arXiv subjects

Chen Chen

Publications and source records attributed to Chen Chen.

At least 685 records · Page 38Linked to original sources

arXiv2023

First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment

Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions. However, existing methods have hitherto neglected the necessity of aligning spatiotemporal visual and linguistic signals, as well as the crucial interactional information between humans and objects. To tackle these limitations, we propose to combine large-scale pre-trained vision-language and video-language models, which serve to contribute stable and reliable multimodal data and facilitate effective spatiotemporal visual-textual alignment. Additionally, a novel hand-object-interaction (HOI) aggregation module is proposed which aids in capturing human-object interaction information, thereby further augmenting the capacity to understand the presented scenario. Our method achieved first place in the CVPR'2023 AQTC Challenge, with a Recall@1 score of 78.7\%. The code is available at https://github.com/tomchen-ctj/CVPR23-LOVEU-AQTC.

cs.CV↗

arXiv2023

Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition

Audio-visual speech recognition (AVSR) provides a promising solution to ameliorate the noise-robustness of audio-only speech recognition with visual information. However, most existing efforts still focus on audio modality to improve robustness considering its dominance in AVSR task, with noise adaptation techniques such as front-end denoise processing. Though effective, these methods are usually faced with two practical challenges: 1) lack of sufficient labeled noisy audio-visual training data in some real-world scenarios and 2) less optimal model generality to unseen testing noises. In this work, we investigate the noise-invariant visual modality to strengthen robustness of AVSR, which can adapt to any testing noises while without dependence on noisy training data, a.k.a., unsupervised noise adaptation. Inspired by human perception mechanism, we propose a universal viseme-phoneme mapping (UniVPM) approach to implement modality transfer, which can restore clean audio from visual signals to enable speech recognition under any noisy conditions. Extensive experiments on public benchmarks LRS3 and LRS2 show that our approach achieves the state-of-the-art under various noisy as well as clean conditions. In addition, we also outperform previous state-of-the-arts on visual speech recognition task.

eess.AS↗

arXiv2023

MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition

Audio-visual speech recognition (AVSR) attracts a surge of research interest recently by leveraging multimodal signals to understand human speech. Mainstream approaches addressing this task have developed sophisticated architectures and techniques for multi-modality fusion and representation learning. However, the natural heterogeneity of different modalities causes distribution gap between their representations, making it challenging to fuse them. In this paper, we aim to learn the shared representations across modalities to bridge their gap. Different from existing similar methods on other multimodal tasks like sentiment analysis, we focus on the temporal contextual dependencies considering the sequence-to-sequence task setting of AVSR. In particular, we propose an adversarial network to refine frame-level modality-invariant representations (MIR-GAN), which captures the commonality across modalities to ease the subsequent multimodal fusion process. Extensive experiments on public benchmarks LRS3 and LRS2 show that our approach outperforms the state-of-the-arts.

eess.AS↗

arXiv2023

Hierarchical Task Network Planning for Facilitating Cooperative Multi-Agent Reinforcement Learning

Exploring sparse reward multi-agent reinforcement learning (MARL) environments with traps in a collaborative manner is a complex task. Agents typically fail to reach the goal state and fall into traps, which affects the overall performance of the system. To overcome this issue, we present SOMARL, a framework that uses prior knowledge to reduce the exploration space and assist learning. In SOMARL, agents are treated as part of the MARL environment, and symbolic knowledge is embedded using a tree structure to build a knowledge hierarchy. The framework has a two-layer hierarchical structure, comprising a hybrid module with a Hierarchical Task Network (HTN) planning and meta-controller at the higher level, and a MARL-based interactive module at the lower level. The HTN module and meta-controller use Hierarchical Domain Definition Language (HDDL) and the option framework to formalize symbolic knowledge and obtain domain knowledge and a symbolic option set, respectively. Moreover, the HTN module leverages domain knowledge to guide low-level agent exploration by assisting the meta-controller in selecting symbolic options. The meta-controller further computes intrinsic rewards of symbolic options to limit exploration behavior and adjust HTN planning solutions as needed. We evaluate SOMARL on two benchmarks, FindTreasure and MoveBox, and report superior performance over state-of-the-art MARL and subgoal-based baselines for MARL environments significantly.

cs.AI↗

arXiv2023

Getting the Most from Eye-Tracking: User-Interaction Based Reading Region Estimation Dataset and Models

A single digital newsletter usually contains many messages (regions). Users' reading time spent on, and read level (skip/skim/read-in-detail) of each message is important for platforms to understand their users' interests, personalize their contents, and make recommendations. Based on accurate but expensive-to-collect eyetracker-recorded data, we built models that predict per-region reading time based on easy-to-collect Javascript browser tracking data. With eye-tracking, we collected 200k ground-truth datapoints on participants reading news on browsers. Then we trained machine learning and deep learning models to predict message-level reading time based on user interactions like mouse position, scrolling, and clicking. We reached 27\% percentage error in reading time estimation with a two-tower neural network based on user interactions only, against the eye-tracking ground truth data, while the heuristic baselines have around 46\% percentage error. We also discovered the benefits of replacing per-session models with per-timestamp models, and adding user pattern features. We concluded with suggestions on developing message-level reading estimation techniques based on available data.

cs.HC↗

arXiv2023

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation Rules (AGRs) have been proposed to defend against Byzantine attacks. However, Byzantine clients can still circumvent robust AGRs when data is non-Identically and Independently Distributed (non-IID). In this paper, we first reveal the root causes of performance degradation of current robust AGRs in non-IID settings: the curse of dimensionality and gradient heterogeneity. In order to address this issue, we propose GAS, a \shorten approach that can successfully adapt existing robust AGRs to non-IID settings. We also provide a detailed convergence analysis when the existing robust AGRs are combined with GAS. Experiments on various real-world datasets verify the efficacy of our proposed GAS. The implementation code is provided in https://github.com/YuchenLiu-a/byzantine-gas.

cs.LG↗

arXiv2023

The State of the Art in Creating Visualization Corpora for Automated Chart Analysis

We present a state-of-the-art report on visualization corpora in automated chart analysis research. We survey 56 papers that created or used a visualization corpus as the input of their research techniques or systems. Based on a multi-level task taxonomy that identifies the goal, method, and outputs of automated chart analysis, we examine the property space of existing chart corpora along five dimensions: format, scope, collection method, annotations, and diversity. Through the survey, we summarize common patterns and practices of creating chart corpora, identify research gaps and opportunities, and discuss the desired properties of future benchmark corpora and the required tools to create them.

cs.HC↗

arXiv2023

Alteration-free and Model-agnostic Origin Attribution of Generated Images

Recently, there has been a growing attention in image generation models. However, concerns have emerged regarding potential misuse and intellectual property (IP) infringement associated with these models. Therefore, it is necessary to analyze the origin of images by inferring if a specific image was generated by a particular model, i.e., origin attribution. Existing methods are limited in their applicability to specific types of generative models and require additional steps during training or generation. This restricts their use with pre-trained models that lack these specific operations and may compromise the quality of image generation. To overcome this problem, we first develop an alteration-free and model-agnostic origin attribution method via input reverse-engineering on image generation models, i.e., inverting the input of a particular model for a specific image. Given a particular model, we first analyze the differences in the hardness of reverse-engineering tasks for the generated images of the given model and other images. Based on our analysis, we propose a method that utilizes the reconstruction loss of reverse-engineering to infer the origin. Our proposed method effectively distinguishes between generated images from a specific generative model and other images, including those generated by different models and real images.

cs.CV↗

arXiv2023

Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition

Automatic speech recognition (ASR) systems degrade significantly under noisy conditions. Recently, speech enhancement (SE) is introduced as front-end to reduce noise for ASR, but it also suppresses some important speech information, i.e., over-suppression. To alleviate this, we propose a dual-path style learning approach for end-to-end noise-robust speech recognition (DPSL-ASR). Specifically, we first introduce clean speech feature along with the fused feature from IFF-Net as dual-path inputs to recover the suppressed information. Then, we propose style learning to map the fused feature close to clean feature, in order to learn latent speech information from the latter, i.e., clean "speech style". Furthermore, we also minimize the distance of final ASR outputs in two paths to improve noise-robustness. Experiments show that the proposed approach achieves relative word error rate (WER) reductions of 10.6% and 8.6% over the best IFF-Net baseline, on RATS and CHiME-4 datasets respectively.

eess.AS↗

arXiv2023

A Neural State-Space Model Approach to Efficient Speech Separation

In this work, we introduce S4M, a new efficient speech separation framework based on neural state-space models (SSM). Motivated by linear time-invariant systems for sequence modeling, our SSM-based approach can efficiently model input signals into a format of linear ordinary differential equations (ODEs) for representation learning. To extend the SSM technique into speech separation tasks, we first decompose the input mixture into multi-scale representations with different resolutions. This mechanism enables S4M to learn globally coherent separation and reconstruction. The experimental results show that S4M performs comparably to other separation backbones in terms of SI-SDRi, while having a much lower model complexity with significantly fewer trainable parameters. In addition, our S4M-tiny model (1.8M parameters) even surpasses attention-based Sepformer (26.0M parameters) in noisy conditions with only 9.2 of multiply-accumulate operation (MACs).

cs.SD↗

arXiv2023

GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation

Recent breakthroughs in the field of language-guided image generation have yielded impressive achievements, enabling the creation of high-quality and diverse images based on user instructions.Although the synthesis performance is fascinating, one significant limitation of current image generation models is their insufficient ability to generate text coherently within images, particularly for complex glyph structures like Chinese characters. To address this problem, we introduce GlyphDraw, a general learning framework aiming to endow image generation models with the capacity to generate images coherently embedded with text for any specific language.We first sophisticatedly design the image-text dataset's construction strategy, then build our model specifically on a diffusion-based image generator and carefully modify the network structure to allow the model to learn drawing language characters with the help of glyph and position information.Furthermore, we maintain the model's open-domain image synthesis capability by preventing catastrophic forgetting by using parameter-efficient fine-tuning techniques.Extensive qualitative and quantitative experiments demonstrate that our method not only produces accurate language characters as in prompts, but also seamlessly blends the generated text into the background.Please refer to our \href{https://1073521013.github.io/glyph-draw.github.io/}{project page}. \end{abstract}

cs.CV↗

arXiv2023

DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Models

Hand mesh reconstruction from the monocular image is a challenging task due to its depth ambiguity and severe occlusion, there remains a non-unique mapping between the monocular image and hand mesh. To address this, we develop DiffHand, the first diffusion-based framework that approaches hand mesh reconstruction as a denoising diffusion process. Our one-stage pipeline utilizes noise to model the uncertainty distribution of the intermediate hand mesh in a forward process. We reformulate the denoising diffusion process to gradually refine noisy hand mesh and then select mesh with the highest probability of being correct based on the image itself, rather than relying on 2D joints extracted beforehand. To better model the connectivity of hand vertices, we design a novel network module called the cross-modality decoder. Extensive experiments on the popular benchmarks demonstrate that our method outperforms the state-of-the-art hand mesh reconstruction approaches by achieving 5.8mm PA-MPJPE on the Freihand test set, 4.98mm PA-MPJPE on the DexYCB test set.

cs.CV↗

arXiv2023

RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search

Text-based person search aims to retrieve the specified person images given a textual description. The key to tackling such a challenging task is to learn powerful multi-modal representations. Towards this, we propose a Relation and Sensitivity aware representation learning method (RaSa), including two novel tasks: Relation-Aware learning (RA) and Sensitivity-Aware learning (SA). For one thing, existing methods cluster representations of all positive pairs without distinction and overlook the noise problem caused by the weak positive pairs where the text and the paired image have noise correspondences, thus leading to overfitting learning. RA offsets the overfitting risk by introducing a novel positive relation detection task (i.e., learning to distinguish strong and weak positive pairs). For another thing, learning invariant representation under data augmentation (i.e., being insensitive to some transformations) is a general practice for improving representation's robustness in existing methods. Beyond that, we encourage the representation to perceive the sensitive transformation by SA (i.e., learning to detect the replaced words), thus promoting the representation's robustness. Experiments demonstrate that RaSa outperforms existing state-of-the-art methods by 6.94%, 4.45% and 15.35% in terms of Rank@1 on CUHK-PEDES, ICFG-PEDES and RSTPReid datasets, respectively. Code is available at: https://github.com/Flame-Chasers/RaSa.

cs.CV↗

arXiv2023

Study of GANs for Noisy Speech Simulation from Clean Speech

The performance of speech processing models trained on clean speech drops significantly in noisy conditions. Training with noisy datasets alleviates the problem, but procuring such datasets is not always feasible. Noisy speech simulation models that generate noisy speech from clean speech help remedy this issue. In our work, we study the ability of Generative Adversarial Networks (GANs) to simulate a variety of noises. Noise from the Ultra-High-Frequency/Very-High-Frequency (UHF/VHF), additive stationary and non-stationary, and codec distortion categories are studied. We propose four GANs, including the non-parallel translators, SpeechAttentionGAN, SimuGAN, and MaskCycleGAN-Augment, and the parallel translator, Speech2Speech-Augment. We achieved improvements of 55.8%, 28.9%, and 22.8% in terms of Multi-Scale Spectral Loss (MSSL) as compared to the baseline for the RATS, TIMIT-Cabin, and TIMIT-Helicopter datasets, respectively, after training on small datasets of about 3 minutes.

cs.SD↗

arXiv2023

The Exploration of Knowledge-Preserving Prompts for Document Summarisation

Despite the great development of document summarisation techniques nowadays, factual inconsistencies between the generated summaries and the original texts still occur from time to time. This study explores the possibility of adopting prompts to incorporate factual knowledge into generated summaries. We specifically study prefix-tuning that uses a set of trainable continuous prefix prompts together with discrete natural language prompts to aid summary generation. Experimental results demonstrate that the trainable prefixes can help the summarisation model extract information from discrete prompts precisely, thus generating knowledge-preserving summaries that are factually consistent with the discrete prompts. The ROUGE improvements of the generated summaries indicate that explicitly adding factual knowledge into the summarisation process could boost the overall performance, showing great potential for applying it to other natural language processing tasks.

cs.CL↗

arXiv2023

Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition

Audio-visual speech recognition (AVSR) research has gained a great success recently by improving the noise-robustness of audio-only automatic speech recognition (ASR) with noise-invariant visual information. However, most existing AVSR approaches simply fuse the audio and visual features by concatenation, without explicit interactions to capture the deep correlations between them, which results in sub-optimal multimodal representations for downstream speech recognition task. In this paper, we propose a cross-modal global interaction and local alignment (GILA) approach for AVSR, which captures the deep audio-visual (A-V) correlations from both global and local perspectives. Specifically, we design a global interaction model to capture the A-V complementary relationship on modality level, as well as a local alignment approach to model the A-V temporal consistency on frame level. Such a holistic view of cross-modal correlations enable better multimodal representations for AVSR. Experiments on public benchmarks LRS3 and LRS2 show that our GILA outperforms the supervised learning state-of-the-art.

eess.AS↗

arXiv2023

UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality relationship, treat each modality equally, suffer sensor noise, and thus reduce multimodal learning performance. In this work, we propose a novel multimodal contrastive method to explore more reliable multimodal representations under the weak supervision of unimodal predicting. Specifically, we first capture task-related unimodal representations and the unimodal predictions from the introduced unimodal predicting task. Then the unimodal representations are aligned with the more effective one by the designed multimodal contrastive method under the supervision of the unimodal predictions. Experimental results with fused features on two image-text classification benchmarks UPMC-Food-101 and N24News show that our proposed Unimodality-Supervised MultiModal Contrastive UniS-MMC learning method outperforms current state-of-the-art multimodal methods. The detailed ablation study and analysis further demonstrate the advantage of our proposed method.

cs.CV↗

arXiv2023

$Δ$-baryon axialvector and pseudoscalar form factors, and associated PCAC relations

A quark+diquark Faddeev equation treatment of the baryon bound state problem in Poincaré-invariant quantum field theory is used to deliver parameter-free predictions for all six $Δ$-baryon elastic weak form factors. Amongst the results, it is worth highlighting that there are two distinct classes of such $Δ$-baryon form factors, $(g_1, g_3, G_{πΔΔ})$, $(h_1, h_3, H_{πΔΔ})$, the functions within each of which are separately linked via partial conservation of axial current (PCAC) and Goldberger-Treiman (GT) relations. Respectively within each class, the listed form factors possess qualitatively the same structural features as the nucleon axial, induced pseudoscalar, and pion-nucleon coupling form factors. For instance, the $Δ$-baryon $g_1$ axial form factor can reliably be approximated by a dipole function, characterised by an axial charge $g_A^{Δ^+}=0.71(9)$ and mass-scale $m_A^Δ=0.95(2)m_Δ$. Moreover, the two distinct $Δ$-baryon PCAC form factor relations are satisfied to a high degree of accuracy on a large range of $Q^2$; the associated GT relations present good approximations only on $Q^2/m_Δ^2 \simeq 0$; and pion pole dominance approximations are reliable within both classes. There are two $πΔΔ$ couplings: $g_{πΔΔ} = 10.46(1.88)$; $h_{πΔΔ}= 35.73(3.75)$; and the associated form factors are soft. Such couplings commonly arise in phenomenology, which may therefore benefit from our analyses. A flavour decomposition of the axial charges reveals that quarks carry $71$\% of the $Δ$-baryon spin. The analogous result for the proton is $\approx 65$\%.

hep-ph↗