Search

This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples. However, prevailing methods methods in few-shot SED predominantly rely on segment-level predictions, which often providing detailed, fine-grained predictions, particularly for events of brief duration. Although frame-level prediction strategies have been proposed to overcome these limitations, these strategies commonly face difficulties with prediction truncation caused by background noise. To alleviate this issue, we introduces an innovative multitask frame-level SED framework. In addition, we introduce TimeFilterAug, a linear timing mask for data augmentation, to increase the model's robustness and adaptability to diverse acoustic environments. The proposed method achieves a F-score of 63.8%, securing the 1st rank in the few-shot bioacoustic event detection category of the Detection and Classification of Acoustic Scenes and Events Challenge 2023., Comment: 6 pages, 4 figures, conference

This paper uses approximate analytical formulas and numerical results with the bino-dominated dark matter (DM) as an example to analyze the impact of the LUX-ZEPLIN (LZ) experiment on the DM phenomenology and naturalness in the Minimal Supersymmetric Standard Model (MSSM). We conclude that the limitation of the latest LZ experiment worsens the naturalness of the MSSM, as the predictions of the $Z$-boson mass and DM relic density demonstrate, particularly in the regions where the correct DM relic density is obtained by the $Z$- or $h$-mediated resonant annihilations., Comment: 17 pages, 6 figures

In this work, we introduce an iterative decoupled algorithm designed for addressing the quasi-static multiple-network poroelasticity problem. This problem pertains to the simultaneous modeling of fluid flow and deformations within an elastic porous medium permeated by multiple fluid networks, each with distinct characteristics. Our approach focuses on the total-pressure-based formulation, which treats the solid displacement, total pressure, and network pressures as primary unknowns. This formulation transforms the original problem into a combination of the generalized Stokes problem and the parabolic problem, offering certain advantages such as mitigating elastic locking effects and streamlining the discretization process. Notably, the algorithm ensures unconditional convergence to the solution of the total-pressure-based coupled algorithm. To validate the accuracy and efficiency of our method, we present numerical experiments. The robustness of the algorithm with respect to the physical parameters and the discretization parameters is carefully investigated., Comment: to be submitted

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress in tackling complex multimodal tasks. Among these cutting-edge developments, Google's Bard stands out for its remarkable multimodal capabilities, promoting comprehensive comprehension and reasoning across various domains. This work presents an early and holistic evaluation of LVLMs' multimodal abilities, with a particular focus on Bard, by proposing a lightweight variant of LVLM-eHub, named Tiny LVLM-eHub. In comparison to the vanilla version, Tiny LVLM-eHub possesses several appealing properties. Firstly, it provides a systematic assessment of six categories of multimodal capabilities, including visual perception, visual knowledge acquisition, visual reasoning, visual commonsense, object hallucination, and embodied intelligence, through quantitative evaluation of $42$ standard text-related visual benchmarks. Secondly, it conducts an in-depth analysis of LVLMs' predictions using the ChatGPT Ensemble Evaluation (CEE), which leads to a robust and accurate evaluation and exhibits improved alignment with human evaluation compared to the word matching approach. Thirdly, it comprises a mere $2.1$K image-text pairs, facilitating ease of use for practitioners to evaluate their own offline LVLMs. Through extensive experimental analysis, this study demonstrates that Bard outperforms previous LVLMs in most multimodal capabilities except object hallucination, to which Bard is still susceptible. Tiny LVLM-eHub serves as a baseline evaluation for various LVLMs and encourages innovative strategies aimed at advancing multimodal techniques. Our project is publicly available at \url{https://github.com/OpenGVLab/Multi-Modality-Arena}., Comment: accepted to IEEE Transactions on Big Data. Project Page: http://lvlm-ehub.opengvlab.com/

Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of publicly available large multimodal models by building a LVLM evaluation Hub (LVLM-eHub). Our LVLM-eHub consists of $8$ representative LVLMs such as InstructBLIP and MiniGPT-4, which are thoroughly evaluated by a quantitative capability evaluation and an online arena platform. The former evaluates $6$ categories of multimodal capabilities of LVLMs such as visual question answering and embodied artificial intelligence on $47$ standard text-related visual benchmarks, while the latter provides the user-level evaluation of LVLMs in an open-world question-answering scenario. The study reveals several innovative findings. First, instruction-tuned LVLM with massive in-domain data such as InstructBLIP heavily overfits many existing tasks, generalizing poorly in the open-world scenario. Second, instruction-tuned LVLM with moderate instruction-following data may result in object hallucination issues (i.e., generate objects that are inconsistent with target images in the descriptions). It either makes the current evaluation metric such as CIDEr for image captioning ineffective or generates wrong answers. Third, employing a multi-turn reasoning evaluation framework can mitigate the issue of object hallucination, shedding light on developing an effective pipeline for LVLM evaluation. The findings provide a foundational framework for the conception and assessment of innovative strategies aimed at enhancing zero-shot multimodal techniques. Our LVLM-eHub will be available at https://github.com/OpenGVLab/Multi-Modality-Arena, Comment: 28 pages, 10 figures, a comprehensive evaluation of large vision-language models

Breast ultrasound videos contain richer information than ultrasound images, therefore it is more meaningful to develop video models for this diagnosis task. However, the collection of ultrasound video datasets is much harder. In this paper, we explore the feasibility of enhancing the performance of ultrasound video classification using the static image dataset. To this end, we propose KGA-Net and coherence loss. The KGA-Net adopts both video clips and static images to train the network. The coherence loss uses the feature centers generated by the static images to guide the frame attention in the video model. Our KGA-Net boosts the performance on the public BUSV dataset by a large margin. The visualization results of frame attention prove the explainability of our method. The codes and model weights of our method will be made publicly available., Comment: Medical Image Computing and Computer-Assisted Intervention 2023

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is a fundamental problem in 3D perception. Compared with the customized sparse convolution, the attention mechanism in Transformers is more appropriate for flexibly modeling long-range relationships and is easier to be deployed in real-world applications. However, due to the sparse characteristics of point clouds, it is non-trivial to apply a standard transformer on sparse points. In this paper, we present Dynamic Sparse Voxel Transformer (DSVT), a single-stride window-based voxel Transformer backbone for outdoor 3D perception. In order to efficiently process sparse points in parallel, we propose Dynamic Sparse Window Attention, which partitions a series of local regions in each window according to its sparsity and then computes the features of all regions in a fully parallel manner. To allow the cross-set connection, we design a rotated set partitioning strategy that alternates between two partitioning configurations in consecutive self-attention layers. To support effective downsampling and better encode geometric information, we also propose an attention-style 3D pooling module on sparse points, which is powerful and deployment-friendly without utilizing any customized CUDA operations. Our model achieves state-of-the-art performance with a broad range of 3D perception tasks. More importantly, DSVT can be easily deployed by TensorRT with real-time inference speed (27Hz). Code will be available at \url{https://github.com/Haiyang-W/DSVT}., Comment: Accepted by CVPR2023

Brain-Computer Interface (BCI) system provides a pathway between humans and the outside world by analyzing brain signals which contain potential neural information. Electroencephalography (EEG) is one of most commonly used brain signals and EEG recognition is an important part of BCI system. Recently, convolutional neural networks (ConvNet) in deep learning are becoming the new cutting edge tools to tackle the problem of EEG recognition. However, training an effective deep learning model requires a big number of data, which limits the application of EEG datasets with a small number of samples. In order to solve the issue of data insufficiency in deep learning for EEG decoding, we propose a novel data augmentation method that add perturbations to amplitudes of EEG signals after transform them to frequency domain. In experiments, we explore the performance of signal recognition with the state-of-the-art models before and after data augmentation on BCI Competition IV dataset 2a and our local dataset. The results show that our data augmentation technique can improve the accuracy of EEG recognition effectively.