Search

Collected and annotated datasets, which are obtained through extensive efforts, are effective for training Deep Neural Network (DNN) models. However, these datasets are susceptible to be misused by unauthorized users, resulting in infringement of Intellectual Property (IP) rights owned by the dataset creators. Reversible Adversarial Exsamples (RAE) can help to solve the issues of IP protection for datasets. RAEs are adversarial perturbed images that can be restored to the original. As a cutting-edge approach, RAE scheme can serve the purposes of preventing unauthorized users from engaging in malicious model training, as well as ensuring the legitimate usage of authorized users. Nevertheless, in the existing work, RAEs still rely on the embedded auxiliary information for restoration, which may compromise their adversarial abilities. In this paper, a novel self-generation and self-recovery method, named as RAEDiff, is introduced for generating RAEs based on a Denoising Diffusion Probabilistic Models (DDPM). It diffuses datasets into a Biased Gaussian Distribution (BGD) and utilizes the prior knowledge of the DDPM for generating and recovering RAEs. The experimental results demonstrate that RAEDiff effectively self-generates adversarial perturbations for DNN models, including Artificial Intelligence Generated Content (AIGC) models, while also exhibiting significant self-recovery capabilities.

We explore the phase structure of Quantum Chromodynamics (QCD) with two dynamical quark flavors at finite temperature and baryon chemical potential, employing the non-perturbative gauge/gravity duality approach. Our gravitational model is tailored to align with state-of-the-art lattice data regarding the thermal properties of multi-flavor QCD. Following a rigorous parameter calibration to match equations of state and the QCD trace anomaly at zero chemical potential derived from cutting-edge lattice QCD simulations, we investigate thermodynamic quantities and order parameters. We predict the location of the critical endpoint (CEP) at $(\mu_{\text{CEP}}, T_{\text{CEP}})=(219,182)$ MeV at which a line of first-order phase transitions terminate. We compute critical exponents associated with the CEP and find that they almost coincide with the critical exponents of the quantum 3D Ising model., Comment: 20 pages, 12 figures

In this paper, we propose a new unsupervised domain adaptation (DA) method called layer-adapted implicit distribution alignment networks (LIDAN) to address the challenge of cross-corpus speech emotion recognition (SER). LIDAN extends our previous ICASSP work, deep implicit distribution alignment networks (DIDAN), whose key contribution lies in the introduction of a novel regularization term called implicit distribution alignment (IDA). This term allows DIDAN trained on source (training) speech samples to remain applicable to predicting emotion labels for target (testing) speech samples, regardless of corpus variance in cross-corpus SER. To further enhance this method, we extend IDA to layer-adapted IDA (LIDA), resulting in LIDAN. This layer-adpated extention consists of three modified IDA terms that consider emotion labels at different levels of granularity. These terms are strategically arranged within different fully connected layers in LIDAN, aligning with the increasing emotion-discriminative abilities with respect to the layer depth. This arrangement enables LIDAN to more effectively learn emotion-discriminative and corpus-invariant features for SER across various corpora compared to DIDAN. It is also worthy to mention that unlike most existing methods that rely on estimating statistical moments to describe pre-assumed explicit distributions, both IDA and LIDA take a different approach. They utilize an idea of target sample reconstruction to directly bridge the feature distribution gap without making assumptions about their distribution type. As a result, DIDAN and LIDAN can be viewed as implicit cross-corpus SER methods. To evaluate LIDAN, we conducted extensive cross-corpus SER experiments on EmoDB, eNTERFACE, and CASIA corpora. The experimental results demonstrate that LIDAN surpasses recent state-of-the-art explicit unsupervised DA methods in tackling cross-corpus SER tasks.

We investigate the CP violation in the decay process $\bar B_{s} \rightarrow \phi(\rho,\omega) P \rightarrow K^{+}K^{-}P$ by considering the interference effects of $\phi\rightarrow K^{+}K^{-}$, $\rho\rightarrow K^{+}K^{-}$ and $\omega\rightarrow K^{+}K^{-}$ within the framework of perturbative QCD method (P refers to $\pi$, K, $\eta$ and $\eta'$ pseudoscalar mesons, respectively). We analyse the mixings of $\phi-\rho^{0}$, $\phi-\omega$ and $\omega-\rho^{0}$ and provide the amplitudes of the quasi-two-body decay processes. The CP violation for $\bar B_{s} \rightarrow K^{+}K^{-} P$ decay process is obvious at the ranges of the three vector mesons interferences. Meanwhile, the localised CP violation can be found for comparing with the experiment results from three-body decay process at the LHC in the near future.

Shape assembly aims to reassemble parts (or fragments) into a complete object, which is a common task in our daily life. Different from the semantic part assembly (e.g., assembling a chair's semantic parts like legs into a whole chair), geometric part assembly (e.g., assembling bowl fragments into a complete bowl) is an emerging task in computer vision and robotics. Instead of semantic information, this task focuses on geometric information of parts. As the both geometric and pose space of fractured parts are exceptionally large, shape pose disentanglement of part representations is beneficial to geometric shape assembly. In our paper, we propose to leverage SE(3) equivariance for such shape pose disentanglement. Moreover, while previous works in vision and robotics only consider SE(3) equivariance for the representations of single objects, we move a step forward and propose leveraging SE(3) equivariance for representations considering multi-part correlations, which further boosts the performance of the multi-part assembly. Experiments demonstrate the significance of SE(3) equivariance and our proposed method for geometric shape assembly. Project page: https://crtie.github.io/SE-3-part-assembly/, Comment: ICCV 2023, Project page: https://crtie.github.io/SE-3-part-assembly/ , Code: https://github.com/crtie/Leveraging-SE-3-Equivariance-for-Learning-3D-Geometric-Shape-Assembly

Audio deepfake detection is an emerging active topic. A growing number of literatures have aimed to study deepfake detection algorithms and achieved effective performance, the problem of which is far from being solved. Although there are some review literatures, there has been no comprehensive survey that provides researchers with a systematic overview of these developments with a unified evaluation. Accordingly, in this survey paper, we first highlight the key differences across various types of deepfake audio, then outline and analyse competitions, datasets, features, classifications, and evaluation of state-of-the-art approaches. For each aspect, the basic techniques, advanced developments and major challenges are discussed. In addition, we perform a unified comparison of representative features and classifiers on ASVspoof 2021, ADD 2023 and In-the-Wild datasets for audio deepfake detection, respectively. The survey shows that future research should address the lack of large scale datasets in the wild, poor generalization of existing detection methods to unknown fake attacks, as well as interpretability of detection results.

In this paper, we propose a novel time-frequency joint learning method for speech emotion recognition, called Time-Frequency Transformer. Its advantage is that the Time-Frequency Transformer can excavate global emotion patterns in the time-frequency domain of speech signal while modeling the local emotional correlations in the time domain and frequency domain respectively. For the purpose, we first design a Time Transformer and Frequency Transformer to capture the local emotion patterns between frames and inside frequency bands respectively, so as to ensure the integrity of the emotion information modeling in both time and frequency domains. Then, a Time-Frequency Transformer is proposed to mine the time-frequency emotional correlations through the local time-domain and frequency-domain emotion features for learning more discriminative global speech emotion representation. The whole process is a time-frequency joint learning process implemented by a series of Transformer models. Experiments on IEMOCAP and CASIA databases indicate that our proposed method outdoes the state-of-the-art methods., Comment: Accepted by International Conference on Neural Information Processing (ICONIP2023)

StackOverflow (SO) is a widely used question-and-answer (Q\&A) website for software developers and computer scientists. GitHub is an online development platform used for storing, tracking, and collaborating on software projects. Prior work relates the information mined from both platforms to link user accounts or compare developers' activities across platforms. However, not much work is done to characterize the SO answers reused by GitHub projects. For this paper, we did an empirical study by mining the SO answers reused by Java projects available on GitHub. We created a hybrid approach of clone detection, keyword-based search, and manual inspection, to identify the answer(s) actually leveraged by developers. Based on the identified answers, we further studied topics of the discussion threads, answer characteristics (e.g., scores, ages, code lengths, and text lengths), and developers' reuse practices. We observed that most reused answers offer programs to implement specific coding tasks. Among all analyzed SO discussion threads, the reused answers often have relatively higher scores, older ages, longer code, and longer text than unused answers. In only 9% of scenarios (40/430), developers fully copied answer code for reuse. In the remaining scenarios, they reused partial code or created brand new code from scratch. Our study characterized 130 SO discussion threads referred to by Java developers in 357 GitHub projects. Our empirical findings can guide SO answerers to provide better answers, and shed lights on future research related to SO and GitHub., Comment: 12 pages

Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep., Comment: Code, benchmark and pre-trained models: https://github.com/Audio-AGI/AudioSep

Coherence is a crucial aspect of evaluating text readability and can be assessed through two primary factors when evaluating an essay in a scoring scenario. The first factor is logical coherence, characterized by the appropriate use of discourse connectives and the establishment of logical relationships between sentences. The second factor is the appropriateness of punctuation, as inappropriate punctuation can lead to confused sentence structure. To address these concerns, we propose a coherence scoring model consisting of a regression model with two feature extractors: a local coherence discriminative model and a punctuation correction model. We employ gradient-boosting regression trees as the regression model and impose monotonicity constraints on the input features. The results show that our proposed model better generalizes unseen data. The model achieved third place in track 1 of NLPCC 2023 shared task 7. Additionally, we briefly introduce our solution for the remaining tracks, which achieves second place for track 2 and first place for both track 3 and track 4., Comment: 12 pages, 1 figure, accepted to NLPCC 2023

Sequential recommendation requires understanding the dynamic patterns of users' behaviors, contexts, and preferences from their historical interactions. Most existing works focus on modeling user-item interactions only from the item level, ignoring that they are driven by latent shopping intentions (e.g., ballpoint pens, miniatures, etc). The detection of the underlying shopping intentions of users based on their historical interactions is a crucial aspect for e-commerce platforms, such as Amazon, to enhance the convenience and efficiency of their customers' shopping experiences. Despite its significance, the area of main shopping intention detection remains under-investigated in the academic literature. To fill this gap, we propose a graph-regularized stochastic Transformer method, G-STO. By considering intentions as sets of products and user preferences as compositions of intentions, we model both of them as stochastic Gaussian embeddings in the latent representation space. Instead of training the stochastic representations from scratch, we develop a global intention relational graph as prior knowledge for regularization, allowing relevant shopping intentions to be distributionally close. Finally, we feed the newly regularized stochastic embeddings into Transformer-based models to encode sequential information from the intention transitions. We evaluate our main shopping intention identification model on three different real-world datasets, where G-STO achieves significantly superior performances to the baselines by 18.08% in Hit@1, 7.01% in Hit@10, and 6.11% in NDCG@10 on average.

We study the dissociation effect of $J/\Psi$ in magnetized, rotating QGP matter at finite temperature and chemical potential using gauge/gravity duality. By incorporating angular velocity into the holographic magnetic catalysis model, we analyze the influence of temperature, chemical potential, magnetic field, and angular velocity on the properties of $J/\Psi$ meson. The results reveal that temperature, chemical potential, and rotation enhance the dissociation effect and increase the effective mass in the QGP phase. However, the magnetic field suppresses dissociation, and its effect on the effective mass is non-trivial. Additionally, we explore the interplay between magnetic field and rotation, identifying a critical angular velocity that determines the dominant effect. As a parallel study, we also examine the rotation effect in the holographic inverse magnetic catalysis model, although the magnetic field exhibits distinctly different behaviors in these two models, the impact of rotation on the dissociation effect of $J/\Psi$ is similar. Finally, we investigate the influence of electric field and demonstrate that it also speeds up the $J/\Psi$ dissociation., Comment: 24 pages, 13 figures

Transformer has emerged in speech emotion recognition (SER) at present. However, its equal patch division not only damages frequency information but also ignores local emotion correlations across frames, which are key cues to represent emotion. To handle the issue, we propose a Local to Global Feature Aggregation learning (LGFA) for SER, which can aggregate longterm emotion correlations at different scales both inside frames and segments with entire frequency information to enhance the emotion discrimination of utterance-level speech features. For this purpose, we nest a Frame Transformer inside a Segment Transformer. Firstly, Frame Transformer is designed to excavate local emotion correlations between frames for frame embeddings. Then, the frame embeddings and their corresponding segment features are aggregated as different-level complements to be fed into Segment Transformer for learning utterance-level global emotion features. Experimental results show that the performance of LGFA is superior to the state-of-the-art methods., Comment: This paper has been accepted on INTERSPEECH 2023