arXiv subjects

Jian Dong

Publications and source records attributed to Jian Dong.

At least 37 records · Page 2Linked to original sources

arXiv2023

Cross-Element Combinatorial Selection for Multi-Element Creative in Display Advertising

The effectiveness of ad creatives is greatly influenced by their visual appearance. Advertising platforms can generate ad creatives with different appearances by combining creative elements provided by advertisers. However, with the increasing number of ad creative elements, it becomes challenging to select a suitable combination from the countless possibilities. The industry's mainstream approach is to select individual creative elements independently, which often overlooks the importance of interaction between creative elements during the modeling process. In response, this paper proposes a Cross-Element Combinatorial Selection framework for multiple creative elements, termed CECS. In the encoder process, a cross-element interaction is adopted to dynamically adjust the expression of a single creative element based on the current candidate creatives. In the decoder process, the creative combination problem is transformed into a cascade selection problem of multiple creative elements. A pointer mechanism with a cascade design is used to model the associations among candidates. Comprehensive experiments on real-world datasets show that CECS achieved the SOTA score on offline metrics. Moreover, the CECS algorithm has been deployed in our industrial application, resulting in a significant 6.02% CTR and 10.37% GMV lift, which is beneficial to the business.

cs.IR↗

arXiv2023

A Deep Behavior Path Matching Network for Click-Through Rate Prediction

User behaviors on an e-commerce app not only contain different kinds of feedback on items but also sometimes imply the cognitive clue of the user's decision-making. For understanding the psychological procedure behind user decisions, we present the behavior path and propose to match the user's current behavior path with historical behavior paths to predict user behaviors on the app. Further, we design a deep neural network for behavior path matching and solve three difficulties in modeling behavior paths: sparsity, noise interference, and accurate matching of behavior paths. In particular, we leverage contrastive learning to augment user behavior paths, provide behavior path self-activation to alleviate the effect of noise, and adopt a two-level matching mechanism to identify the most appropriate candidate. Our model shows excellent performance on two real-world datasets, outperforming the state-of-the-art CTR model. Moreover, our model has been deployed on the Meituan food delivery platform and has accumulated 1.6% improvement in CTR and 1.8% improvement in advertising revenue.

cs.AI↗

arXiv2023

Decision-Making Context Interaction Network for Click-Through Rate Prediction

Click-through rate (CTR) prediction is crucial in recommendation and online advertising systems. Existing methods usually model user behaviors, while ignoring the informative context which influences the user to make a click decision, e.g., click pages and pre-ranking candidates that inform inferences about user interests, leading to suboptimal performance. In this paper, we propose a Decision-Making Context Interaction Network (DCIN), which deploys a carefully designed Context Interaction Unit (CIU) to learn decision-making contexts and thus benefits CTR prediction. In addition, the relationship between different decision-making context sources is explored by the proposed Adaptive Interest Aggregation Unit (AIAU) to improve CTR prediction further. In the experiments on public and industrial datasets, DCIN significantly outperforms the state-of-the-art methods. Notably, the model has obtained the improvement of CTR+2.9%/CPM+2.1%/GMV+1.5% for online A/B testing and served the main traffic of Meituan Waimai advertising system.

cs.IR↗

arXiv2022

Overview of the Observing System and Initial Scientific Accomplishments of the East Asian VLBI Network (EAVN)

The East Asian VLBI Network (EAVN) is an international VLBI facility in East Asia and is operated under mutual collaboration between East Asian countries, as well as part of Southeast Asian and European countries. EAVN currently consists of 16 radio telescopes and three correlators located in China, Japan, and Korea, and is operated mainly at three frequency bands, 6.7, 22, and 43 GHz with the longest baseline length of 5078 km, resulting in the highest angular resolution of 0.28 milliarcseconds at 43 GHz. One of distinct capabilities of EAVN is multi-frequency simultaneous data reception at nine telescopes, which enable us to employ the frequency phase transfer technique to obtain better sensitivity at higher observing frequencies. EAVN started its open-use program in the second half of 2018, providing a total observing time of more than 1100 hours in a year. EAVN fills geographical gap in global VLBI array, resulting in enabling us to conduct contiguous high-resolution VLBI observations. EAVN has produced various scientific accomplishments especially in observations toward active galactic nuclei, evolved stars, and star-forming regions. These activities motivate us to initiate launch of the 'Global VLBI Alliance' to provide an opportunity of VLBI observation with the longest baselines on the earth.

astro-ph.IM↗

arXiv2022

A Comprehensive Evaluation Framework for Deep Model Robustness

Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples, which motivates the evaluation and benchmark of model robustness. However, current evaluations usually use simple metrics to study the performance of defenses, which are far from understanding the limitation and weaknesses of these defense methods. Thus, most proposed defenses are quickly shown to be attacked successfully, which results in the ``arm race'' phenomenon between attack and defense. To mitigate this problem, we establish a model robustness evaluation framework containing 23 comprehensive and rigorous metrics, which consider two key perspectives of adversarial learning (i.e., data and model). Through neuron coverage and data imperceptibility, we use data-oriented metrics to measure the integrity of test examples; by delving into model structure and behavior, we exploit model-oriented metrics to further evaluate robustness in the adversarial setting. To fully demonstrate the effectiveness of our framework, we conduct large-scale experiments on multiple datasets including CIFAR-10, SVHN, and ImageNet using different models and defenses with our open-source platform. Overall, our paper provides a comprehensive evaluation framework, where researchers could conduct comprehensive and fast evaluations using the open-source toolkit, and the analytical results could inspire deeper understanding and further improvement to the model robustness.

cs.CV↗

arXiv2022

Extinction by plasmonic nanoparticles in dispersive and dissipative media

Extinction of small metallic spheres has been well understood through the classical Mie theory when the host medium is dispersive and transparent. However, the role of host dissipation on the particulate extinction remains a competition between the enhancing and reducing effects on the localized surface plasmonic resonance (LSPR). Here, using a generalized Mie theory, we elaborate on the specific influence mechanisms of host dissipation on the extinction efficiency factors of a plasmonic nanosphere. To this end, we isolate the dissipative effects by comparing the dispersive and dissipative host with its transparent counterpart. As a result, we identify the damping effects of host dissipation on the LSPR including the resonance widening and amplitude reducing. The resonance positions are shifted by host dissipation, which cannot be predicted by the classical Fröhlich condition. Finally, we demonstrate that a wide-band extinction enhancement due to host dissipation can be realized away from the positions of LSPR.

physics.optics↗

arXiv2021

PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction

Human motion prediction, which aims to predict future human poses given past poses, has recently seen increased interest. Many recent approaches are based on Recurrent Neural Networks (RNN) which model human poses with exponential maps. These approaches neglect the pose velocity as well as temporal relation of different poses, and tend to converge to the mean pose or fail to generate natural-looking poses. We therefore propose a novel Position-Velocity Recurrent Encoder-Decoder (PVRED) for human motion prediction, which makes full use of pose velocities and temporal positional information. A temporal position embedding method is presented and a Position-Velocity RNN (PVRNN) is proposed. We also emphasize the benefits of quaternion parameterization of poses and design a novel trainable Quaternion Transformation (QT) layer, which is combined with a robust loss function during training. We provide quantitative results for both short-term prediction in the future 0.5 seconds and long-term prediction in the future 0.5 to 1 seconds. Experiments on several benchmarks show that our approach considerably outperforms the state-of-the-art methods. In addition, qualitative visualizations in the future 4 seconds show that our approach could predict future human-like and meaningful poses in very long time horizons. Code is publicly available on GitHub: \textcolor{red}{https://github.com/hongsong-wang/PVRNN}.

cs.CV↗

arXiv2021

Image-to-Video Generation via 3D Facial Dynamics

We present a versatile model, FaceAnime, for various video generation tasks from still images. Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information from the input face image and a sequence of sparse facial landmarks. However, the generated face images usually suffer from quality loss, image distortion, identity change, and expression mismatching due to the weak representation capacity of the facial landmarks. In this paper, we propose to "imagine" a face video from a single face image according to the reconstructed 3D face dynamics, aiming to generate a realistic and identity-preserving face video, with precisely predicted pose and facial expression. The 3D dynamics reveal changes of the facial expression and motion, and can serve as a strong prior knowledge for guiding highly realistic face video generation. In particular, we explore face video prediction and exploit a well-designed 3D dynamic prediction network to predict a 3D dynamic sequence for a single face image. The 3D dynamics are then further rendered by the sparse texture mapping algorithm to recover structural details and sparse textures for generating face frames. Our model is versatile for various AR/VR and entertainment applications, such as face video retargeting and face video prediction. Superior experimental results have well demonstrated its effectiveness in generating high-fidelity, identity-preserving, and visually pleasant face video clips from a single source face image.

cs.CV↗

arXiv2021

East Asian VLBI Network Observations of Active Galactic Nuclei Jets: Imaging with KaVA+Tianma+Nanshan

The East Asian very-long-baseline interferometry (VLBI) Network (EAVN) is a rapidly evolving international VLBI array that is currently promoted under joint efforts among China, Japan, and Korea. EAVN aims at forming a joint VLBI Network by combining a large number of radio telescopes distributed over East Asian regions. After the combination of the Korean VLBI Network (KVN) and the VLBI Exploration of Radio Astrometry (VERA) into KaVA, further expansion with the joint array in East Asia is actively promoted. Here we report the first imaging results (at 22 and 43 GHz) of bright radio sources obtained with KaVA connected to Tianma 65-m and Nanshan 26-m Radio Telescopes in China. To test the EAVN imaging performance for different sources, we observed four active galactic nuclei (AGN) having different brightness and morphology. As a result, we confirmed that Tianma 65-m Radio Telescope (TMRT) significantly enhances the overall array sensitivity, a factor of 4 improvement in baseline sensitivity and 2 in image dynamic range compared to the case of KaVA only. The addition of Nanshan 26-m Radio Telescope (NSRT) further doubled the east-west angular resolution. With the resulting high-dynamic-range, high-resolution images with EAVN (KaVA+TMRT+NSRT), various fine-scale structures in our targets, such as the counter-jet in M87, a kink-like morphology of the 3C273 jet and the weak emission in other sources, are successfully detected. This demonstrates the powerful capability of EAVN to study AGN jets and to achieve other science goals in general. Ongoing expansion of EAVN will further enhance the angular resolution, detection sensitivity and frequency coverage of the network.

astro-ph.GA↗

arXiv2020

DR 21 South Filament: a Parsec-sized Dense Gas Accretion Flow onto the DR 21 Massive Young Cluster

DR21 south filament (DR21SF) is a unique component of the giant network of filamentary molecular clouds in the north region of Cygnus X complex. Unlike the highly fragmented and star-forming active environment it resides, DR21SF exhibits a coherent profile in the column density map with very few star formation signposts, even though the previously reported linear density of the filament is an order of magnitude higher than the thermal stable threshold. We derive the size (3.6~pc by 0.13~pc), temperature (10 to 15~K), and mass (1048~\textit{M$_\odot$}) of DR21SF from Shanghai 65 m TianMa Radio Telescope (TMRT) observations of NH$_3$ (1, 1) and (2, 2) inversion lines in conjunction with the column density map from our previous work. Star-forming sites are identified along the filament where gas temperature excesses. We find clear gradients in radial velocity and intrinsic line-width along the spine of the filament. The gradients can be well interpreted with a scenario of an accretion flow feeding DR 21 at a mass transfer rate of $1.1 \times 10^{-3}$~\textit{M$_\odot$} yr$^{-1}$. Based on the analysis of its kinematic temperature, intrinsic line-width and mass distribution, we conclude that DR21SF is in an overall trans-critical status, which indicates an early evolutionary stage.

astro-ph.GA↗

arXiv2020

A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing

Modern radar systems have high requirements in terms of accuracy, robustness and real-time capability when operating on increasingly complex electromagnetic environments. Traditional radar signal processing (RSP) methods have shown some limitations when meeting such requirements, particularly in matters of target classification. With the rapid development of machine learning (ML), especially deep learning, radar researchers have started integrating these new methods when solving RSP-related problems. This paper aims at helping researchers and practitioners to better understand the application of ML techniques to RSP-related problems by providing a comprehensive, structured and reasoned literature overview of ML-based RSP techniques. This work is amply introduced by providing general elements of ML-based RSP and by stating the motivations behind them. The main applications of ML-based RSP are then analysed and structured based on the application field. This paper then concludes with a series of open questions and proposed research directions, in order to indicate current gaps and potential future solutions and trends.

eess.SP↗

arXiv2019

Very Long Natural Scenery Image Prediction by Outpainting

Comparing to image inpainting, image outpainting receives less attention due to two challenges in it. The first challenge is how to keep the spatial and content consistency between generated images and original input. The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input. To solve the two problems, we devise some innovative modules, named Skip Horizontal Connection and Recurrent Content Transfer, and integrate them into our designed encoder-decoder structure. By this design, our network can generate highly realistic outpainting prediction effectively and efficiently. Other than that, our method can generate new images with very long sizes while keeping the same style and semantic content as the given input. To test the effectiveness of the proposed architecture, we collect a new scenery dataset with diverse, complicated natural scenes. The experimental results on this dataset have demonstrated the efficacy of our proposed network. The code and dataset are available from https://github.com/z-x-yang/NS-Outpainting.

cs.CV↗

arXiv2019

A 6.7 GHz Methanol Maser Survey II. Low Galactic Latitudes

We report the results of our systematic survey for Galactic 6.7 GHz Class II CH$_3$OH maser emission toward a sample of young stellar objects. The survey was conducted with the Shanghai Tianma Radio Telescope (TMRT). The sample consists of 3348 sources selected from the all-sky \emph{Wide-Field Infrared Survey Explorer (WISE)} point source catalog. We have discussed the selection criteria in detail and the detection results of those at high Galactic latitudes (i.e. $|b|>$ 2$^\circ$) in a previous paper (paper I). Here, we present the results from the survey of those at low Galactic latitudes, i.e. $|b|<2^\circ$. Of 1875 selected \emph{WISE} point sources, 291 positions that were actually associated with 224 sources were detected with CH$_3$OH maser emission. Among them, 32 are newly detected. Majority of the newly detected sources are associated with bright WISE sources. The majority of the detected sources (209/224 = 93.3\%) are quite close to the Galactic Plane ($|b|<1^\circ$) and lie on the inner spiral arms with positive LSR velocities. Detection rate and the color-color distribution of our detection are all matched with our anticipation. Combining with detections from previous surveys, we compile a catalogue of 1085 sources with 6.7 GHz CH$_3$OH maser emission in our Galaxy.

astro-ph.GA↗

arXiv2019

A 6.7 GHz Methanol Maser Survey at High Galactic Latitudes

We performed a systematic 6.7 GHz Class \uppercase\expandafter{\romannumeral2} methanol maser survey using the Shanghai Tianma Radio Telescope toward targets selected from the all-sky \emph{Wide-Field Infrared Survey Explorer (WISE)} point catalog. In this paper, we report the results from the survey of those at high Galactic latitudes, i.e. $|b|>$ 2$^\circ$. Of 1473 selected \emph{WISE} point sources at high latitude, 17 point positions that were actually associated with 12 sources were detected with maser emission, reflecting the rarity (1$-$2\%) of methanol masers in the region away from the Galactic plane. Out of the 12 sources, 3 are detected for the first time. The spectral energy distribution (SED) at infrared bands shows that these new detected masers occur in the massive star forming regions. Compared to previous detections, the methanol maser changes significantly in both spectral profiles and flux densities. The infrared \emph{WISE} images show that almost all of these masers are located in the positions of the bright \emph{WISE} point sources. Compared with the methanol masers at the Galactic plane, these high-latitude methanol masers provide good tracers for investigating the physics and kinematics around massive young stellar objects, because they are believed to be less affected by the surrounding cluster environment.

astro-ph.GA↗

arXiv2019

Radiative heat transfer between metallic nanoparticle clusters in both near field and far field

Micro-nanoparticle systems have wide applications in thermal science and technology. In dense particulate system, the particle separation distance may be less than the characteristic thermal wavelength and near field effect will be significant and become a key factor to influence thermal radiation transfer in the system. In this study, radiative heat transfer (RHT) between two metallic nanoparticles clusters are explored using many-body radiative heat transfer theory implemented with the coupled electric and magnetic dipole (CEMD) approach, which effectively takes into account the contribution of magnetic polarization of metallic nanoparticles on heat exchange. As the focus, the effects of magnetic polarization and many-body interaction (MBI) on RHT were analyzed. The effects of fractal dimension and relative orientation of the clusters were also analyzed. Results show that the contribution of magnetically polarized eddy-current Joule dissipation dominates the RHT between Ag nanoparticle clusters. If only electric polarization (EP approach) is considered, the heat conductance will be underestimated as compared with the CEMD approach in both near field and far field regime. The effect of MBI on the RHT between Ag nanoparticle clusters is unobvious at room temperature, which is quite different from the SiC nanoparticle clusters. For the latter, MBI tends to suppress RHT significantly. The relative orientation has remarkable effect on radiative heat flux for clusters with lacy structure when the separation distance is in the near field. While for the separation distance in far field, both the relative orientation and the fractal dimension has a weak influence on radiative heat flux. This work will help the understanding of thermal transport in dense particulate system.

physics.app-ph↗

arXiv2018

Long-distance near-field energy transport via propagating surface waves

Near-field radiative heat transfer (RHT) between two bodies can significantly exceed the far-field limit set by Planck's law due to the evanescent wave tunneling, which typically can only occur when the two bodies are separated at subwavelength distances. We show that the RHT between two SiC nanoparticles with separation distances much larger than the thermal wavelength can still exceed the far-field limit when the particles are located within a subwavelength distance away from a SiC substrate. In this configuration, the localized surface phonon polariton (SPhP) of the particles couples to the propagating SPhP of the substrate which then provides a new channel for the near-field energy transport and enhances the RHT by orders of magnitude at large distances. The enhancement is also demonstrated to appear in a chain of closely spaced SiC nanoparticles located in the near field of a SiC substrate. The findings provide a new way for the long-distance transport of near-field energy.

physics.app-ph↗

arXiv2017

Widespread Presence of Glycolaldehyde and Ethylene Glycol Around Sagittarius B2

We report the detection of widespread CH$_2$OHCHO and HOCH$_2$CH$_2$OH emission in Galactic center giant molecular cloud Sagittarius B2 using the Shanghai Tianma 65m Radio Telescope. Our observations show for the first time that the spatial distribution of these two important prebiotic molecules extends over 15 arc-minutes, corresponding to a linear size of approximately 36 pc. These two molecules are not just distributed in or near the hot cores. The abundance of these two molecules seems to decrease from the cold outer region to the central region associated with star-formation activity. Results present here suggest that these two molecules are likely to form through a low temperature process. Recent theoretical and experimental studies demonstrated that prebiotic molecules can be efficiently formed in icy grain mantles through several pathways. However, these complex ice features cannot be directly observed, and most constraints on the ice compositions come from millimeter observations of desorbed ice chemistry products. These results, combined with laboratory studies, strongly support the existence of abundant prebiotic molecules in ices.

astro-ph.GA↗

arXiv2017

Radiative heat transfer in many-body systems: coupled electric and magnetic dipole approach

The many-body radiative heat transfer theory [P. Ben-Abdallah, S.-A. Biehs, and K. Joulain, Phys. Rev. Lett. 107, 114301 (2011)] only considered the contribution from the electric dipole moment. For metal particles, however, the magnetic dipole moment due to eddy current plays an important role, which can further couple with the electric dipole moment to introduce crossed terms. In this work, we develop coupled electric and magnetic dipole (CEMD) approach for the radiative heat transfer in a collection of objects in mutual interaction. Due to the coupled electric and magnetic interactions, four terms, namely the electric-electric, the electric-magnetic, the magnetic-electric and the magnetic-magnetic terms, contribute to the radiative heat flux and the local energy density. The CEMD is applied to study the radiative heat transfer between various dimers of nanoparticles. It is found that each of the four terms can dominate the radiative heat transfer depending on the position and composition of particles. Moreover, near-field many-body interactions are studied by CEMD considering both dielectric and metallic nanoparticles. The near-field radiative heat flux and local energy density can be greatly increased when the particles are in coupled resonances. Surface plasmon polariton and surface phonon polariton can be coupled to enhance the radiative heat flux.

cond-mat.other↗