Search

Generating realistic 3D human-object interactions (HOIs) from text descriptions is a active research topic with potential applications in virtual and augmented reality, robotics, and animation. However, creating high-quality 3D HOIs remains challenging due to the lack of large-scale interaction data and the difficulty of ensuring physical plausibility, especially in out-of-domain (OOD) scenarios. Current methods tend to focus either on the body or the hands, which limits their ability to produce cohesive and realistic interactions. In this paper, we propose OOD-HOI, a text-driven framework for generating whole-body human-object interactions that generalize well to new objects and actions. Our approach integrates a dual-branch reciprocal diffusion model to synthesize initial interaction poses, a contact-guided interaction refiner to improve physical accuracy based on predicted contact areas, and a dynamic adaptation mechanism which includes semantic adjustment and geometry deformation to improve robustness. Experimental results demonstrate that our OOD-HOI could generate more realistic and physically plausible 3D interaction pose in OOD scenarios compared to existing methods.

Sound source localization aims to localize objects emitting the sound in visual scenes. Recent works obtaining impressive results typically rely on contrastive learning. However, the common practice of randomly sampling negatives in prior arts can lead to the false negative issue, where the sounds semantically similar to visual instance are sampled as negatives and incorrectly pushed away from the visual anchor/query. As a result, this misalignment of audio and visual features could yield inferior performance. To address this issue, we propose a novel audio-visual learning framework which is instantiated with two individual learning schemes: self-supervised predictive learning (SSPL) and semantic-aware contrastive learning (SACL). SSPL explores image-audio positive pairs alone to discover semantically coherent similarities between audio and visual features, while a predictive coding module for feature alignment is introduced to facilitate the positive-only learning. In this regard SSPL acts as a negative-free method to eliminate false negatives. By contrast, SACL is designed to compact visual features and remove false negatives, providing reliable visual anchor and audio negatives for contrast. Different from SSPL, SACL releases the potential of audio-visual contrastive learning, offering an effective alternative to achieve the same goal. Comprehensive experiments demonstrate the superiority of our approach over the state-of-the-arts. Furthermore, we highlight the versatility of the learned representation by extending the approach to audio-visual event classification and object detection tasks. Code and models are available at: https://github.com/zjsong/SACL., Comment: arXiv admin note: substantial text overlap with arXiv:2203.13412

Urban areas, as the primary human habitat in modern civilization, accommodate a broad spectrum of social activities. With the surge of embodied intelligence, recent years have witnessed an increasing presence of physical agents in urban areas, such as autonomous vehicles and delivery robots. As a result, practitioners significantly value crafting authentic, simulation-ready 3D cities to facilitate the training and verification of such agents. However, this task is quite challenging. Current generative methods fall short in either diversity, controllability, or fidelity. In this work, we resort to the procedural content generation (PCG) technique for high-fidelity generation. It assembles superior assets according to empirical rules, ultimately leading to industrial-grade outcomes. To ensure diverse and self contained creation, we design a management protocol to accommodate extensive PCG plugins with distinct functions and interfaces. Based on this unified PCG library, we develop a multi-agent framework to transform multi-modal instructions, including OSM, semantic maps, and satellite images, into executable programs. The programs coordinate relevant plugins to construct the 3D city consistent with the control condition. A visual feedback scheme is introduced to further refine the initial outcomes. Our method, named CityX, demonstrates its superiority in creating diverse, controllable, and realistic 3D urban scenes. The synthetic scenes can be seamlessly deployed as a real-time simulator and an infinite data generator for embodied intelligence research. Our project page: https://cityx-lab.github.io.

The scarcity of large-scale 3D-text paired data poses a great challenge on open vocabulary 3D scene understanding, and hence it is popular to leverage internet-scale 2D data and transfer their open vocabulary capabilities to 3D models through knowledge distillation. However, the existing distillation-based 3D scene understanding approaches rely on the representation capacity of 2D models, disregarding the exploration of geometric priors and inherent representational advantages offered by 3D data. In this paper, we propose an effective approach, namely Geometry Guided Self-Distillation (GGSD), to learn superior 3D representations from 2D pre-trained models. Specifically, we first design a geometry guided distillation module to distill knowledge from 2D models, and then leverage the 3D geometric priors to alleviate the inherent noise in 2D models and enhance the representation learning process. Due to the advantages of 3D representation, the performance of the distilled 3D student model can significantly surpass that of the 2D teacher model. This motivates us to further leverage the representation advantages of 3D data through self-distillation. As a result, our proposed GGSD approach outperforms the existing open vocabulary 3D scene understanding methods by a large margin, as demonstrated by our experiments on both indoor and outdoor benchmark datasets.

Interlayer rotation in van der Waals (vdW) materials offers great potential for manipulating phonon dynamics and heat flow in advanced electronics with ever higher compactness and power density. However, despite extensive theoretical efforts in recent years, experimental measurements remain scarce especially due to the critical challenges of preparing single-crystalline twisted interfaces and probing interfacial thermal transport with sufficient resolution. Here, we exploited the intrinsic twisted interfaces in highly oriented pyrolytic graphite (HOPG). By developing novel experimental schemes based on microfabricated mesas, we managed to achieve simultaneous mechanical characterizations and thermal measurements. In particular, we pushed the HOPG mesas with a microprobe to identify and rotate single-crystalline intrinsic interfaces owing to their slippery nature as is well known in structural superlubricity. Remarkably, we observed over 30-fold suppression of thermal conductance for the slippery interfaces by using epitaxial graphite as a control. Nonetheless, the interfacial conductance remains around 600 $\mathrm{MWm^{-2}K^{-1}}$ which surpasses the highest values for artificially stacked vdW structures by more than five times. Further, atomic simulations revealed the predominant role of the transverse acoustic phonons. Together, our findings highlight a general physical picture that directly correlates interfacial thermal transport with sliding resistance, and lay the foundation for twist-enabled thermal management which are particularly beneficial to twistronics and slidetronics.

Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The effect of the design of each component is still unclear. In addition, the iterative denoising process consumes considerable computational overhead, which is prohibitive for real-time scenarios such as virtual characters and humanoid robots. For this reason, we first conduct a comprehensive investigation into network architectures, training strategies, and inference processs. Based on the profound analysis, we tailor each component for efficient high-quality human motion generation. Despite the promising performance, the tailored model still suffers from foot skating which is an ubiquitous issue in diffusion-based solutions. To eliminate footskate, we identify foot-ground contact and correct foot motions along the denoising process. By organically combining these well-designed components together, we present StableMoFusion, a robust and efficient framework for human motion generation. Extensive experimental results show that our StableMoFusion performs favorably against current state-of-the-art methods. Project page: https://h-y1heng.github.io/StableMoFusion-page/

Understanding the transition mechanism of boundary layer flows is of great significance in physics and engineering, especially due to the current development of supersonic and hypersonic aircraft. In this paper, we construct multiple unstable acoustic modes so-called Mack modes, which play a crucial role during the early stage of transition in the supersonic boundary layer. To this end, we develop an inner-outer gluing iteration to solve a hyperbolic-elliptic mixed type and singular system.

Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance. By performing score distillation sampling (SDS) iteratively across different views, these methods succeed in lifting 2D generative prior to the 3D space. However, such a 2D generative image prior bakes the effect of illumination and shadow into the texture. As a result, material maps optimized by SDS inevitably involve spurious correlated components. The absence of precise material definition makes it infeasible to relight the generated assets reasonably in novel scenes, which limits their application in downstream scenarios. In contrast, humans can effortlessly circumvent this ambiguity by deducing the material of the object from its appearance and semantics. Motivated by this insight, we propose MaterialSeg3D, a 3D asset material generation framework to infer underlying material from the 2D semantic prior. Based on such a prior model, we devise a mechanism to parse material in 3D space. We maintain a UV stack, each map of which is unprojected from a specific viewpoint. After traversing all viewpoints, we fuse the stack through a weighted voting scheme and then employ region unification to ensure the coherence of the object parts. To fuel the learning of semantics prior, we collect a material dataset, named Materialized Individual Objects (MIO), which features abundant images, diverse categories, and accurate annotations. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method.

Developing comprehensive explicit world models is crucial for understanding and simulating real-world scenarios. Recently, Procedural Controllable Generation (PCG) has gained significant attention in large-scale scene generation by enabling the creation of scalable, high-quality assets. However, PCG faces challenges such as limited modular diversity, high expertise requirements, and challenges in managing the diverse elements and structures in complex scenes. In this paper, we introduce a large-scale scene generation framework, SceneX, which can automatically produce high-quality procedural models according to designers' textual descriptions. Specifically, the proposed method comprises two components, PCGHub and PCGPlanner. The former encompasses an extensive collection of accessible procedural assets and thousands of hand-craft API documents to perform as a standard protocol for PCG controller. The latter aims to generate executable actions for Blender to produce controllable and precise 3D assets guided by the user's instructions. Extensive experiments demonstrated the capability of our method in controllable large-scale scene generation, including nature scenes and unbounded cities, as well as scene editing such as asset placement and season translation.

For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners. These requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify two key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. To address them, we propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we use LoRA modules to fine-tune the FFN layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. GS-LoRA is effective, parameter-efficient, data-efficient, and easy to implement. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that GS-LoRA manages to forget specific classes with minimal impact on other classes. Codes will be released on \url{https://github.com/bjzhb666/GS-LoRA}., Comment: Accepted by CVPR 2024, latest version ahead of carema ready version

Two-dimensional (2D) crystals proved revolutionary soon after graphene was discovered in 2004. However, 2D amorphous materials only became accessible in 2020 and remain largely unexplored. In particular, the thermophysical properties of amorphous materials are of great interest upon transition from 3D to 2D. Here, we probe thermal transport in 2D amorphous carbon. A cross-plane thermal conductivity ($\kappa$) down to 0.079 $\rm{Wm}^{-1}K^{-1}$ is measured for van der Waals stacked multilayers at room temperature, which is among the lowest reported to date. Meanwhile, an unexpectedly high in-plane $\kappa$ is obtained for freestanding monolayers which is a few times larger than what is predicted by conventional wisdom for 3D amorphous carbon with similar $\rm{sp}^{2}$ fraction. Our molecular dynamics simulations reveal the role of disorder and highlight the impact of dimensionality. Amorphous materials at the 2D limit open up new avenues for understanding and manipulating heat at the atomic scale.

The star formation histories (SFHs) of galaxies provide valuable insights into galaxy evolution and stellar physics. Understanding the SFHs enables the study of chemical enrichment of galaxies, star formation triggered by interactions, and the behavior of various stellar populations. This work investigates the SFHs of ten dwarf galaxies in the Local Group (LG), which spans a wide range of types, masses, luminosities, and metallicities. The analysis is based on our new sample of the member stars in the LG after removing the foreground dwarf stars by the near-infrared color-color diagram and the Gaia astrometric information. The samples include the most complete and pure red supergiants and asymptotic giant branch stars to gain valuable insights into the recent SFHs of the galaxies. The CMD fitting method is introduced to measure the SFH. The Padova isochrones are used to generate initial model CMDs, accounting for photometric errors and completeness through star field simulations to match the completeness and error distributions of the observed CMDs. Subsequently, the SFHs, distance modulus, and metallicity of the ten dwarf galaxies are determined by fitting the CMDs. The results indicate that the star formation rates (SFRs) of dwarf irregulars show a gradual increase, while those of dwarf ellipticals exhibit a gradual decrease from the past to the present. Furthermore, this work shows that the star formation activity in dwarf ellipticals persisted up to 30 Myr ago. A significant increasing feature in the SFH of NGC 6822 reveals star formation activity triggered by an interaction event., Comment: 21 pages, 11 figures, 5 tables, accepted for publication in ApJ

3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a Gaussian Decomposition scheme, which ingeniously utilizes the special structure of 3D Gaussian, finds out, and then decomposes the boundary Gaussians. Moreover, to achieve fast interactive 3D segmentation, we introduce a novel training-free pipeline by lifting a 2D foundation model to 3D-GS. Extensive experiments demonstrate that our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks.

Indoor scene generation has attracted significant attention recently as it is crucial for applications of gaming, virtual reality, and interior design. Current indoor scene generation methods can produce reasonable room layouts but often lack diversity and realism. This is primarily due to the limited coverage of existing datasets, including only large furniture without tiny furnishings in daily life. To address these challenges, we propose FurniScene, a large-scale 3D room dataset with intricate furnishing scenes from interior design professionals. Specifically, the FurniScene consists of 11,698 rooms and 39,691 unique furniture CAD models with 89 different types, covering things from large beds to small teacups on the coffee table. To better suit fine-grained indoor scene layout generation, we introduce a novel Two-Stage Diffusion Scene Model (TSDSM) and conduct an evaluation benchmark for various indoor scene generation based on FurniScene. Quantitative and qualitative evaluations demonstrate the capability of our method to generate highly realistic indoor scenes. Our dataset and code will be publicly available soon.

Masked visual modeling has attracted much attention due to its promising potential in learning generalizable representations. Typical approaches urge models to predict specific contents of masked tokens, which can be intuitively considered as teaching a student (the model) to solve given problems (predicting masked contents). Under such settings, the performance is highly correlated with mask strategies (the difficulty of provided problems). We argue that it is equally important for the model to stand in the shoes of a teacher to produce challenging problems by itself. Intuitively, patches with high values of reconstruction loss can be regarded as hard samples, and masking those hard patches naturally becomes a demanding reconstruction task. To empower the model as a teacher, we propose Hard Patches Mining (HPM), predicting patch-wise losses and subsequently determining where to mask. Technically, we introduce an auxiliary loss predictor, which is trained with a relative objective to prevent overfitting to exact loss values. Also, to gradually guide the training procedure, we propose an easy-to-hard mask strategy. Empirically, HPM brings significant improvements under both image and video benchmarks. Interestingly, solely incorporating the extra loss prediction objective leads to better representations, verifying the efficacy of determining where is hard to reconstruct. The code is available at https://github.com/Haochen-Wang409/HPM., Comment: arXiv admin note: substantial text overlap with arXiv:2304.05919

Full projector compensation is a practical task of projector-camera systems. It aims to find a projector input image, named compensation image, such that when projected it cancels the geometric and photometric distortions due to the physical environment and hardware. State-of-the-art methods use deep learning to address this problem and show promising performance for low-resolution setups. However, directly applying deep learning to high-resolution setups is impractical due to the long training time and high memory cost. To address this issue, this paper proposes a practical full compensation solution. Firstly, we design an attention-based grid refinement network to improve geometric correction quality. Secondly, we integrate a novel sampling scheme into an end-to-end compensation network to alleviate computation and introduce attention blocks to preserve key features. Finally, we construct a benchmark dataset for high-resolution projector full compensation. In experiments, our method demonstrates clear advantages in both efficiency and quality.

Contemporary domain adaptation offers a practical solution for achieving cross-domain transfer of semantic segmentation between labeled source data and unlabeled target data. These solutions have gained significant popularity; however, they require the model to be retrained when the test environment changes. This can result in unbearable costs in certain applications due to the time-consuming training process and concerns regarding data privacy. One-shot domain adaptation methods attempt to overcome these challenges by transferring the pre-trained source model to the target domain using only one target data. Despite this, the referring style transfer module still faces issues with computation cost and over-fitting problems. To address this problem, we propose a novel framework called Informative Data Mining (IDM) that enables efficient one-shot domain adaptation for semantic segmentation. Specifically, IDM provides an uncertainty-based selection criterion to identify the most informative samples, which facilitates quick adaptation and reduces redundant training. We then perform a model adaptation method using these selected samples, which includes patch-wise mixing and prototype-based information maximization to update the model. This approach effectively enhances adaptation and mitigates the overfitting problem. In general, we provide empirical evidence of the effectiveness and efficiency of IDM. Our approach outperforms existing methods and achieves a new state-of-the-art one-shot performance of 56.7\%/55.4\% on the GTA5/SYNTHIA to Cityscapes adaptation tasks, respectively. The code will be released at \url{https://github.com/yxiwang/IDM}., Comment: Accepted by ICCV 2023

As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident. To address this, we present DropPos, a novel pretext task designed to reconstruct Dropped Positions. The formulation of DropPos is simple: we first drop a large random subset of positional embeddings and then the model classifies the actual position for each non-overlapping patch among all possible positions solely based on their visual appearance. To avoid trivial solutions, we increase the difficulty of this task by keeping only a subset of patches visible. Additionally, considering there may be different patches with similar visual appearances, we propose position smoothing and attentive reconstruction strategies to relax this classification problem, since it is not necessary to reconstruct their exact positions in these cases. Empirical evaluations of DropPos show strong capabilities. DropPos outperforms supervised pre-training and achieves competitive results compared with state-of-the-art self-supervised alternatives on a wide range of downstream benchmarks. This suggests that explicitly encouraging spatial reasoning abilities, as DropPos does, indeed contributes to the improved location awareness of ViTs. The code is publicly available at https://github.com/Haochen-Wang409/DropPos., Comment: Accepted by NeurIPS 2023

Domain generalization (DG) attempts to generalize a model trained on single or multiple source domains to the unseen target domain. Benefiting from the success of Visual-and-Language Pre-trained models in recent years, we argue that it is crucial for domain generalization by introducing extra text information. In this paper, we develop a novel Text-guided Domain Generalization (TDG) paradigm for domain generalization, which includes three following aspects. Specifically, we first devise an automatic words generation method to extend the description of current domains with novel domain-relevant words. Then, we embed the generated domain information into the text feature space, by the proposed prompt learning-based text feature generation method, which shares a common representation space with the image feature. Finally, we utilize both input image features and generated text features to train a specially designed classifier that generalizes well on unseen target domains, while the image encoder is also updated under the supervision of gradients back propagated from the classifier. Our experimental results show that the techniques incorporated by TDG contribute to the performance in an easy implementation manner. Experimental results on several domain generalization benchmarks show that our proposed framework achieves superior performance by effectively leveraging generated text information in domain generalization., Comment: 8pages,3 figures

The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes. Previous work has introduced generative replay, which involves replaying old class samples generated from a pre-trained GAN, to address the issues of catastrophic forgetting and privacy concerns. However, the generated images lack semantic precision and exhibit out-of-distribution characteristics, resulting in inaccurate masks that further degrade the segmentation performance. To tackle these challenges, we propose DiffusePast, a novel framework featuring a diffusion-based generative replay module that generates semantically accurate images with more reliable masks guided by different instructions (e.g., text prompts or edge maps). Specifically, DiffusePast introduces a dual-generator paradigm, which focuses on generating old class images that align with the distribution of downstream datasets while preserving the structure and layout of the original images, enabling more precise masks. To adapt to the novel visual concepts of newly added classes continuously, we incorporate class-wise token embedding when updating the dual-generator. Moreover, we assign adequate pseudo-labels of old classes to the background pixels in the new step images, further mitigating the forgetting of previously learned knowledge. Through comprehensive experiments, our method demonstrates competitive performance across mainstream benchmarks, striking a better balance between the performance of old and novel classes., Comment: e.g.: 13 pages, 7 figures

The crux of label-efficient semantic segmentation is to produce high-quality pseudo-labels to leverage a large amount of unlabeled or weakly labeled data. A common practice is to select the highly confident predictions as the pseudo-ground-truths for each pixel, but it leads to a problem that most pixels may be left unused due to their unreliability. However, we argue that every pixel matters to the model training, even those unreliable and ambiguous pixels. Intuitively, an unreliable prediction may get confused among the top classes, however, it should be confident about the pixel not belonging to the remaining classes. Hence, such a pixel can be convincingly treated as a negative key to those most unlikely categories. Therefore, we develop an effective pipeline to make sufficient use of unlabeled data. Concretely, we separate reliable and unreliable pixels via the entropy of predictions, push each unreliable pixel to a category-wise queue that consists of negative keys, and manage to train the model with all candidate pixels. Considering the training evolution, we adaptively adjust the threshold for the reliable-unreliable partition. Experimental results on various benchmarks and training settings demonstrate the superiority of our approach over the state-of-the-art alternatives., Comment: Accepted by IJCV. arXiv admin note: text overlap with arXiv:2203.03884

Domain adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, existing methods primarily focus on directly learning qualified target features, making it challenging to guarantee their discrimination in the absence of target labels. This work provides a new perspective. We observe that the features learned with source data manage to keep categorically discriminative during training, thereby enabling us to implicitly learn adequate target representations by simply \textbf{pulling target features close to source features for each category}. To this end, we propose T2S-DA, which we interpret as a form of pulling Target to Source for Domain Adaptation, encouraging the model in learning similar cross-domain features. Also, considering the pixel categories are heavily imbalanced for segmentation datasets, we come up with a dynamic re-weighting strategy to help the model concentrate on those underperforming classes. Extensive experiments confirm that T2S-DA learns a more discriminative and generalizable representation, significantly surpassing the state-of-the-art. We further show that our method is quite qualified for the domain generalization task, verifying its domain-invariant property., Comment: Accepted by IJCV

Generalized linear models (GLMs) form one of the most popular classes of models in statistics. The gamma variant is used, for instance, in actuarial science for the modelling of claim amounts in insurance. A flaw of GLMs is that they are not robust against outliers (i.e., against erroneous or extreme data points). A difference in trends in the bulk of the data and the outliers thus yields skewed inference and predictions. To address this problem, robust methods have been introduced. The most commonly applied robust method is frequentist and consists in an estimator which is derived from a modification of the derivative of the log-likelihood. We propose an alternative approach which is modelling-based and thus fundamentally different. It allows for an understanding and interpretation of the modelling, and it can be applied for both frequentist and Bayesian statistical analyses. The approach possesses appealing theoretical and empirical properties.

In this paper, we study the zero-viscosity limit of the compressible Navier-Stokes equations in a half-space with non-slip boundary condition. We justify the Prandtl boundary layer expansion for the analytic data: the compressible Navier-Stokes equations can be approximated by the compressible Euler equations away from the boundary, and by the compressible Prandtl equation near the boundary., Comment: 43 pages

The Tollmien-Schlichting (T-S) waves play a key role in the early stages of boundary layer transition. In a breakthrough work, Grenier, Guo and Nguyen gave the first rigorous construction of the T-S waves of temporal mode for the incompressible fluid. Yang and Zhang recently made an important contribution by constructing the compressible T-S waves of temporal mode for certain boundary layer profiles with Mach number $m<\frac{1}{\sqrt 3}$. In this paper, we construct the T-S waves of both temporal mode and spatial mode to the linearized compressible Navier-Stokes system around the boundary layer flow in the whole subsonic regime $m<1$, including the Blasius profile. Our approach is based on a novel iteration scheme between the quasi-incompressible and quasi-compressible systems, with a key ingredient being the solution of an Orr-Sommerfeld type equation using a new Airy-Airy-Rayleigh iteration instead of Rayleigh-Airy iteration introduced by Grenier, Guo and Nguyen. We believe the method developed in this work can be applied in solving other related problems for subsonic flows.

Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches, and their performances are highly related to pre-defined mask strategies. Intuitively, this procedure can be considered as training a student (the model) on solving given problems (predict masked patches). However, we argue that the model should not only focus on solving given problems, but also stand in the shoes of a teacher to produce a more challenging problem by itself. To this end, we propose Hard Patches Mining (HPM), a brand-new framework for MIM pre-training. We observe that the reconstruction loss can naturally be the metric of the difficulty of the pre-training task. Therefore, we introduce an auxiliary loss predictor, predicting patch-wise losses first and deciding where to mask next. It adopts a relative relationship learning strategy to prevent overfitting to exact reconstruction loss values. Experiments under various settings demonstrate the effectiveness of HPM in constructing masked images. Furthermore, we empirically find that solely introducing the loss prediction objective leads to powerful representations, verifying the efficacy of the ability to be aware of where is hard to reconstruct., Comment: Accepted to CVPR 2023

Few-Shot transfer learning has become a major focus of research as it allows recognition of new classes with limited labeled data. While it is assumed that train and test data have the same data distribution, this is often not the case in real-world applications. This leads to decreased model transfer effects when the new class distribution differs significantly from the learned classes. Research into Cross-Domain Few-Shot (CDFS) has emerged to address this issue, forming a more challenging and realistic setting. In this survey, we provide a detailed taxonomy of CDFS from the problem setting and corresponding solutions view. We summarise the existing CDFS network architectures and discuss the solution ideas for each direction the taxonomy indicates. Furthermore, we introduce various CDFS downstream applications and outline classification, detection, and segmentation benchmarks and corresponding standards for evaluation. We also discuss the challenges of CDFS research and explore potential directions for future investigation. Through this review, we aim to provide comprehensive guidance on CDFS research, enabling researchers to gain insight into the state-of-the-art while allowing them to build upon existing solutions to develop their own CDFS models.

Dust extinction law is crucial to recover the intrinsic energy distribution of celestial objects and infer the characteristics of interstellar dust. Based on the traditional pair method, an improved pair method is proposed to model the dust extinguished spectral energy distribution (SED) of an individual star. Instead of the mathematically parameterizing extinction curves, the extinction curves in this work are directly from the silicate-graphite dust model, so that the dust extinction law can be obtained and the dust properties can be analyzed simultaneously. The ATLAS9 stellar model atmosphere is adopted for the intrinsic SEDs in this work, while the silicate-graphite dust model with a dust size distribution of $dn/da \sim a^{-\alpha}{\rm exp}(-a/a_c),~0.005 < a < 5~\mu{\rm m}$ for each component is adopted for the model extinction curves. One typical extinction tracer in the dense region (V410 Anon9) and one in the diffuse region (Cyg OB2 \#12) of the MW are chosen to test the reliability and the practicability of the improved pair method in different stellar environments. The results are consistent with their interstellar environments and are in agreement with the previous observations and studies, which prove that the improved pair method is effective and applicable in different stellar environments. In addition to the reliable extinction results, the derived parameters in the dust model can be used to analyze the dust properties, which cannot be achieved by other methods with the mathematical extinction models. With the improved pair method, the stellar parameters can also be inferred and the extinction law beyond the wavelengths of observed data can be predicted based on the dust model as well.

As a new member of GECAM mission, the GECAM-C (also called High Energy Burst Searcher, HEBS) is a gamma-ray all-sky monitor onboard SATech-01 satellite, which was launched on July 27th, 2022 to detect gamma-ray transients from 6 keV to 6 MeV, such as Gamma-Ray Bursts (GRBs), high energy counterpart of Gravitational Waves (GWs) and Fast Radio Bursts (FRBs), and Soft Gamma-ray Repeaters (SGRs). Together with GECAM-A and GECAM-B launched in December 2020, GECAM-C will greatly improve the monitoring coverage, localization, as well as temporal and spectral measurements of gamma-ray transients. GECAM-C employs 12 SiPM-based Gamma-Ray Detectors (GRDs) to detect gamma-ray transients . In this paper, we firstly give a brief description of the design of GECAM-C GRDs, and then focus on the on-ground tests and in-flight performance of GRDs. We also did the comparison study of the SiPM in-flight performance between GECAM-C and GECAM-B. The results show GECAM-C GRD works as expected and is ready to make scientific observations., Comment: 18 pages, 16 figures

Collecting and annotating task-oriented dialog data is difficult, especially for highly specific domains that require expert knowledge. At the same time, informal communication channels such as instant messengers are increasingly being used at work. This has led to a lot of work-relevant information that is disseminated through those channels and needs to be post-processed manually by the employees. To alleviate this problem, we present TexPrax, a messaging system to collect and annotate problems, causes, and solutions that occur in work-related chats. TexPrax uses a chatbot to directly engage the employees to provide lightweight annotations on their conversation and ease their documentation work. To comply with data privacy and security regulations, we use an end-to-end message encryption and give our users full control over their data which has various advantages over conventional annotation tools. We evaluate TexPrax in a user-study with German factory employees who ask their colleagues for solutions on problems that arise during their daily work. Overall, we collect 202 task-oriented German dialogues containing 1,027 sentences with sentence-level expert annotations. Our data analysis also reveals that real-world conversations frequently contain instances with code-switching, varying abbreviations for the same entity, and dialects which NLP systems should be able to handle., Comment: Accepted at AACL 2022 (System Demonstrations). Code and data: https://github.com/UKPLab/TexPrax

The infrared excess from OB stars are commonly considered as contributions from ionized stellar wind or circumstellar dust. With the newly published LAMOST-OB catalog and GOSSS data, this work steps further on understanding the infrared excess of OB stars. Based on a forward modeling approach comparing the spectral slope of observational Spectral Energy Distributions (SED) and photospheric models, 1147 stars are found to have infrared excess from 7818 stars with good-quality photometric data. After removing the objects in the sightline of dark clouds, 532 ($\sim7\%$) B-type stars and 118 ($\sim23\%$) O-type stars are identified to be true OB stars with circumstellar infrared excess emission. The ionized stellar wind model and the circumstellar dust model are adopted to explain the infrared excess, and Bayes Factors are computed to quantitatively compare the two. It is shown that the infrared excess can be accounted for by the stellar wind for about 65\% cases in which 33\% by free-free emission and 32\% by synchrotron radiation. Other 30\% sources could have and 4\% should have a dust component or other mechanisms to explain the sharply increase flux at $\lambda > 10\mu$m. The parameters of dust model indicate a large-scale circumstellar halo structure which implies the origin of the dust from the birthplace of the OB stars. A statistical study suggests that the proportion with infrared excess in OB stars increases with stellar effective temperature and luminosity, and that there is no systematic change of the mechanism for infrared emission with stellar parameters., Comment: Accepted for publication in the ApJ (July 13, 2022). 17 pages, 9 figures. Typos corrected, authors info updated