arXiv subjects

Dan Guo

Publications and source records attributed to Dan Guo.

At least 109 records · Page 6Linked to original sources

arXiv2023

Dual-path TokenLearner for Remote Photoplethysmography-based Physiological Measurement with Facial Videos

Remote photoplethysmography (rPPG) based physiological measurement is an emerging yet crucial vision task, whose challenge lies in exploring accurate rPPG prediction from facial videos accompanied by noises of illumination variations, facial occlusions, head movements, \etc, in a non-contact manner. Existing mainstream CNN-based models make efforts to detect physiological signals by capturing subtle color changes in facial regions of interest (ROI) caused by heartbeats. However, such models are constrained by the limited local spatial or temporal receptive fields in the neural units. Unlike them, a native Transformer-based framework called Dual-path TokenLearner (Dual-TL) is proposed in this paper, which utilizes the concept of learnable tokens to integrate both spatial and temporal informative contexts from the global perspective of the video. Specifically, the proposed Dual-TL uses a Spatial TokenLearner (S-TL) to explore associations in different facial ROIs, which promises the rPPG prediction far away from noisy ROI disturbances. Complementarily, a Temporal TokenLearner (T-TL) is designed to infer the quasi-periodic pattern of heartbeats, which eliminates temporal disturbances such as head movements. The two TokenLearners, S-TL and T-TL, are executed in a dual-path mode. This enables the model to reduce noise disturbances for final rPPG signal prediction. Extensive experiments on four physiological measurement benchmark datasets are conducted. The Dual-TL achieves state-of-the-art performances in both intra- and cross-dataset testings, demonstrating its immense potential as a basic backbone for rPPG measurement. The source code is available at \href{https://github.com/VUT-HFUT/Dual-TL}{https://github.com/VUT-HFUT/Dual-TL}

cs.CV↗

arXiv2023

M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector

Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike natural images, a malignant mammogram typically contains only one malignant finding; (2) mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment; (3) most mammograms are negative and do not contain any findings. In this work, we tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; (3) incorporating multi-instance learning (MIL) to train with unannotated images and perform breast-level classification. The resulting model, M&M, is a Multi-view and Multi-instance learning system that can both localize malignant findings and provide breast-level predictions. We validate M&M's detection and classification performance using five mammography datasets. In addition, we demonstrate the effectiveness of each proposed component through comprehensive ablation studies.

cs.CV↗

arXiv2023

ViGT: Proposal-free Video Grounding with Learnable Token in Transformer

The video grounding (VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely Video Grounding Transformer (ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows. (1) The token is unrelated to the video or the query and avoids data bias toward the original video and query. (2) The token simultaneously performs global context aggregation from video and query features. First, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention (i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets: ANet Captions, TACoS and YouCookII. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

cs.CV↗

arXiv2023

Data Augmentation for Human Behavior Analysis in Multi-Person Conversations

In this paper, we present the solution of our team HFUT-VUT for the MultiMediate Grand Challenge 2023 at ACM Multimedia 2023. The solution covers three sub-challenges: bodily behavior recognition, eye contact detection, and next speaker prediction. We select Swin Transformer as the baseline and exploit data augmentation strategies to address the above three tasks. Specifically, we crop the raw video to remove the noise from other parts. At the same time, we utilize data augmentation to improve the generalization of the model. As a result, our solution achieves the best results of 0.6262 for bodily behavior recognition in terms of mean average precision and the accuracy of 0.7771 for eye contact detection on the corresponding test set. In addition, our approach also achieves comparable results of 0.5281 for the next speaker prediction in terms of unweighted average recall.

cs.CV↗

arXiv2023

Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classification

In this paper, we briefly introduce the solution of our team HFUT-VUT for the Micros-gesture Classification in the MiGA challenge at IJCAI 2023. The micro-gesture classification task aims at recognizing the action category of a given video based on the skeleton data. For this task, we propose a 3D-CNNs-based micro-gesture recognition network, which incorporates a skeletal and semantic embedding loss to improve action classification performance. Finally, we rank 1st in the Micro-gesture Classification Challenge, surpassing the second-place team in terms of Top-1 accuracy by 1.10%.

cs.CV↗

arXiv2023

Improving Audio-Visual Video Parsing with Pseudo Visual Labels

Audio-Visual Video Parsing is a task to predict the events that occur in video segments for each modality. It often performs in a weakly supervised manner, where only video event labels are provided, i.e., the modalities and the timestamps of the labels are unknown. Due to the lack of densely annotated labels, recent work attempts to leverage pseudo labels to enrich the supervision. A commonly used strategy is to generate pseudo labels by categorizing the known event labels for each modality. However, the labels are still limited to the video level, and the temporal boundaries of event timestamps remain unlabeled. In this paper, we propose a new pseudo label generation strategy that can explicitly assign labels to each video segment by utilizing prior knowledge learned from the open world. Specifically, we exploit the CLIP model to estimate the events in each video segment based on visual modality to generate segment-level pseudo labels. A new loss function is proposed to regularize these labels by taking into account their category-richness and segmentrichness. A label denoising strategy is adopted to improve the pseudo labels by flipping them whenever high forward binary cross entropy loss occurs. We perform extensive experiments on the LLP dataset and demonstrate that our method can generate high-quality segment-level pseudo labels with the help of our newly proposed loss and the label denoising strategy. Our method achieves state-of-the-art audio-visual video parsing performance.

cs.CV↗

arXiv2023

Audio-Visual Segmentation

We propose to explore a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark (AVSBench), providing pixel-wise annotations for the sounding objects in audible videos. Two settings are studied with this benchmark: 1) semi-supervised audio-visual segmentation with a single sound source and 2) fully-supervised audio-visual segmentation with multiple sound sources. To deal with the AVS problem, we propose a novel method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process. We also design a regularization loss to encourage the audio-visual mapping during training. Quantitative and qualitative experiments on the AVSBench compare our approach to several existing methods from related tasks, demonstrating that the proposed method is promising for building a bridge between the audio and pixel-wise visual semantics. Code is available at https://github.com/OpenNLPLab/AVSBench.

cs.CV↗

arXiv2023

Audio-Visual Segmentation with Semantics

We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single sound source; 2) fully-supervised audio-visual segmentation with multiple sound sources, and 3) fully-supervised audio-visual semantic segmentation. The first two settings need to generate binary masks of sounding objects indicating pixels corresponding to the audio, while the third setting further requires generating semantic maps indicating the object category. To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process. We also design a regularization loss to encourage audio-visual mapping during training. Quantitative and qualitative experiments on AVSBench compare our approach to several existing methods for related tasks, demonstrating that the proposed method is promising for building a bridge between the audio and pixel-wise visual semantics. Code is available at https://github.com/OpenNLPLab/AVSBench. Online benchmark is available at http://www.avlbench.opennlplab.cn.

cs.CV↗

arXiv2022

Contrastive Positive Sample Propagation along the Audio-Visual Event Line

Visual and audio signals often coexist in natural environments, forming audio-visual events (AVEs). Given a video, we aim to localize video segments containing an AVE and identify its category. It is pivotal to learn the discriminative features for each video segment. Unlike existing work focusing on audio-visual feature fusion, in this paper, we propose a new contrastive positive sample propagation (CPSP) method for better deep feature representation learning. The contribution of CPSP is to introduce the available full or weak label as a prior that constructs the exact positive-negative samples for contrastive learning. Specifically, the CPSP involves comprehensive contrastive constraints: pair-level positive sample propagation (PSP), segment-level and video-level positive sample activation (PSA$_S$ and PSA$_V$). Three new contrastive objectives are proposed (\emph{i.e.}, $\mathcal{L}_{\text{avpsp}}$, $\mathcal{L}_\text{spsa}$, and $\mathcal{L}_\text{vpsa}$) and introduced into both the fully and weakly supervised AVE localization. To draw a complete picture of the contrastive learning in AVE localization, we also study the self-supervised positive sample propagation (SSPSP). As a result, CPSP is more helpful to obtain the refined audio-visual features that are distinguishable from the negatives, thus benefiting the classifier prediction. Extensive experiments on the AVE and the newly collected VGGSound-AVEL100k datasets verify the effectiveness and generalization ability of our method.

cs.CV↗

arXiv2022

Connection between near the $D_s^+D_s^-$ threshold enhancement in $B^+ \to D_s^+D_s^-K^+$ and conventional charmonium $χ_{c0}(2P)$

Focusing on recent measurement of $B^+ \to D_s^+D_s^-K^+$ process given by the LHCb Collaboration, we propose that this newly observed near the $D_s^+D_s^-$ threshold enhancement can be due to the contribution of the $χ_{c0}(2P)$, which is a $P$-wave charmonium below the $D_s^+D_s^-$ threshold. By performing a combined fit to the measured $D_s^+D_s^-$, $D_s^+K^+$, and $D_s^-K^+$ invariant mass spectra, introducing the $χ_{c0}(2P)$ can well reproduce the near threshold enhancement in the $D_s^+D_s^-$ invariant mass spectrum. When depicting the whole $D_s^+D_s^-$ invariant mass spectrum, the contributions from higher charmonium $ψ(4230)$ and charmoniumlike state $X_0(4140)$ are obvious. In addition, a charmed meson $D^*(3^3S_1)$ with mass around 3015 MeV is found to be important to depict the $D_s^-K^+$ invariant mass spectrum well. Especially, the importance of node effect of the spatial wave function of the $χ_{c0}(2P)$ is revealed, by which the anomaly of the ratio $Γ(X\to D^+D^-)/Γ(X\to D_s^+D_s^-)$ indicated by LHCb can be explained well. Finally, our scenario of the newly observed enhancement structure resulted from the $χ_{c0}(2P)$ is enforced.

hep-ph↗

arXiv2022

MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation

In most E-commerce platforms, whether the displayed items trigger the user's interest largely depends on their most eye-catching multimodal content. Consequently, increasing efforts focus on modeling multimodal user preference, and the pressing paradigm is to incorporate complete multimodal deep features of the items into the recommendation module. However, the existing studies ignore the mismatch problem between multimodal feature extraction (MFE) and user interest modeling (UIM). That is, MFE and UIM have different emphases. Specifically, MFE is migrated from and adapted to upstream tasks such as image classification. In addition, it is mainly a content-oriented and non-personalized process, while UIM, with its greater focus on understanding user interaction, is essentially a user-oriented and personalized process. Therefore, the direct incorporation of MFE into UIM for purely user-oriented tasks, tends to introduce a large number of preference-independent multimodal noise and contaminate the embedding representations in UIM. This paper aims at solving the mismatch problem between MFE and UIM, so as to generate high-quality embedding representations and better model multimodal user preferences. Towards this end, we develop a novel model, MEGCF. The UIM of the proposed model captures the semantic correlation between interactions and the features obtained from MFE, thus making a better match between MFE and UIM. More precisely, semantic-rich entities are first extracted from the multimodal data, since they are more relevant to user preferences than other multimodal information. These entities are then integrated into the user-item interaction graph. Afterwards, a symmetric linear Graph Convolution Network (GCN) module is constructed to perform message propagation over the graph, in order to capture both high-order semantic correlation and collaborative filtering signals.

cs.IR↗

arXiv2022

Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation

Graph Convolution Networks (GCNs), with their efficient ability to capture high-order connectivity in graphs, have been widely applied in recommender systems. Stacking multiple neighbor aggregation is the major operation in GCNs. It implicitly captures popularity features because the number of neighbor nodes reflects the popularity of a node. However, existing GCN-based methods ignore a universal problem: users' sensitivity to item popularity is differentiated, but the neighbor aggregations in GCNs actually fix this sensitivity through Graph Laplacian Normalization, leading to suboptimal personalization. In this work, we propose to model multi-grained popularity features and jointly learn them together with high-order connectivity, to match the differentiation of user preferences exhibited in popularity features. Specifically, we develop a Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering model, short for JMP-GCF, which uses a popularity-aware embedding generation to construct multi-grained popularity features, and uses the idea of joint learning to capture the signals within and between different granularities of popularity features that are relevant for modeling user preferences. Additionally, we propose a multistage stacked training strategy to speed up model convergence. We conduct extensive experiments on three public datasets to show the state-of-the-art performance of JMP-GCF.

cs.IR↗

arXiv2022

Pion Photoproduction off Nucleon with Hamiltonian Effective Field Theory

We analyze the $γN\toπN$ process in the negative parity channel with Hamiltonian effective filed theory which is successful in studying the nucleon resonances associated with the meson-nucleon scattering and lattice QCD simulations. We provide the scattering amplitude of pion photoproduction and extract the electric dipole amplitudes $E_{0+}$. The triquark component in $N^*(1535)$ is important for improving the consistence between our results and the experimental data.

hep-ph↗

arXiv2022

Newly observed $a_0(1817)$ as the scaling point of constructing the scalar meson spectroscopy

Stimulated by the newly observed $a_0(1817)$ by the BESIII Collaboration, we find a perfect Regge trajectory composed of the $a_0(980)$, $a_0(1450)$, and $a_0(1817)$, which leads us to categorize the $a_0(980)$, $a_0(1450)$, and $a_0(1817)$ into the isovector scalar meson family. This scenario is supported by their two-body Okubo-Zweig-Iizuka allowed strong decay behaviors. In this scheme, we also predict the third radial excitation of the $a_0(980)$, which is denoted as the $a_0(2115)$, accessible at future experiment as a direct test of this assignment. We find another Regge trajectory which contains three isoscalar scalar states $f_0(980)$, $X(1812)$, and $f_0(2100)$. We investigate their two-body Okubo-Zweig-Iizuka allowed strong decay patterns, which are roughly consistent with the experimental data. The $f_0(980)$, $X(1812)$, and $f_0(2100)$ can be well grouped into the isoscalar scalar meson family. We want to emphasize that these two Regge trajectories have a similar slope. In summary, the present work provides a scheme of constructing the scalar meson family based on these reported scalar states. The possibility of the $f_0(1710)$ as the candidate of the scalar glueball cannot be excluded by the observation of the $a_0(1817)$ since the $a_0(1817)$ is more suitable as the isovector partner of the $X(1812)$.

hep-ph↗

arXiv2020

SAPAG: A Self-Adaptive Privacy Attack From Gradients

Distributed learning such as federated learning or collaborative learning enables model training on decentralized data from users and only collects local gradients, where data is processed close to its sources for data privacy. The nature of not centralizing the training data addresses the privacy issue of privacy-sensitive data. Recent studies show that a third party can reconstruct the true training data in the distributed machine learning system through the publicly-shared gradients. However, existing reconstruction attack frameworks lack generalizability on different Deep Neural Network (DNN) architectures and different weight distribution initialization, and can only succeed in the early training phase. To address these limitations, in this paper, we propose a more general privacy attack from gradient, SAPAG, which uses a Gaussian kernel based of gradient difference as a distance measure. Our experiments demonstrate that SAPAG can construct the training data on different DNNs with different weight initializations and on DNNs in any training phases.

cs.LG↗

arXiv2020

Recurrent Relational Memory Network for Unsupervised Image Captioning

Unsupervised image captioning with no annotations is an emerging challenge in computer vision, where the existing arts usually adopt GAN (Generative Adversarial Networks) models. In this paper, we propose a novel memory-based network rather than GAN, named Recurrent Relational Memory Network ($R^2M$). Unlike complicated and sensitive adversarial learning that non-ideally performs for long sentence generation, $R^2M$ implements a concepts-to-sentence memory translator through two-stage memory mechanisms: fusion and recurrent memories, correlating the relational reasoning between common visual concepts and the generated words for long periods. $R^2M$ encodes visual context through unsupervised training on images, while enabling the memory to learn from irrelevant textual corpus via supervised fashion. Our solution enjoys less learnable parameters and higher computational efficiency than GAN-based methods, which heavily bear parameter sensitivity. We experimentally validate the superiority of $R^2M$ than state-of-the-arts on all benchmark datasets.

cs.CV↗

arXiv2020

Iterative Context-Aware Graph Inference for Visual Dialog

Visual dialog is a challenging task that requires the comprehension of the semantic dependencies among implicit visual and textual contexts. This task can refer to the relation inference in a graphical model with sparse contexts and unknown graph structure (relation descriptor), and how to model the underlying context-aware relation inference is critical. To this end, we propose a novel Context-Aware Graph (CAG) neural network. Each node in the graph corresponds to a joint semantic feature, including both object-based (visual) and history-related (textual) context representations. The graph structure (relations in dialog) is iteratively updated using an adaptive top-$K$ message passing mechanism. Specifically, in every message passing step, each node selects the most $K$ relevant nodes, and only receives messages from them. Then, after the update, we impose graph attention on all the nodes to get the final graph embedding and infer the answer. In CAG, each node has dynamic relations in the graph (different related $K$ neighbor nodes), and only the most relevant nodes are attributive to the context-aware relational graph inference. Experimental results on VisDial v0.9 and v1.0 datasets show that CAG outperforms comparative methods. Visualization results further validate the interpretability of our method.

cs.CV↗

arXiv2019

A realistic dimension-independent approach for charged defect calculations in semiconductors

First-principles calculations of charged defects have become a cornerstone of research in semiconductors and insulators by providing insights into their fundamental physical properties. But current standard approach using the so-called jellium model has encountered both conceptual ambiguity and computational difficulty, especially for low-dimensional semiconducting materials. In this Communication, we propose a physical, straightforward, and dimension-independent universal model to calculate the formation energies of charged defects in both three-dimensional (3D) bulk and low-dimensional semiconductors. Within this model, the ionized electrons or holes are placed on the realistic host band-edge states instead of the virtual jellium state, therefore, rendering it not only naturally keeps the supercell charge neutral, but also has clear physical meaning. This realistic model reproduces the same accuracy as the traditional jellium model for most of the 3D semiconducting materials, and remarkably, for the low-dimensional structures, it is able to cure the divergence caused by the artificial long-range electrostatic energy introduced in the jellium model, and hence gives meaningful formation energies of defects in charged state and transition energy levels of the corresponding defects. Our realistic method, therefore, will have significant impact for the study of defect physics in all low-dimensional systems including quantum dots, nanowires, surfaces, interfaces, and 2D materials.

cond-mat.mtrl-sci↗