Search

Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not differentiate whether the domain differences come from the marginals or the dependence structures. In many business and financial applications, the labeling function usually has different sensitivities to the changes in the marginals versus changes in the dependence structures. Measuring the overall distributional differences will not be discriminative enough in acquiring transferability. Without the needed structural resolution, the learned transfer is less optimal. This paper proposes a new domain adaptation approach in which one can measure the differences in the internal dependence structure separately from those in the marginals. By optimizing the relative weights among them, the new regularization strategy greatly relaxes the rigidness of the existing approaches. It allows a learning machine to pay special attention to places where the differences matter the most. Experiments on three real-world datasets show that the improvements are quite notable and robust compared to various benchmark domain adaptation models., Comment: 15 pages

Medical image segmentation plays an important role in computer-aided diagnosis. Attention mechanisms that distinguish important parts from irrelevant parts have been widely used in medical image segmentation tasks. This paper systematically reviews the basic principles of attention mechanisms and their applications in medical image segmentation. First, we review the basic concepts of attention mechanism and formulation. Second, we surveyed over 300 articles related to medical image segmentation, and divided them into two groups based on their attention mechanisms, non-Transformer attention and Transformer attention. In each group, we deeply analyze the attention mechanisms from three aspects based on the current literature work, i.e., the principle of the mechanism (what to use), implementation methods (how to use), and application tasks (where to use). We also thoroughly analyzed the advantages and limitations of their applications to different tasks. Finally, we summarize the current state of research and shortcomings in the field, and discuss the potential challenges in the future, including task specificity, robustness, standard evaluation, etc. We hope that this review can showcase the overall research context of traditional and Transformer attention methods, provide a clear reference for subsequent research, and inspire more advanced attention research, not only in medical image segmentation, but also in other image analysis scenarios., Comment: Submitted to Medical Image Analysis, survey paper, 34 pages, over 300 references

Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. Such a trend underscored the potential of training LLMs with unlimited language data, advancing the development of a universal embodied agent. In this work, we introduce the NavGPT, a purely LLM-based instruction-following navigation agent, to reveal the reasoning capability of GPT models in complex embodied scenes by performing zero-shot sequential action prediction for vision-and-language navigation (VLN). At each step, NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status, and makes the decision to approach the target. Through comprehensive experiments, we demonstrate NavGPT can explicitly perform high-level planning for navigation, including decomposing instruction into sub-goal, integrating commonsense knowledge relevant to navigation task resolution, identifying landmarks from observed scenes, tracking navigation progress, and adapting to exceptions with plan adjustment. Furthermore, we show that LLMs is capable of generating high-quality navigational instructions from observations and actions along a path, as well as drawing accurate top-down metric trajectory given the agent's navigation history. Despite the performance of using NavGPT to zero-shot R2R tasks still falling short of trained models, we suggest adapting multi-modality inputs for LLMs to use as visual navigation agents and applying the explicit reasoning of LLMs to benefit learning-based models.

Automating radiology report generation can ease the reporting workload for radiologists. However, existing works focus mainly on the chest area due to the limited availability of public datasets for other regions. Besides, they often rely on naive data-driven approaches, e.g., a basic encoder-decoder framework with captioning loss, which limits their ability to recognise complex patterns across diverse anatomical regions. To address these issues, we propose X-RGen, a radiologist-minded report generation framework across six anatomical regions. In X-RGen, we seek to mimic the behaviour of human radiologists, breaking them down into four principal phases: 1) initial observation, 2) cross-region analysis, 3) medical interpretation, and 4) report formation. Firstly, we adopt an image encoder for feature extraction, akin to a radiologist's preliminary review. Secondly, we enhance the recognition capacity of the image encoder by analysing images and reports across various regions, mimicking how radiologists gain their experience and improve their professional ability from past cases. Thirdly, just as radiologists apply their expertise to interpret radiology images, we introduce radiological knowledge of multiple anatomical regions to further analyse the features from a clinical perspective. Lastly, we generate reports based on the medical-aware features using a typical auto-regressive text decoder. Both natural language generation (NLG) and clinical efficacy metrics show the effectiveness of X-RGen on six X-ray datasets. Our code and checkpoints are available at: https://github.com/YtongXie/X-RGen., Comment: Accepted by ACCV 2024 (Oral)

Deep image denoising models often rely on large amount of training data for the high quality performance. However, it is challenging to obtain sufficient amount of data under real-world scenarios for the supervised training. As such, synthesizing realistic noise becomes an important solution. However, existing techniques have limitations in modeling complex noise distributions, resulting in residual noise and edge artifacts in denoising methods relying on synthetic data. To overcome these challenges, we propose a novel method that synthesizes realistic noise using diffusion models, namely Realistic Noise Synthesize Diffusor (RNSD). In particular, the proposed time-aware controlling module can simulate various environmental conditions under given camera settings. RNSD can incorporate guided multiscale content, such that more realistic noise with spatial correlations can be generated at multiple frequencies. In addition, we construct an inversion mechanism to predict the unknown camera setting, which enables the extension of RNSD to datasets without setting information. Extensive experiments demonstrate that our RNSD method significantly outperforms the existing methods not only in the synthesized noise under multiple realism metrics, but also in the single image denoising performances.

We report the first observation of a pressure-induced transition from a superconducting (SC) to an insulating (I) phase in single-crystal Ba$_{1-x}$K$_x$BiO$_3$ ($x$ = 0.4, 0.43, 0.52, and 0.58) superconductors. X-ray diffraction measurements conducted at 20 K reveal a direct relationship between this SC-I transition and a pressure-induced distortion of crystal structure. With increasing pressure, the lattice parameters a and c of the ambient-pressure superconducting tetragonal (T) phase are compressed continuously below a critical pressure (Pc1), wherein the pressure (P) dependence of superconducting transition temperature (Tc) displays a small variation. However, upon further compression, the lattice of the compressed T phase displays an anisotropic change, and Tc shows a monotonous decrease. When the pressure reaches Pc2 (Pc2 > Pc1), the compressed T phase collapses along the c axis, followed by the disappearance of superconductivity and the appearance of the insulating phase. This SC-I transition is fully reversible, with the critical pressure increasing alongside K doping concentration. These findings are strikingly similar to the SC-I transition observed in hole-doped high-Tc cuprate superconductors under pressure. Identifying their commonalities could deepen our understanding of the mechanisms that underlie high- Tc superconductivity in these two oxide superconductors with a perovskite structure., Comment: 16 pages and 5 figures

Recent years have witnessed a widespread adoption of containers. While containers simplify and accelerate application development, existing container network technologies either incur significant overhead, which hurts performance for distributed applications, or lose flexibility or compatibility, which hinders the widespread deployment in production. We carefully analyze the kernel data path of an overlay network, quantifying the time consumed by each segment of the data path and identifying the \emph{extra overhead} in an overlay network compared to bare metal. We observe that this extra overhead generates repetitive results among packets, which inspires us to introduce caches within an overlay network. We design and implement ONCache (\textbf{O}verlay \textbf{N}etwork \textbf{Cache}), a cache-based container overlay network, to eliminate the extra overhead while maintaining flexibility and compatibility. We implement ONCache using the extended Berkeley Packet Filter (eBPF) with only 524 lines of code, and integrate it as a plugin of Antrea. With ONCache, containers attain networking performance akin to that of bare metal. Compared to the standard overlay networks, ONCache improves throughput and request-response transaction rate by 12\% and 36\% for TCP (20\% and 34\% for UDP), respectively, while significantly reducing per-packet CPU overhead. Popular distributed applications also benefit from ONCache.

The three-dimensional electronic structure and the nature of Ce 4f electrons of the Kondo insulator CeRu4Sn6 are investigated by angle-resolved photoemission spectroscopy, utilizing tunable photon energies. Our results reveal (i) the three-dimensional k-space nature of the Fermi surface, (ii) the localized-to-itinerant transition of f electrons occurs at a much high temperature than the hybridization gap opening temperature, and (iii) the "relocalization" of itinerant f electrons below 25 K, which could be the precursor to the establishment of magnetic order., Comment: 6 pages, 4 figures

Volume data is commonly found in many scientific disciplines, like medicine, physics, and biology. Experts rely on robust scientific visualization techniques to extract valuable insights from the data. Recent years have shown path tracing to be the preferred approach for volumetric rendering, given its high levels of realism. However, real-time volumetric path tracing often suffers from stochastic noise and long convergence times, limiting interactive exploration. In this paper, we present a novel method to enable real-time global illumination for volume data visualization. We develop Photon Field Networks -- a phase-function-aware, multi-light neural representation of indirect volumetric global illumination. The fields are trained on multi-phase photon caches that we compute a priori. Training can be done within seconds, after which the fields can be used in various rendering tasks. To showcase their potential, we develop a custom neural path tracer, with which our photon fields achieve interactive framerates even on large datasets. We conduct in-depth evaluations of the method's performance, including visual quality, stochastic noise, inference and rendering speeds, and accuracy regarding illumination and phase function awareness. Results are compared to ray marching, path tracing and photon mapping. Our findings show that Photon Field Networks can faithfully represent indirect global illumination across the phase spectrum while exhibiting less stochastic noise and rendering at a significantly faster rate than traditional methods.

Efficient deep learning-based approaches have achieved remarkable performance in single image super-resolution. However, recent studies on efficient super-resolution have mainly focused on reducing the number of parameters and floating-point operations through various network designs. Although these methods can decrease the number of parameters and floating-point operations, they may not necessarily reduce actual running time. To address this issue, we propose a novel multi-stage lightweight network boosting method, which can enable lightweight networks to achieve outstanding performance. Specifically, we leverage enhanced high-resolution output as additional supervision to improve the learning ability of lightweight student networks. Upon convergence of the student network, we further simplify our network structure to a more lightweight level using reparameterization techniques and iterative network pruning. Meanwhile, we adopt an effective lightweight network training strategy that combines multi-anchor distillation and progressive learning, enabling the lightweight network to achieve outstanding performance. Ultimately, our proposed method achieves the fastest inference time among all participants in the NTIRE 2023 efficient super-resolution challenge while maintaining competitive super-resolution performance. Additionally, extensive experiments are conducted to demonstrate the effectiveness of the proposed components. The results show that our approach achieves comparable performance in representative dataset DIV2K, both qualitatively and quantitatively, with faster inference and fewer number of network parameters.

The exotic states $X(3872)$ and $Z_c(3900)$ have long been conjectured as isoscalar and isovector $\bar{D}^*D$ molecules. In this work, we first propose the triangle diagram mechanism to investigate their productions in $B$ decays as well as their heavy quark spin symmetry partners, $X_2(4013)$ and $Z_c(4020)$. We show that the large isospin breaking of the ratio $\mathcal{B}[B^+ \to X(3872) K^+]/\mathcal{B}[B^0 \to X(3872) K^0] $ can be attributed to the isospin breaking of the neutral and charged $\bar{D}^*D$ components in their wave functions. For the same reason, the branching fractions of $Z_c(3900)$ in $B$ decays are smaller than the corresponding ones of $X(3872)$ by at least one order of magnitude, which naturally explains its non-observation. A hierarchy for the production fractions of $X(3872)$, $Z_c(3900)$, $X_2(4013)$, and $Z_c(4020)$ in $B$ decays, consistent with all existing data, is predicted. Furthermore, with the factorization ansatz we extract the decay constants of $X(3872)$, $Z_c(3900)$, and $Z_c(4020)$ as $\bar{D}^*D^{(*)}$ molecules via the $B$ decays, and then calculate their branching fractions in the relevant $B_{(s)}$ decays, which turn out to agree with all existing experimental data. The mechanism we proposed is useful to elucidate the internal structure of the many exotic hadrons discovered so far and to extract the decay constants of hadronic molecules,which can be used to predict their production in related processes.

We investigated the electronic structure of the antiferromagnetic Kondo lattice CePd5Al2 using high-resolution angle-resolved photoemission spectroscopy. The experimentally determined band structure of the conduction electrons is predominated by the Pd 4d character. It contains multiple hole and electron Fermi pockets, in good agreement with density functional theory calculations. The Fermi surface is folded over Q0 = (0, 0, 1), manifested by Fermi surface reconstruction and band folding. Our results suggest that Fermi surface nesting drives the formation of antiferromagnetic order in CePd5Al2., Comment: 6 pages,3 figure

Implicit Neural Representations (INRs) have recently exhibited immense potential in the field of scientific visualization for both data generation and visualization tasks. However, these representations often consist of large multi-layer perceptrons (MLPs), necessitating millions of operations for a single forward pass, consequently hindering interactive visual exploration. While reducing the size of the MLPs and employing efficient parametric encoding schemes can alleviate this issue, it compromises generalizability for unseen parameters, rendering it unsuitable for tasks such as temporal super-resolution. In this paper, we introduce HyperINR, a novel hypernetwork architecture capable of directly predicting the weights for a compact INR. By harnessing an ensemble of multiresolution hash encoding units in unison, the resulting INR attains state-of-the-art inference performance (up to 100x higher inference bandwidth) and can support interactive photo-realistic volume visualization. Additionally, by incorporating knowledge distillation, exceptional data and visualization generation quality is achieved, making our method valuable for real-time parameter exploration. We validate the effectiveness of the HyperINR architecture through a comprehensive ablation study. We showcase the versatility of HyperINR across three distinct scientific domains: novel view synthesis, temporal super-resolution of volume data, and volume rendering with dynamic global shadows. By simultaneously achieving efficiency and generalizability, HyperINR paves the way for applying INR in a wider array of scientific visualization applications.

A material described as lutetium-hydrogen-nitrogen (Lu-H-N in short) was recently claimed to have near-ambient superconductivity[Gammon et al, Nature 615, 244, 2023]. If the results could be reproduced by other teams, it would be a major scientific breakthrough. Here, we report our results of transport and structure measurements on a material prepared using the same method as that reported by Gammon et al. Our X-ray diffraction measurements indicated that the obtained sample contained three substances: the FCC-1 phase (Fm-3m) with a lattice parameter a=5.03 {\AA}, the FCC-2 phase (Fm-3m) with a lattice parameter a= 4.755 {\AA} and Lu metal. These two FCC phases are identical to the those reported in the so-called near-ambient superconductor. However, we found that the samples had no evidence of superconductivity, through our resistance measurements in the temperature range of 300 - 4 K and pressure range of 0.9 - 3.4 GPa, and our magnetic susceptibility measurements in the pressure range of 0.8-3.3 GPa and temperature down to 100 K. We also used a laser heating technique to heat the sample to 1800{\deg}C and found no superconductivity in the produced dark blue samples below 6.5 GPa. In addition, the color of the both samples remain dark blue in the pressure range investigated., Comment: 13 pages and 4 figures

Implicit neural representations (INRs) have emerged as a powerful tool for compressing large-scale volume data. This opens up new possibilities for in situ visualization. However, the efficient application of INRs to distributed data remains an underexplored area. In this work, we develop a distributed volumetric neural representation and optimize it for in situ visualization. Our technique eliminates data exchanges between processes, achieving state-of-the-art compression speed, quality and ratios. Our technique also enables the implementation of an efficient strategy for caching large-scale simulation data in high temporal frequencies, further facilitating the use of reactive in situ visualization in a wider range of scientific problems. We integrate this system with the Ascent infrastructure and evaluate its performance and usability using real-world simulations.

In the present work, we investigate the charmed meson loops contributions to the pionic transitions from $Z_c(4020)^+$ to the $D$ wave triplets charmonia by using an effective Lagrangian approach. Our estimations indicate that the predicted branching fraction of $Z_c(4020)^+ \to \pi^+ \psi(1^3D_J) , \ J=(1,2,3)$ are much smaller than the one of $Z_c(4020)^+ \to \pi^+ h_c $. Thus, searching $Z_c(4020)^\pm$ in the $\pi^\pm \psi(1^3D_J) $ invariant mass distributions is impossible. Thus, the observed peak structures at 4.04 and 4.13 GeV in the $\pi^\pm \psi(3770)$ invariant mass distributions should not come from the contributions of $Z_c(4020)^\pm$, and further precise experimental measurements of the $e^+ e^- \to \pi^+ \pi^- \psi(3770)$ process are needed to decode the nature of these two peak structures., Comment: 9 pages, 5 figures, accepted for publication in EPJC

The origin of calcium production in the first stars (Pop III stars), which formed out of the primordial matter of the Big Bang, and their fates, remain most fascinating mysteries in astrophysics. Advanced nuclear burning and supernovae were thought to be the dominant source of the Ca production seen in all stars. Here we report on a qualitatively different path to Ca production through break-out from the "warm" carbon-nitrogen-oxygen (CNO) cycle. We extend direct measurement of the $^{19}$F($p$, $\gamma$)$^{20}$Ne break-out reaction down to an unprecedentedly low energy point of 186 keV and discover a key resonance at 225 keV. In the domain of astrophysical interest, at around 0.1 giga kelvin, this thermonuclear $^{19}$F($p$,$\gamma$)$^{20}$Ne rate is up to a factor of 7.4 larger than the previous recommended rate. Our stellar models show a stronger break-out during stellar hydrogen burning than thought before, and may reveal the nature of Ca production in Pop III stars imprinted on the oldest known ultra-iron poor star, SMSS0313-6708. This result from the China Jinping Underground Laboratory, the deepest laboratory in the world, offering an environment with extremely low cosmic-ray induced background, has far-reaching implications on our understanding of how the first stars evolve and die. Our rate showcases the impact that faint Pop III star supernovae can have on the nucleosynthesis observed in the oldest known stars and first galaxies, key mission targets of the James Webb Space Telescope., Comment: 32 pages, 8 figures, 6 tables

In the present work, we investigate the productions of the molecular states composed of $D^{(*)}_s \bar{D}^{(*)}$ and $D^{(*)}_s \bar{D}^{(*)}_s$ in the $B$ and $B_s$ decays by using an effective Lagrangian approach. The branching ratios in terms of the model parameter $\alpha$ and the binding energy $\Delta E$ are estimated. Our estimations indicate that the branching fractions are of the order of $10^{-4}$ and the relative ratios are very weakly dependent on the model parameter $\alpha$ and the binding energy $\Delta E$. The predicted ratios are helpful for searching the hidden-charm molecular states with strange quark in the future experiments at Belle II and LHCb., Comment: 12 pages, 4 figures and 6 tables, accepted by Phys. Rev. D

The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence. As humans, we use this ability to not only interpret the world around us, but also to predict the outcomes of the various interactions we experience. Generalising over multiple observations is a task that has historically presented difficulties for machines to grasp, especially when requiring computer vision. In this paper, we propose a model that can extract general rules from video demonstrations by simultaneously performing summarisation and translation. Our approach differs from prior works by framing the problem as a multi-sequence-to-sequence task, wherein summarisation is learnt by the model. This allows our model to utilise edge cases that would otherwise be suppressed or discarded by traditional summarisation techniques. Additionally, we show that our approach can handle noisy specifications without the need for additional filtering methods. We evaluate our model by synthesising programs from video demonstrations in the Vizdoom environment achieving state-of-the-art results with a relative increase of 11.75% program accuracy on prior works

The dynamic portfolio construction problem requires dynamic modeling of the joint distribution of multivariate stock returns. To achieve this, we propose a dynamic generative factor model which uses random variable transformation as an implicit way of distribution modeling and relies on the Attention-GRU network for dynamic learning and forecasting. The proposed model captures the dynamic dependence among multivariate stock returns, especially focusing on the tail-side properties. We also propose a two-step iterative algorithm to train the model and then predict the time-varying model parameters, including the time-invariant tail parameters. At each investment date, we can easily simulate new samples from the learned generative model, and we further perform CVaR portfolio optimization with the simulated samples to form a dynamic portfolio strategy. The numerical experiment on stock data shows that our model leads to wiser investments that promise higher reward-risk ratios and present lower tail risks.

Here we report the first investigation on correlation between the transport properties and the corresponding stability of the lattice structure for CaK(Fe1-xNix)4As4 (x=0.04 and 0), a new type of putative topological superconductors, with and without a spin-vortex crystal (SVC) state in a wide pressure range involving superconducting to non-superconducting transition and the half- to full-collapse of tetragonal (h-cT and f-cT) phases, by the complementary measurements of high-pressure resistance, Hall coefficient and synchrotron X-ray diffraction. We identify the three critical pressures, P1 that is the turn-on critical pressure of the h-cT phase transition and it coincides with the critical pressure for the sign change of Hall coefficient from positive to negative, a manifestation of the Fermi surface reconstruction, P2 that is the turn-off pressures of the h-cT phase transition, and P3 that is the critical pressure of the f-cT phase transition. By comparing the high-pressure results measured from the two kinds of samples, we find a distinct left-shift of the P1 for the doped sample, at the pressure of which its SVC state is fully suppressed, however the P2 and the P3 remain the same as that of the undoped one. Our results not only provide a consistent understanding on the results reported before, but also demonstrate the importance of the Fe-As bonding in stabilizing the superconductivity of the iron pnictide superconductors through the pressure window.

We propose a mechanism to engineer an $n$-photon blockade in a nonlinear cavity with an $n$-photon parametric drive $\lambda(\hat{a}^{\dag n}+\hat{a}^n)$. When an $n$-photon-excitation resonance condition is satisfied, the presence of n photons in the cavity suppresses the absorption of the subsequent photons. To confirm the validity of this proposal, we study the n-photon blockade in an atom-cavity system, a Kerr-nonlinear resonator, and two-coupled Kerr nonlinear resonators. Our results demonstrate that $n$-photon bunching and $(n+1)$-photon antibunching can be simultaneously obtained in these systems. This effect is due both to the anharmonic energy ladder and to the nature of the $n$-photon drive. To show the importance of the drive, we compare the results of the $n$-photon drive with a coherent (one-photon) drive, proving the enhancement of antibunching in the parametric-drive case. This proposal is general and can be applied to realize the $n$-photon blockade in other nonlinear systems.

Data centers, the engines of the global Internet, are supported by massive high-speed optical interconnects. In optical fiber communication, the classic direct detection obtains only the intensity of the optical field, while the coherent detection counterpart utilizes both phase and polarization diversities at the expense of beating with a narrow-linewidth and high-stable local oscillator (LO). Herein, we propose and demonstrate a four-dimensional Jones space optical field recovery (4-D JSFR) scheme without LO. The information encoded on the intensity and phase of both polarizations can be captured by the polarization-diversity full-field receiver structure and subsequently extracted through deep neural network-aided field recovery. It achieves similar electrical spectral efficiency as standard intradyne coherent detection. The fully recovered optical field can extend the transmission distance beyond the power fading limitation induced by fiber chromatic dispersion. Furthermore, the LO-free advantage makes 4-D JSFR suitable for monolithic photonic integration, offering a spectrally efficient and cost-effective candidate for large-scale data center applications. Our results could motivate a fundamental paradigm shift in the optical field recovery theory and future optical transceiver design., Comment: 29 pages, 7 figures

We study the $\rho$ and $\omega$ meson contribution to the radiative decays $X(3872)\rightarrow J/\psi \pi \gamma$ and $X(3872)\rightarrow J/\psi \pi\pi \gamma$. The $X(3872)\rightarrow J/\psi \pi \gamma$ is dominated by the $\omega$ meson. As for the $X(3872)\rightarrow J/\psi \pi\pi \gamma$, the contributions of the cascade decays through the $\rho$ and $\omega$ mesons are strongly suppressed with respect to the diagrams which proceed either through the $\psi(2S)$ or the three body decay of $\rho$. The branching ratios of $X(3872)\rightarrow J/\psi \pi \gamma$ and $X(3872)\rightarrow J/\psi \pi\pi \gamma$ are $(8.10^{+3.50}_{-2.88})\times10^{-3}$ and $(2.38\pm1.06)\%$, which may be accessible by the BESIII and LHCb Collaborations. Especailly, the $X(3872)\rightarrow J/\psi \pi \gamma$ and $X(3872)\rightarrow J/\psi \pi^+\pi^- \gamma$ decays can be employed to extract the couplings $g_{X\psi\omega}$ and $g_{X\psi\rho}$, which probe the isoscalar and isovector components of the X(3872) wave function respectively., Comment: 8 pages, 6 figures and 2 tables, accepted by Phys. Rev. D

A spectral variation accompanied with flux variability is a commonly-observed phenomenon for blazars. In order to further investigate the optical spectral feature of blazars, we have collected the long-term optical V and R band data of 27 blazars (14 BL Lacs and 13 FSRQs), and calculated their optical spectral indices. The results show that the spectral indices vary with respect to the brightness for all of these blazars. In general, the optical spectrum progressively becomes flatter (or steeper), when the brightness increases. However the spectrum changes more and more slowly, until it tends to be stable. In other words, the source becomes bluer (or redder) and then gradually stabilizes when it brightens, which are briefly named the bluer-stable-when-brighter (BSWB) and redder-stable-when-brighter (RSWB) behaviors, respectively. Thirteen of the 14 BL Lacs show the BSWB behavior, with an exception of AO 0235+164. On the contrary, most of FSRQs (10 out of 13) exhibit the RSWB trend. It is confirmed that blazars follow the two universal optical spectral behaviors, namely, BSWB and RSWB. The model of two constant-spectral-index components can well explain the optical spectral features qualitatively and quantitatively. The results illustrate that the optical emission are mainly composed of two stable-color components, i.e., less variable thermal emission and high variable synchrotron radiation. And in most cases, the thermal component of BL Lacs is redder than that of synchrotron radiation, whereas FSRQs are the opposite., Comment: 9 pages, 14 figures, accepted by MNRAS

Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference. V2C is more challenging than conventional text-to-speech tasks as it additionally requires the generated speech to exactly match the varying emotions and speaking speed presented in the video. Unlike previous works, we propose a novel movie dubbing architecture to tackle these problems via hierarchical prosody modelling, which bridges the visual information to corresponding speech prosody from three aspects: lip, face, and scene. Specifically, we align lip movement to the speech duration, and convey facial expression to speech energy and pitch via attention mechanism based on valence and arousal representations inspired by recent psychology findings. Moreover, we design an emotion booster to capture the atmosphere from global video scenes. All these embeddings together are used to generate mel-spectrogram and then convert to speech waves via existing vocoder. Extensive experimental results on the Chem and V2C benchmark datasets demonstrate the favorable performance of the proposed method. The source code and trained models will be released to the public., Comment: accepted to CVPR 2023