arXiv subjects

Biao Wang

Publications and source records attributed to Biao Wang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Bounds for Erdős covering systems in global function fields

Covering systems of the integers were introduced by Erdős in 1950. Since then, many beautiful questions and conjectures about these objects have been posed. Most famously, Erdős asked whether the minimum modulus of a covering system with distinct moduli is arbitrarily large. This problem was resolved in 2015 by Hough, who proved that the minimum modulus is bounded. In 2022, Balister et al. developed Hough's method and gave a simpler but more versatile proof of Hough's result. Their technique has many applications in a number of variants on Erdős' minimum modulus problem. In this paper, we show that there is no covering system of multiplicity $s$ in any global function field of genus $g$ over $\mathbb{F}_q$ for $q\geq(82.26+18.88g)e^{0.95g}s^2$. Moreover, we obtain that there is no covering system of $\mathbb{F}_q[x]$ with distinct moduli for $q>73$. This improves the results in the previous work of the author joint with Li, Wang and Yi.

math.NT↗

arXiv2024

Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights

Despite the recognized potential of multimodal data to improve model accuracy, many large-scale industrial recommendation systems, including Taobao display advertising system, predominantly depend on sparse ID features in their models. In this work, we explore approaches to leverage multimodal data to enhance the recommendation accuracy. We start from identifying the key challenges in adopting multimodal data in a manner that is both effective and cost-efficient for industrial systems. To address these challenges, we introduce a two-phase framework, including: 1) the pre-training of multimodal representations to capture semantic similarity, and 2) the integration of these representations with existing ID-based models. Furthermore, we detail the architecture of our production system, which is designed to facilitate the deployment of multimodal representations. Since the integration of multimodal representations in mid-2023, we have observed significant performance improvements in Taobao display advertising system. We believe that the insights we have gathered will serve as a valuable resource for practitioners seeking to leverage multimodal data in their systems.

cs.IR↗

arXiv2024

PersonificationNet: Making customized subject act like a person

Recently customized generation has significant potential, which uses as few as 3-5 user-provided images to train a model to synthesize new images of a specified subject. Though subsequent applications enhance the flexibility and diversity of customized generation, fine-grained control over the given subject acting like the person's pose is still lack of study. In this paper, we propose a PersonificationNet, which can control the specified subject such as a cartoon character or plush toy to act the same pose as a given referenced person's image. It contains a customized branch, a pose condition branch and a structure alignment module. Specifically, first, the customized branch mimics specified subject appearance. Second, the pose condition branch transfers the body structure information from the human to variant instances. Last, the structure alignment module bridges the structure gap between human and specified subject in the inference stage. Experimental results show our proposed PersonificationNet outperforms the state-of-the-art methods.

cs.CV↗

arXiv2024

Classification of Power Quality Disturbances Using Resnet with Channel Attention Mechanism

The detection and classification of power quality disturbances (PQDs) carries significant importance for power systems. In response to this imperative, numerous intelligent diagnostic methods have been developed. However, existing identification methods usually concentrate on single-type signals or on complex signals with two types, rendering them susceptible to noisy labels and environmental effects. This study proposes a novel method for the classification of PQDs, termed ST-GSResNet, which utilizes the S-Transform and an improved residual neural network (ResNet) with a channel attention mechanism. The ST-GSResNet approach initially uses the S-Transform to transform a time-series signal into a 2D time-frequency image for feature enhancement. Then, an improved ResNet model is introduced, which employs grouped convolution instead of the traditional convolution operation. This improvement aims to facilitate learning with a block-diagonal structured sparsity on the channel dimension, the highly-correlated filters are learned in a more structured way in the networks with filter groups. By reducing the number of parameters in the network in this significant manner, the model becomes less prone to overfitting. Furthermore, the SE module concentrates on primary components, which enhances the model's robustness in recognition and immunity to noise. Experimental results demonstrate that, compared to existing deep learning models, our approach has advantages in computational efficiency and classification accuracy.

eess.SP↗

arXiv2024

A generalization of the Titchmarsh divisor problem

Let $d^{(k)}(n)$ be the $k$-free divisor function for integer $k\ge2$. Let $a$ be a nonzero integer. In this paper, we establish an asymptotic formula \begin{equation*} \sum_{p\leq x} d^{(k)}(p-a) =b_k \cdot x+O\left(\frac{x}{\log x}\right) \end{equation*} related to the Titchmarsh divisor problem, where $b_k$ is a positive constant dependent on $k$ and $a$. For the proof, we apply a result of Felix and show a general asymptotic formula for a class of arithmetic functions including the unitary divisor function, $k$-free divisor function and the proper Pillai's function.

math.NT↗

arXiv2024

On covering systems of polynomial rings over finite fields

In 1950, Erdős posed a question known as the minimum modulus problem on covering systems for $\mathbb{Z}$, which asked whether the minimum modulus of a covering system with distinct moduli is bounded. This long-standing problem was finally resolved by Hough in 2015, as he proved that the minimum modulus of any covering system with distinct moduli does not exceed $10^{16}$. Recently, Balister, Bollobás, Morris, Sahasrabudhe, and Tiba developed a versatile method called the distortion method and significantly reduced Hough's bound to $616,000$. In this paper, we apply this method to present a proof that the smallest degree of the moduli in any covering system for $\mathbb{F}_q[x]$ of multiplicity $s$ is bounded by a constant depending only on $s$ and $q$. Consequently, we successfully resolve the minimum modulus problem for $\mathbb{F}_q[x]$ and disprove a conjecture by Azlin.

math.NT↗

arXiv2024

GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction

In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model. This model generalizes graph diffusion in different feature spaces, and uses the inception module to avoid the large amount of computations caused by complex network structures. We evaluate GIDN model on Open Graph Benchmark(OGB) datasets, reached an 11% higher performance than AGDN on ogbl-collab dataset.

cs.LG↗

arXiv2024

AtomoVideo: High Fidelity Image-to-Video Generation

Recently, video generation has achieved significant rapid development based on superior text-to-image generation techniques. In this work, we propose a high fidelity framework for image-to-video generation, named AtomoVideo. Based on multi-granularity image injection, we achieve higher fidelity of the generated video to the given image. In addition, thanks to high quality datasets and training strategies, we achieve greater motion intensity while maintaining superior temporal consistency and stability. Our architecture extends flexibly to the video frame prediction task, enabling long sequence prediction through iterative generation. Furthermore, due to the design of adapter training, our approach can be well combined with existing personalized models and controllable modules. By quantitatively and qualitatively evaluation, AtomoVideo achieves superior results compared to popular methods, more examples can be found on our project website: https://atomo-video.github.io/.

cs.CV↗

arXiv2024

Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation

Image-to-video (I2V) generation tasks always suffer from keeping high fidelity in the open domains. Traditional image animation techniques primarily focus on specific domains such as faces or human poses, making them difficult to generalize to open domains. Several recent I2V frameworks based on diffusion models can generate dynamic content for open domain images but fail to maintain fidelity. We found that two main factors of low fidelity are the loss of image details and the noise prediction biases during the denoising process. To this end, we propose an effective method that can be applied to mainstream video diffusion models. This method achieves high fidelity based on supplementing more precise image information and noise rectification. Specifically, given a specified image, our method first adds noise to the input image latent to keep more details, then denoises the noisy latent with proper rectification to alleviate the noise prediction biases. Our method is tuning-free and plug-and-play. The experimental results demonstrate the effectiveness of our approach in improving the fidelity of generated videos. For more image-to-video generated results, please refer to the project website: https://noise-rectification.github.io.

cs.CV↗

arXiv2024

Hierarchical Masked 3D Diffusion Model for Video Outpainting

Video outpainting aims to adequately complete missing areas at the edges of video frames. Compared to image outpainting, it presents an additional challenge as the model should maintain the temporal consistency of the filled area. In this paper, we introduce a masked 3D diffusion model for video outpainting. We use the technique of mask modeling to train the 3D diffusion model. This allows us to use multiple guide frames to connect the results of multiple video clip inferences, thus ensuring temporal consistency and reducing jitter between adjacent frames. Meanwhile, we extract the global frames of the video as prompts and guide the model to obtain information other than the current video clip using cross-attention. We also introduce a hybrid coarse-to-fine inference pipeline to alleviate the artifact accumulation problem. The existing coarse-to-fine pipeline only uses the infilling strategy, which brings degradation because the time interval of the sparse frames is too large. Our pipeline benefits from bidirectional learning of the mask modeling and thus can employ a hybrid strategy of infilling and interpolation when generating sparse frames. Experiments show that our method achieves state-of-the-art results in video outpainting tasks. More results and codes are provided at our https://fanfanda.github.io/M3DDM/.

cs.CV↗

arXiv2023

Generative Action Description Prompts for Skeleton-based Action Recognition

Skeleton-based action recognition has recently received considerable attention. Current approaches to skeleton-based action recognition are typically formulated as one-hot classification tasks and do not fully exploit the semantic relations between actions. For example, "make victory sign" and "thumb up" are two actions of hand gestures, whose major difference lies in the movement of hands. This information is agnostic from the categorical one-hot encoding of action classes but could be unveiled from the action description. Therefore, utilizing action description in training could potentially benefit representation learning. In this work, we propose a Generative Action-description Prompts (GAP) approach for skeleton-based action recognition. More specifically, we employ a pre-trained large-scale language model as the knowledge engine to automatically generate text descriptions for body parts movements of actions, and propose a multi-modal training scheme by utilizing the text encoder to generate feature vectors for different body parts and supervise the skeleton encoder for action representation learning. Experiments show that our proposed GAP method achieves noticeable improvements over various baseline models without extra computation cost at inference. GAP achieves new state-of-the-arts on popular skeleton-based action recognition benchmarks, including NTU RGB+D, NTU RGB+D 120 and NW-UCLA. The source code is available at https://github.com/MartinXM/GAP.

cs.CV↗

arXiv2023

Generalizations of the Erdős-Kac Theorem and the Prime Number Theorem

In this paper, we study the linear independence between the distribution of the number of prime factors of integers and that of the largest prime factors of integers. Respectively, under a restriction on the largest prime factors of integers, we will refine the Erdős-Kac Theorem and Loyd's recent result on Bergelson and Richter's dynamical generalizations of the Prime Number Theorem. At the end, we will show that the analogue of these results holds with respect to the Erdős-Pomerance Theorem as well.

math.NT↗

arXiv2023

TJ-FlyingFish: Design and Implementation of an Aerial-Aquatic Quadrotor with Tiltable Propulsion Units

Aerial-aquatic vehicles are capable to move in the two most dominant fluids, making them more promising for a wide range of applications. We propose a prototype with special designs for propulsion and thruster configuration to cope with the vast differences in the fluid properties of water and air. For propulsion, the operating range is switched for the different mediums by the dual-speed propulsion unit, providing sufficient thrust and also ensuring output efficiency. For thruster configuration, thrust vectoring is realized by the rotation of the propulsion unit around the mount arm, thus enhancing the underwater maneuverability. This paper presents a quadrotor prototype of this concept and the design details and realization in practice.

cs.RO↗

arXiv2022

Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing

Along with the widespread use of face recognition systems, their vulnerability has become highlighted. While existing face anti-spoofing methods can be generalized between attack types, generic solutions are still challenging due to the diversity of spoof characteristics. Recently, the spoof trace disentanglement framework has shown great potential for coping with both seen and unseen spoof scenarios, but the performance is largely restricted by the single-modal input. This paper focuses on this issue and presents a multi-modal disentanglement model which targetedly learns polysemantic spoof traces for more accurate and robust generic attack detection. In particular, based on the adversarial learning mechanism, a two-stream disentangling network is designed to estimate spoof patterns from the RGB and depth inputs, respectively. In this case, it captures complementary spoofing clues inhering in different attacks. Furthermore, a fusion module is exploited, which recalibrates both representations at multiple stages to promote the disentanglement in each individual modality. It then performs cross-modality aggregation to deliver a more comprehensive spoof trace representation for prediction. Extensive evaluations are conducted on multiple benchmarks, demonstrating that learning polysemantic spoof traces favorably contributes to anti-spoofing with more perceptible and interpretable results.

cs.CV↗

arXiv2022

Video Object of Interest Segmentation

In this work, we present a new computer vision task named video object of interest segmentation (VOIS). Given a video and a target image of interest, our objective is to simultaneously segment and track all objects in the video that are relevant to the target image. This problem combines the traditional video object segmentation task with an additional image indicating the content that users are concerned with. Since no existing dataset is perfectly suitable for this new task, we specifically construct a large-scale dataset called LiveVideos, which contains 2418 pairs of target images and live videos with instance-level annotations. In addition, we propose a transformer-based method for this task. We revisit Swin Transformer and design a dual-path structure to fuse video and image features. Then, a transformer decoder is employed to generate object proposals for segmentation and tracking from the fused features. Extensive experiments on LiveVideos dataset show the superiority of our proposed method.

cs.CV↗

arXiv2022

Estimation of Reliable Proposal Quality for Temporal Action Detection

Temporal action detection (TAD) aims to locate and recognize the actions in an untrimmed video. Anchor-free methods have made remarkable progress which mainly formulate TAD into two tasks: classification and localization using two separate branches. This paper reveals the temporal misalignment between the two tasks hindering further progress. To address this, we propose a new method that gives insights into moment and region perspectives simultaneously to align the two tasks by acquiring reliable proposal quality. For the moment perspective, Boundary Evaluate Module (BEM) is designed which focuses on local appearance and motion evolvement to estimate boundary quality and adopts a multi-scale manner to deal with varied action durations. For the region perspective, we introduce Region Evaluate Module (REM) which uses a new and efficient sampling method for proposal feature representation containing more contextual information compared with point feature to refine category score and proposal boundary. The proposed Boundary Evaluate Module and Region Evaluate Module (BREM) are generic, and they can be easily integrated with other anchor-free TAD methods to achieve superior performance. In our experiments, BREM is combined with two different frameworks and improves the performance on THUMOS14 by 3.6% and 1.0% respectively, reaching a new state-of-the-art (63.6% average mAP). Meanwhile, a competitive result of 36.2% average mAP is achieved on ActivityNet-1.3 with the consistent improvement of BREM. The codes are released at https://github.com/Junshan233/BREM.

cs.CV↗

arXiv2022

Motion and Appearance Adaptation for Cross-Domain Motion Transfer

Motion transfer aims to transfer the motion of a driving video to a source image. When there are considerable differences between object in the driving video and that in the source image, traditional single domain motion transfer approaches often produce notable artifacts; for example, the synthesized image may fail to preserve the human shape of the source image (cf . Fig. 1 (a)). To address this issue, in this work, we propose a Motion and Appearance Adaptation (MAA) approach for cross-domain motion transfer, in which we regularize the object in the synthesized image to capture the motion of the object in the driving frame, while still preserving the shape and appearance of the object in the source image. On one hand, considering the object shapes of the synthesized image and the driving frame might be different, we design a shape-invariant motion adaptation module that enforces the consistency of the angles of object parts in two images to capture the motion information. On the other hand, we introduce a structure-guided appearance consistency module designed to regularize the similarity between the corresponding patches of the synthesized image and the source image without affecting the learned motion in the synthesized image. Our proposed MAA model can be trained in an end-to-end manner with a cyclic reconstruction loss, and ultimately produces a satisfactory motion transfer result (cf . Fig. 1 (b)). We conduct extensive experiments on human dancing dataset Mixamo-Video to Fashion-Video and human face dataset Vox-Celeb to Cufs; on both of these, our MAA model outperforms existing methods both quantitatively and qualitatively.

cs.CV↗

arXiv2022

Strain engineering of two-dimensional piezo-photocatalytic materials for hydrogen production

Low-dimensional transition metal dichalcogenides (TMDC) exhibit great photocatalytic performance and tunability. In this work, using first-principles simulations based on density functional theory (DFT), we demonstrate that external electric bias can be employed to further improve the photocatalytic hydrogen production efficiency of the six AB$_{2}$ (A=Mo, W and B=S, Se, Te) TMDC monolayers by exploiting their piezoelectric response. In particular, when subjected to a proper amount of electrically induced tensile biaxial strain, most TMDC monolayers turn into potentially ideal photocatalyst towards the hydrogen evolution reaction (HER). The beneficial effects of introducing tensile biaxial strain on the TMDC monolayers are not limited to the reduction of the band gap and proper adjustment of the band edge positions, but also to the modification of the H adsorption free energy in such a way that the HER reaction is noticeably favored.

cond-mat.mtrl-sci↗