Searcharxiv⌕ Search

arXiv subjects

Jia Jia

Publications and source records attributed to Jia Jia.

At least 55 records · Page 3Linked to original sources
arXiv2023

Speech-Driven 3D Face Animation with Composite and Regional Facial Movements

Speech-driven 3D face animation poses significant challenges due to the intricacy and variability inherent in human facial movements. This paper emphasizes the importance of considering both the composite and regional natures of facial movements in speech-driven 3D face animation. The composite nature pertains to how speech-independent factors globally modulate speech-driven facial movements along the temporal dimension. Meanwhile, the regional nature alludes to the notion that facial movements are not globally correlated but are actuated by local musculature along the spatial dimension. It is thus indispensable to incorporate both natures for engendering vivid animation. To address the composite nature, we introduce an adaptive modulation module that employs arbitrary facial movements to dynamically adjust speech-driven facial movements across frames on a global scale. To accommodate the regional nature, our approach ensures that each constituent of the facial features for every frame focuses on the local spatial movements of 3D faces. Moreover, we present a non-autoregressive backbone for translating audio to 3D facial movements, which maintains high-frequency nuances of facial movements and facilitates efficient inference. Comprehensive experiments and user studies demonstrate that our method surpasses contemporary state-of-the-art approaches both qualitatively and quantitatively.

cs.CV↗
arXiv2023

Mobile Supply: The Last Piece of Jigsaw of Recommender System

Recommendation system is a fundamental functionality of online platforms. With the development of computing power of mobile phones, some researchers have deployed recommendation algorithms on users' mobile devices to address the problems of data transmission delay and pagination trigger mechanism. However, the existing edge-side mobile rankings cannot completely solve the problem of pagination trigger mechanism. The mobile ranking can only sort the items on the current page, and the fixed set of candidate items limits the performance of the mobile ranking. Besides, after the user has viewed the items of interest to the user on the current page, the user refresh to get a new page of items. This will affect the user's immersive experience because the user is not satisfied with the left items on the current page. In order to address the problem of pagination trigger mechanism, we propose a completely new module in the pipeline of recommender system named Mobile Supply. The pipeline of recommender system is extended to "retrival->pre-ranking->ranking->re-ranking->Mobile Supply->mobile ranking". Specifically, we introduce the concept of list value and use point-wise paradigm to approximate list-wise estimation to calculate the maximum revenue that can be achieved by mobile ranking for the current page. We also design a new mobile ranking approach named device-aware mobile ranking considering the differences of mobile devices tailored to the new pipeline. Extensive offline and online experiments show the superiority of our proposed method and prove that Mobile Supply can further improve the performance of edge-side recommender system and user experience. Mobile Supply has been deployed on the homepage of a large-scale online food platform and has yielded considerable profits in our business.

cs.IR↗
arXiv2023

Multi-Granularity Attention Model for Group Recommendation

Group recommendation provides personalized recommendations to a group of users based on their shared interests, preferences, and characteristics. Current studies have explored different methods for integrating individual preferences and making collective decisions that benefit the group as a whole. However, most of them heavily rely on users with rich behavior and ignore latent preferences of users with relatively sparse behavior, leading to insufficient learning of individual interests. To address this challenge, we present the Multi-Granularity Attention Model (MGAM), a novel approach that utilizes multiple levels of granularity (i.e., subsets, groups, and supersets) to uncover group members' latent preferences and mitigate recommendation noise. Specially, we propose a Subset Preference Extraction module that enhances the representation of users' latent subset-level preferences by incorporating their previous interactions with items and utilizing a hierarchical mechanism. Additionally, our method introduces a Group Preference Extraction module and a Superset Preference Extraction module, which explore users' latent preferences on two levels: the group-level, which maintains users' original preferences, and the superset-level, which includes group-group exterior information. By incorporating the subset-level embedding, group-level embedding, and superset-level embedding, our proposed method effectively reduces group recommendation noise across multiple granularities and comprehensively learns individual interests. Extensive offline and online experiments have demonstrated the superiority of our method in terms of performance.

cs.IR↗
arXiv2023

Exploring the Spatiotemporal Features of Online Food Recommendation Service

Online Food Recommendation Service (OFRS) has remarkable spatiotemporal characteristics and the advantage of being able to conveniently satisfy users' needs in a timely manner. There have been a variety of studies that have begun to explore its spatiotemporal properties, but a comprehensive and in-depth analysis of the OFRS spatiotemporal features is yet to be conducted. Therefore, this paper studies the OFRS based on three questions: how spatiotemporal features play a role; why self-attention cannot be used to model the spatiotemporal sequences of OFRS; and how to combine spatiotemporal features to improve the efficiency of OFRS. Firstly, through experimental analysis, we systemically extracted the spatiotemporal features of OFRS, identified the most valuable features and designed an effective combination method. Secondly, we conducted a detailed analysis of the spatiotemporal sequences, which revealed the shortcomings of self-attention in OFRS, and proposed a more optimized spatiotemporal sequence method for replacing self-attention. In addition, we also designed a Dynamic Context Adaptation Model to further improve the efficiency and performance of OFRS. Through the offline experiments on two large datasets and online experiments for a week, the feasibility and superiority of our model were proven.

cs.IR↗
arXiv2023

SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation

Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate generative distributions. This work presents a new score-decomposed diffusion model (SDDM) on manifolds to explicitly optimize the tangled distributions during image generation. SDDM derives manifolds to make the distributions of adjacent time steps separable and decompose the score function or energy guidance into an image ``denoising" part and a content ``refinement" part. To refine the image in the same noise level, we equalize the refinement parts of the score function and energy guidance, which permits multi-objective optimization on the manifold. We also leverage the block adaptive instance normalization module to construct manifolds with lower dimensions but still concentrated with the perturbed reference image. SDDM outperforms existing SBDM-based methods with much fewer diffusion steps on several I2I benchmarks.

cs.CV↗
arXiv2023

ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint

Large-scale online recommender system spreads all over the Internet being in charge of two basic tasks: Click-Through Rate (CTR) and Post-Click Conversion Rate (CVR) estimations. However, traditional CVR estimators suffer from well-known Sample Selection Bias and Data Sparsity issues. Entire space models were proposed to address the two issues via tracing the decision-making path of "exposure_click_purchase". Further, some researchers observed that there are purchase-related behaviors between click and purchase, which can better draw the user's decision-making intention and improve the recommendation performance. Thus, the decision-making path has been extended to "exposure_click_in-shop action_purchase" and can be modeled with conditional probability approach. Nevertheless, we observe that the chain rule of conditional probability does not always hold. We report Probability Space Confusion (PSC) issue and give a derivation of difference between ground-truth and estimation mathematically. We propose a novel Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint (ESMC) and two alternatives: Entire Space Multi-Task Model with Siamese Network (ESMS) and Entire Space Multi-Task Model in Global Domain (ESMG) to address the PSC issue. Specifically, we handle "exposure_click_in-shop action" and "in-shop action_purchase" separately in the light of characteristics of in-shop action. The first path is still treated with conditional probability while the second one is treated with parameter constraint strategy. Experiments on both offline and online environments in a large-scale recommendation system illustrate the superiority of our proposed methods over state-of-the-art models. The real-world datasets will be released.

cs.AI↗
arXiv2023

Shuffled Autoregression For Motion Interpolation

This work aims to provide a deep-learning solution for the motion interpolation task. Previous studies solve it with geometric weight functions. Some other works propose neural networks for different problem settings with consecutive pose sequences as input. However, motion interpolation is a more complex problem that takes isolated poses (e.g., only one start pose and one end pose) as input. When applied to motion interpolation, these deep learning methods have limited performance since they do not leverage the flexible dependencies between interpolation frames as the original geometric formulas do. To realize this interpolation characteristic, we propose a novel framework, referred to as \emph{Shuffled AutoRegression}, which expands the autoregression to generate in arbitrary (shuffled) order and models any inter-frame dependencies as a directed acyclic graph. We further propose an approach to constructing a particular kind of dependency graph, with three stages assembled into an end-to-end spatial-temporal motion Transformer. Experimental results on one of the current largest datasets show that our model generates vivid and coherent motions from only one start frame to one end frame and outperforms competing methods by a large margin. The proposed model is also extensible to multiple keyframes' motion interpolation tasks and other areas' interpolation.

cs.CV↗
arXiv2023

Smooth projective surfaces with pseudo-effective tangent bundles

Let $S$ be a non-uniruled (i.e., non-birationally ruled) smooth projective surface. We show that the tangent bundle $T_S$ is pseudo-effective if and only if the canonical divisor $K_S$ is nef and the second Chern class vanishes, i.e., $c_2(S)=0$. Moreover, we study the blow-up of a non-rational ruled surface with pseudo-effective tangent bundle.

math.AG↗
arXiv2023

Surjective endomorphisms of projective surfaces: the existence of infinitely many dense orbits

Let $f \colon X \to X$ be a surjective endomorphism of a normal projective surface. When $\operatorname{deg} f \geq 2$, applying an (iteration of) $f$-equivariant minimal model program (EMMP), we determine the geometric structure of $X$. Using this, we extend the second author's result to singular surfaces to the extent that either $X$ has an $f$-invariant non-constant rational function, or $f$ has infinitely many Zariski-dense forward orbits; this result is also extended to Adelic topology (which is finer than Zariski topology).

math.AG↗
arXiv2022

BASM: A Bottom-up Adaptive Spatiotemporal Model for Online Food Ordering Service

Online Food Ordering Service (OFOS) is a popular location-based service that helps people to order what you want. Compared with traditional e-commerce recommendation systems, users' interests may be diverse under different spatiotemporal contexts, leading to various spatiotemporal data distribution, which limits the fitting capacity of the model. However, numerous current works simply mix all samples to train a set of model parameters, which makes it difficult to capture the diversity in different spatiotemporal contexts. Therefore, we address this challenge by proposing a Bottom-up Adaptive Spatiotemporal Model(BASM) to adaptively fit the spatiotemporal data distribution, which further improve the fitting capability of the model. Specifically, a spatiotemporal-aware embedding layer performs weight adaptation on field granularity in feature embedding, to achieve the purpose of dynamically perceiving spatiotemporal contexts. Meanwhile, we propose a spatiotemporal semantic transformation layer to explicitly convert the concatenated input of the raw semantic to spatiotemporal semantic, which can further enhance the semantic representation under different spatiotemporal contexts. Furthermore, we introduce a novel spatiotemporal adaptive bias tower to capture diverse spatiotemporal bias, reducing the difficulty to model spatiotemporal distinction. To further verify the effectiveness of BASM, we also novelly propose two new metrics, Time-period-wise AUC (TAUC) and City-wise AUC (CAUC). Extensive offline evaluations on public and industrial datasets are conducted to demonstrate the effectiveness of our proposed modle. The online A/B experiment also further illustrates the practicability of the model online service. This proposed method has now been implemented on the Ele.me, a major online food ordering platform in China, serving more than 100 million online users.

cs.LG↗
arXiv2022

Spatiotemporal-Enhanced Network for Click-Through Rate Prediction in Location-based Services

In Location-Based Services(LBS), user behavior naturally has a strong dependence on the spatiotemporal information, i.e., in different geographical locations and at different times, user click behavior will change significantly. Appropriate spatiotemporal enhancement modeling of user click behavior and large-scale sparse attributes is key to building an LBS model. Although most of existing methods have been proved to be effective, they are difficult to apply to takeaway scenarios due to insufficient modeling of spatiotemporal information. In this paper, we address this challenge by seeking to explicitly model the timing and locations of interactions and proposing a Spatiotemporal-Enhanced Network, namely StEN. In particular, StEN applies a Spatiotemporal Profile Activation module to capture common spatiotemporal preference through attribute features. A Spatiotemporal Preference Activation is further applied to model the personalized spatiotemporal preference embodied by behaviors in detail. Moreover, a Spatiotemporal-aware Target Attention mechanism is adopted to generate different parameters for target attention at different locations and times, thereby improving the personalized spatiotemporal awareness of the model.Comprehensive experiments are conducted on three large-scale industrial datasets, and the results demonstrate the state-of-the-art performance of our methods. In addition, we have also released an industrial dataset for takeaway industry to make up for the lack of public datasets in this community.

cs.IR↗
arXiv2022

Amplified endomorphisms of Fano fourfolds

Let $X$ be a smooth Fano fourfold admitting a conic bundle structure. We show that $X$ is toric if and only if $X$ admits an amplified endomorphism; in this case, $X$ is a rational variety.

math.AG↗
arXiv2022

Moishezon manifolds with no nef and big classes

We show that a compact complex manifold $X$ has no non-trivial nef $(1,1)$-classes if there is a non-isomorphic bimeromorphic map $f\colon X\dashrightarrow Y$ isomorphic in codimension $1$ to a compact Kähler manifold $Y$ with $h^{1,1}=1$. In particular, there exist infinitely many isomorphic classes of smooth compact Moishezon threefolds with no nef and big $(1,1)$-classes. This contradicts a recent paper (Strongly Jordan property and free actions of non-abelian free groups, Proc. Edinb. Math. Soc., (2022): 1--11).

math.AG↗
arXiv2022

Towards Cross-speaker Reading Style Transfer on Audiobook Dataset

Cross-speaker style transfer aims to extract the speech style of the given reference speech, which can be reproduced in the timbre of arbitrary target speakers. Existing methods on this topic have explored utilizing utterance-level style labels to perform style transfer via either global or local scale style representations. However, audiobook datasets are typically characterized by both the local prosody and global genre, and are rarely accompanied by utterance-level style labels. Thus, properly transferring the reading style across different speakers remains a challenging task. This paper aims to introduce a chunk-wise multi-scale cross-speaker style model to capture both the global genre and the local prosody in audiobook speeches. Moreover, by disentangling speaker timbre and style with the proposed switchable adversarial classifiers, the extracted reading style is made adaptable to the timbre of different speakers. Experiment results confirm that the model manages to transfer a given reading style to new target speakers. With the support of local prosody and global genre type predictor, the potentiality of the proposed method in multi-speaker audiobook generation is further revealed.

cs.SD↗
arXiv2022

Equivariant Kähler model for Fujiki's class

Let $X$ be a compact complex manifold in Fujiki's class $\mathcal{C}$, i.e., admitting a big $(1,1)$-class $[α]$. Consider $\text{Aut}(X)$ the group of biholomorphic automorphisms and $\text{Aut}_{[α]}(X)$ the subgroup of automorphisms preserving the class $[α]$ via pullback. We show that $X$ admits an $\text{Aut}_{[α]}(X)$-equivariant Kähler model: there is a bimeromorphic holomorphic map $σ\colon \widetilde{X}\to X$ from a Kähler manifold $\widetilde{X}$ such that $\text{Aut}_{[α]}(X)$ lifts holomorphically via $σ$. There are several applications. We show that $\text{Aut}_{[α]}(X)$ is a Lie group with only finitely many components. This generalizes an early result of Lieberman and Fujiki on the Kähler case. We also show that every torsion subgroup of $\text{Aut}(X)$ is almost abelian, and $\text{Aut}(X)$ is finite if it is a torsion group.

math.AG↗
arXiv2021

Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis

People talk with diversified styles. For one piece of speech, different talking styles exhibit significant differences in the facial and head pose movements. For example, the "excited" style usually talks with the mouth wide open, while the "solemn" style is more standardized and seldomly exhibits exaggerated motions. Due to such huge differences between different styles, it is necessary to incorporate the talking style into audio-driven talking face synthesis framework. In this paper, we propose to inject style into the talking face synthesis framework through imitating arbitrary talking style of the particular reference video. Specifically, we systematically investigate talking styles with our collected \textit{Ted-HD} dataset and construct style codes as several statistics of 3D morphable model~(3DMM) parameters. Afterwards, we devise a latent-style-fusion~(LSF) model to synthesize stylized talking faces by imitating talking styles from the style codes. We emphasize the following novel characteristics of our framework: (1) It doesn't require any annotation of the style, the talking style is learned in an unsupervised manner from talking videos in the wild. (2) It can imitate arbitrary styles from arbitrary videos, and the style codes can also be interpolated to generate new styles. Extensive experiments demonstrate that the proposed framework has the ability to synthesize more natural and expressive talking styles compared with baseline methods.

cs.CV↗
arXiv2021

Tumera: Tutor of Photography Beginners

With the popularity of photographic equipment, more and more people are starting to learn photography by themselves. Although they have easy access to photographic materials, it is uneasy to obtain professional feedback or guidance that can help them improve their photography skills. Therefore, we develop an intelligently interactive system, Tumera, that provides aesthetics guidance for photography beginners. When shooting, Tumera gives timely feedback on the pictures in the view port. After shooting, scores evaluating the aesthetic quality of different aspects of the photos and corresponding improvement suggestions are given. Tumera allows users to share, rank, discuss, and learn from their works and interaction with the system based on the scores and suggestions. In the experiment, Tumera showed good accuracy, real-time computing ability, and effective guiding performance.

cs.HC↗