Automated mark localization in scatter images, greatly helpful for discovering knowledge and understanding enormous document images and reasoning in visual question answering AI systems, is a highly challenging problem because of the ubiquity of overlapping marks. Locating overlapping marks faces many difficulties such as no texture, less contextual information, hallow shape and tiny size. Here, we formulate it as a combinatorial optimization problem on clustering-based re-visualization from a non-training generative perspective, to locate scatter marks by finding the status of multi-variables when an objective function reaches a minimum. The objective function is constructed on difference between binarized scatter images and corresponding generated re-visualization based on their clustering. Fundamentally, re-visualization tries to generate a new scatter graph only taking a rasterized scatter image as an input, and clustering is employed to provide the information for such re-visualization. This method could stably locate severely-overlapping, variable-size and variable-shape marks in scatter images without dependence of any training dataset or reference. Meanwhile, we propose an adaptive variant of simulated annealing which can works on various connected regions. In addition, we especially built a dataset named SML2023 containing hundreds of scatter images with different markers and various levels of overlapping severity, and tested the proposed method and compared it to existing methods. The results show that it can accurately locate most marks in scatter images with different overlapping severity and marker types, with about 0.3 absolute increase on an assignment-cost-based metric in comparison with state-of-the-art methods. This work is of value to data mining on massive web pages and literatures, and shedding new light on image measurement such as bubble counting.
When handling streaming graphs, existing graph representation learning models encounter a catastrophic forgetting problem, where previously learned knowledge of these models is easily overwritten when learning with newly incoming graphs. In response, Continual Graph Learning emerges as a novel paradigm enabling graph representation learning from static to streaming graphs. Our prior work, CaT is a replay-based framework with a balanced continual learning procedure, which designs a small yet effective memory bank for replaying data by condensing incoming graphs. Although the CaT alleviates the catastrophic forgetting problem, there exist three issues: (1) The graph condensation algorithm derived in CaT only focuses on labelled nodes while neglecting abundant information carried by unlabelled nodes; (2) The continual training scheme of the CaT overemphasises on the previously learned knowledge, limiting the model capacity to learn from newly added memories; (3) Both the condensation process and replaying process of the CaT are time-consuming. In this paper, we propose a psudo-label guided memory bank (PUMA) CGL framework, extending from the CaT to enhance its efficiency and effectiveness by overcoming the above-mentioned weaknesses and limits. To fully exploit the information in a graph, PUMA expands the coverage of nodes during graph condensation with both labelled and unlabelled nodes. Furthermore, a training-from-scratch strategy is proposed to upgrade the previous continual learning scheme for a balanced training between the historical and the new graphs. Besides, PUMA uses a one-time prorogation and wide graph encoders to accelerate the graph condensation and the graph encoding process in the training stage to improve the efficiency of the whole framework. Extensive experiments on four datasets demonstrate the state-of-the-art performance and efficiency over existing methods.
Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera parameters e.g. intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain, yet they are mandatory to triangulate corresponding pixels in 3D space, which is the core of all best performing MVS algorithms. In this work, we take an opposite stance and introduce DUSt3R, a radically novel paradigm for Dense and Unconstrained Stereo 3D Reconstruction of arbitrary image collections, i.e. operating without prior information about camera calibration nor viewpoint poses. We cast the pairwise reconstruction problem as a regression of pointmaps, relaxing the hard constraints of usual projective camera models. We show that this formulation smoothly unifies the monocular and binocular reconstruction cases. In the case where more than two images are provided, we further propose a simple yet effective global alignment strategy that expresses all pairwise pointmaps in a common reference frame. We base our network architecture on standard Transformer encoders and decoders, allowing us to leverage powerful pretrained models. Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera. Exhaustive experiments on all these tasks showcase that the proposed DUSt3R can unify various 3D vision tasks and set new SoTAs on monocular/multi-view depth estimation as well as relative pose estimation. In summary, DUSt3R makes many geometric 3D vision tasks easy.
The next-generation (6G) wireless networks are expected to provide not only seamless and high data-rate communications, but also ubiquitous sensing services. By providing vast spatial degrees of freedom (DoFs), ultra-massive multiple-input multiple-output (UM-MIMO) technology is a key enabler for both sensing and communications in 6G. However, the adoption of UM-MIMO leads to a shift from the far field to the near field in terms of the electromagnetic propagation, which poses novel challenges in system design. Specifically, near-field effects introduce highly non-linear spherical wave models that render existing designs based on plane wave assumptions ineffective. In this paper, we focus on two crucial tasks in sensing and communications, respectively, i.e., localization and channel estimation, and investigate their joint design by exploring the near-field propagation characteristics, achieving mutual benefits between two tasks. In addition, multiple base stations (BSs) are leveraged to collaboratively facilitate a cooperative localization framework. To address the joint channel estimation and cooperative localization problem for near-field UM-MIMO systems, we propose a variational Newtonized near-field channel estimation (VNNCE) algorithm and a Gaussian fusion cooperative localization (GFCL) algorithm. The VNNCE algorithm exploits the spatial DoFs provided by the near-field channel to obtain position-related soft information, while the GFCL algorithm fuses this soft information to achieve more accurate localization. Additionally, we introduce a joint architecture that seamlessly integrates channel estimation and cooperative localization.
Surface electromyography (sEMG) is a widely used muscle activity monitoring technique. sEMG measures muscle activity through monopolar and bipolar, multi-electrode electrodes. The surface electrodes are placed on the surface of the skin above the target muscle and the received signal can be used to infer the state of the muscle - active, inactive or fatigued - which serves as vital information during neurological and orthopaedic rehabilitation. Additionally, the sEMG signal can also be used for the control of prostheses. sEMG requires contact with the participant's skin and is thus a potentially uncomfortable method for the measurement of muscle activity. Moreover, the setup procedure has been termed time-consuming by sEMG experts and is listed as one of the main barriers to the clinical employment of the technique. Previous studies have shown that architectural changes, particularly muscle deformation, can provide information about the activity of the muscle, providing an alternative to sEMG. In all these studies, the muscle deformation signal is acquired using ultrasound imaging, an approach known as sonomyography (SMG). Despite its advantages, such as improved spatial resolution, SMG is still a contact based approach. In this paper, we propose a non-contact muscle activity monitoring approach that measures the muscle deformation signal using a Frequency Modulated Continuous Wave (FMCW) mmWave radar which we call radiomyography (RMG). In future, this system will enable muscle activation to be measured in an unconstrained and less cumbersome manner for both the person conducting the test and the individual being tested.
Effectively leveraging multimodal data such as various images, laboratory tests and clinical information is gaining traction in a variety of AI-based medical diagnosis and prognosis tasks. Most existing multi-modal techniques only focus on enhancing their performance by leveraging the differences or shared features from various modalities and fusing feature across different modalities. These approaches are generally not optimal for clinical settings, which pose the additional challenges of limited training data, as well as being rife with redundant data or noisy modality channels, leading to subpar performance. To address this gap, we study the robustness of existing methods to data redundancy and noise and propose a generalized dynamic multimodal information bottleneck framework for attaining a robust fused feature representation. Specifically, our information bottleneck module serves to filter out the task-irrelevant information and noises in the fused feature, and we further introduce a sufficiency loss to prevent dropping of task-relevant information, thus explicitly preserving the sufficiency of prediction information in the distilled feature. We validate our model on an in-house and a public COVID19 dataset for mortality prediction as well as two public biomedical datasets for diagnostic tasks. Extensive experiments show that our method surpasses the state-of-the-art and is significantly more robust, being the only method to remain performance when large-scale noisy channels exist. Our code is publicly available at https://github.com/BII-wushuang/DMIB.
In recent advancements in spoken question answering (QA), end-to-end models have made significant strides. However, previous research has primarily focused on extractive span selection. While this extractive-based approach is effective when answers are present directly within the input, it falls short in addressing abstractive questions, where answers are not directly extracted but inferred from the given information. To bridge this gap, we introduce the first end-to-end Generative Spoken Question Answering (GSQA) model that empowers the system to engage in abstractive reasoning. The challenge in training our GSQA model lies in the absence of a spoken abstractive QA dataset. We propose using text models for initialization and leveraging the extractive QA dataset to transfer knowledge from the text generative model to the spoken generative model. Experimental results indicate that our model surpasses the previous extractive model by 3% on extractive QA datasets. Furthermore, the GSQA model has only been fine-tuned on the spoken extractive QA dataset. Despite not having seen any spoken abstractive QA data, it can still closely match the performance of the cascade model. In conclusion, our GSQA model shows the potential to generalize to a broad spectrum of questions, thus further expanding the spoken question answering capabilities of abstractive QA. Our code is available at https://voidful.github.io/GSQA
This paper addresses the challenge of 3D instance segmentation by simultaneously leveraging 3D geometric and multi-view image information. Many previous works have applied deep learning techniques to 3D point clouds for instance segmentation. However, these methods often failed to generalize to various types of scenes due to the scarcity and low-diversity of labeled 3D point cloud data. Some recent works have attempted to lift 2D instance segmentations to 3D within a bottom-up framework. The inconsistency in 2D instance segmentations among views can substantially degrade the performance of 3D segmentation. In this work, we introduce a novel 3D-to-2D query framework to effectively exploit 2D segmentation models for 3D instance segmentation. Specifically, we pre-segment the scene into several superpoints in 3D, formulating the task into a graph cut problem. The superpoint graph is constructed based on 2D segmentation models, where node features are obtained from multi-view image features and edge weights are computed based on multi-view segmentation results, enabling the better generalization ability. To process the graph, we train a graph neural network using pseudo 3D labels from 2D segmentation models. Experimental results on the ScanNet, ScanNet++ and KITTI-360 datasets demonstrate that our method achieves robust segmentation performance and can generalize across different types of scenes. Our project page is available at https://zju3dv.github.io/sam_graph.
Vision-and-Language Navigation (VLN) task aims to enable AI agents to accurately understand and follow natural language instructions to navigate through real-world environments, ultimately reaching specific target locations. We recognise a promising opportunity to extend VLN to a comparable navigation task that holds substantial significance in our daily lives, albeit within the virtual realm: navigating websites on the Internet. This paper proposes a new task named Vision-and-Language Navigation on Websites (WebVLN), where we use question-based instructions to train an agent, emulating how users naturally browse websites. Unlike the existing VLN task that only pays attention to vision and instruction (language), the WebVLN agent further considers underlying web-specific content like HTML, which could not be seen on the rendered web pages yet contains rich visual and textual information. Toward this goal, we contribute a dataset, WebVLN-v1, and introduce a novel approach called Website-aware VLN Network (WebVLN-Net), which is built upon the foundation of state-of-the-art VLN techniques. Experimental results show that WebVLN-Net outperforms current VLN and web-related navigation methods. We believe that the introduction of the new WebVLN task and its dataset will establish a new dimension within the VLN domain and contribute to the broader vision-and-language research community. The code is available at: https://github.com/WebVLN/WebVLN.
For robotic decision-making under uncertainty, the balance between exploitation and exploration of available options must be carefully taken into account. In this study, we introduce a new variant of contextual multi-armed bandits called observation-augmented CMABs (OA-CMABs) wherein a decision-making agent can utilize extra outcome observations from an external information source. CMABs model the expected option outcomes as a function of context features and hidden parameters, which are inferred from previous option outcomes. In OA-CMABs, external observations are also a function of context features and thus provide additional evidence about the hidden parameters. Yet, if an external information source is error-prone, the resulting posterior updates can harm decision-making performance unless the presence of errors is considered. To this end, we propose a robust Bayesian inference process for OA-CMABs that is based on the concept of probabilistic data validation. Our approach handles complex mixture model parameter priors and hybrid observation likelihoods for semantic data sources, allowing us to develop validation algorithms based on recently develop probabilistic semantic data association techniques. Furthermore, to more effectively cope with the combined sources of uncertainty in OA-CMABs, we derive a new active inference algorithm for option selection based on expected free energy minimization. This generalizes previous work on active inference for bandit-based robotic decision-making by accounting for faulty observations and non-Gaussian inference. Our approaches are demonstrated on a simulated asynchronous search site selection problem for space exploration. The results show that even if incorrect observations are provided by external information sources, efficient decision-making and robust parameter inference are still achieved in a wide variety of experimental conditions.