as can model-based iterative reconstruction (MBIR), albeit at a higher computational cost. In this paper, we introduce a direct-reconstruction DNN method called Recurrent Stacked Back Projection (RSBP) that uses sequentially-acquired backprojections of individual views as input to a recurrent convolutional LSTM network. The SBP structure maintains all information in the sinogram, while the recurrent processing exploits the correlations between adjacent views and produces an updated reconstruction after each new view. We train our network on simulated data and test on both simulated and real data and demonstrate that RSBP outperforms both DNN post-processing of FBP images and basic MBIR, with a lower computational cost than MBIR., Comment: 5 pages, 5 pages, 2021 Asilomar Conference on Signals, Systems, and Computers

It has long been a recognized problem that many datasets contain significant levels of missing numerical data. A potentially critical predicate for application of machine learning methods to datasets involves addressing this problem. However, this is a challenging task. In this paper, we apply a recently developed multi-level stochastic optimization approach to the problem of imputation in massive medical records. The approach is based on computational applied mathematics techniques and is highly accurate. In particular, for the Best Linear Unbiased Predictor (BLUP) this multi-level formulation is exact, and is significantly faster and more numerically stable. This permits practical application of Kriging methods to data imputation problems for massive datasets. We test this approach on data from the National Inpatient Sample (NIS) data records, Healthcare Cost and Utilization Project (HCUP), Agency for Healthcare Research and Quality. Numerical results show that the multi-level method significantly outperforms current approaches and is numerically robust. It has superior accuracy as compared with methods recommended in the recent report from HCUP. Benchmark tests show up to 75% reductions in error. Furthermore, the results are also superior to recent state of the art methods such as discriminative deep learning., Comment: 11 pages, 4 figures

Increasingly, there is a marked interest in estimating causal effects under network interference due to the fact that interference manifests naturally in networked experiments. However, network information generally is available only up to some level of error. We study the propagation of such errors to estimators of average causal effects under network interference. Specifically, assuming a four-level exposure model and Bernoulli random assignment of treatment, we characterize the impact of network noise on the bias and variance of standard estimators in homogeneous and inhomogeneous networks. In addition, we propose method-of-moments estimators for bias reduction where a minimal number of network replicates are available. We show our estimators are asymptotically normal and provide confidence intervals for quantifying the uncertainty in these estimates. We illustrate the practical performance of our estimators through simulation studies in British secondary school contact networks., Comment: 68 pages, 1 figure