Feida Zhu

Yuhang Liu, Wei Wei, Daowan Peng et al. · microsoft-research

In recent years, the pre-training-then-fine-tuning paradigm has yielded immense success on a wide spectrum of cross-modal tasks, such as visual question answering (VQA), in which a visual-language (VL) model is first optimized via self-supervised task objectives, e.g., masked language modeling (MLM) and image-text matching (ITM), and then fine-tuned to adapt to downstream task (e.g., VQA) via a brand-new objective function, e.g., answer prediction. The inconsistency of the objective forms not only severely limits the generalization of pre-trained VL models to downstream tasks, but also requires a large amount of labeled data for fine-tuning. To alleviate the problem, we propose an innovative VL fine-tuning paradigm (named Declaration-based Prompt Tuning, abbreviated as DPT), which jointly optimizes the objectives of pre-training and fine-tuning of VQA model, boosting the effective adaptation of pre-trained VL models to the downstream task. Specifically, DPT reformulates the objective form of VQA task via (1) textual adaptation, which converts the given questions into declarative sentence-form for prompt-tuning, and (2) task adaptation, which optimizes the objective function of VQA problem in the manner of pre-training phase. Experimental results on GQA dataset show that DPT outperforms the fine-tuned counterpart by a large margin regarding accuracy in both fully-supervised (2.68%) and zero-shot/few-shot (over 31%) settings. All the data and codes will be available to facilitate future research.

Weiran Pan, Wei Wei, Feida Zhu

Fine-grained entity typing (FET) aims to assign proper semantic types to entity mentions according to their context, which is a fundamental task in various entity-leveraging applications. Current FET systems usually establish on large-scale weakly-supervised/distantly annotation data, which may contain abundant noise and thus severely hinder the performance of the FET task. Although previous studies have made great success in automatically identifying the noisy labels in FET, they usually rely on some auxiliary resources which may be unavailable in real-world applications (e.g. pre-defined hierarchical type structures, human-annotated subsets). In this paper, we propose a novel approach to automatically correct noisy labels for FET without external resources. Specifically, it first identifies the potentially noisy labels by estimating the posterior probability of a label being positive or negative according to the logits output by the model, and then relabel candidate noisy labels by training a robust model over the remaining clean labels. Experiments on two popular benchmarks prove the effectiveness of our method. Our source code can be obtained from https://github.com/CCIIPLab/DenoiseFET.

Huichao Zhang, Bowen Chen, Hao Yang et al.

Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and texturing in 3D that ensure details and various styles (realistic, fictional, etc). We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance. In specific, we introduce a 2D diffusion model conditioned on DensePose signal to establish 3D pose control of avatars through 2D images, which enhances view consistency from partially observed scenarios. It addresses the infamous Janus Problem and significantly stablizes the generation process. Moreover, we propose a progressive high-resolution 3D synthesis strategy, which obtains substantial improvement over the quality of the created 3D avatars. To this end, the proposed AvatarVerse pipeline achieves zero-shot 3D modeling of 3D avatars that are not only more expressive, but also in higher quality and fidelity than previous works. Rigorous qualitative evaluations and user studies showcase AvatarVerse's superiority in synthesizing high-fidelity 3D avatars, leading to a new standard in high-quality and stable 3D avatar creation. Our project page is: https://avatarverse3d.github.io

Zhenyu Xie, Zaiyu Huang, Xin Dong et al.

Image-based Virtual Try-ON aims to transfer an in-shop garment onto a specific person. Existing methods employ a global warping module to model the anisotropic deformation for different garment parts, which fails to preserve the semantic information of different parts when receiving challenging inputs (e.g, intricate human poses, difficult garments). Moreover, most of them directly warp the input garment to align with the boundary of the preserved region, which usually requires texture squeezing to meet the boundary shape constraint and thus leads to texture distortion. The above inferior performance hinders existing methods from real-world applications. To address these problems and take a step towards real-world virtual try-on, we propose a General-Purpose Virtual Try-ON framework, named GP-VTON, by developing an innovative Local-Flow Global-Parsing (LFGP) warping module and a Dynamic Gradient Truncation (DGT) training strategy. Specifically, compared with the previous global warping mechanism, LFGP employs local flows to warp garments parts individually, and assembles the local warped results via the global garment parsing, resulting in reasonable warped parts and a semantic-correct intact garment even with challenging inputs.On the other hand, our DGT training strategy dynamically truncates the gradient in the overlap area and the warped garment is no more required to meet the boundary constraint, which effectively avoids the texture squeezing problem. Furthermore, our GP-VTON can be easily extended to multi-category scenario and jointly trained by using data from different garment categories. Extensive experiments on two high-resolution benchmarks demonstrate our superiority over the existing state-of-the-art methods.

Ling Cheng, Feida Zhu, Yong Wang et al.

With the ever-increasing boom of Cryptocurrency, detecting fraudulent behaviors and associated malicious addresses draws significant research effort. However, most existing studies still rely on the full history features or full-fledged address transaction networks, thus cannot meet the requirements of early malicious address detection, which is urgent but seldom discussed by existing studies. To detect fraud behaviors of malicious addresses in the early stage, we present Evolve Path Tracer, which consists of Evolve Path Encoder LSTM, Evolve Path Graph GCN, and Hierarchical Survival Predictor. Specifically, in addition to the general address features, we propose asset transfer paths and corresponding path graphs to characterize early transaction patterns. Further, since the transaction patterns are changing rapidly during the early stage, we propose Evolve Path Encoder LSTM and Evolve Path Graph GCN to encode asset transfer path and path graph under an evolving structure setting. Hierarchical Survival Predictor then predicts addresses' labels with nice scalability and faster prediction speed. We investigate the effectiveness and versatility of Evolve Path Tracer on three real-world illicit bitcoin datasets. Our experimental results demonstrate that Evolve Path Tracer outperforms the state-of-the-art methods. Extensive scalability experiments demonstrate the model's adaptivity under a dynamic prediction setting.

Congyi Wang, Feida Zhu, Shilei Wen

Existing methods proposed for hand reconstruction tasks usually parameterize a generic 3D hand model or predict hand mesh positions directly. The parametric representations consisting of hand shapes and rotational poses are more stable, while the non-parametric methods can predict more accurate mesh positions. In this paper, we propose to reconstruct meshes and estimate MANO parameters of two hands from a single RGB image simultaneously to utilize the merits of two kinds of hand representations. To fulfill this target, we propose novel Mesh-Mano interaction blocks (MMIBs), which take mesh vertices positions and MANO parameters as two kinds of query tokens. MMIB consists of one graph residual block to aggregate local information and two transformer encoders to model long-range dependencies. The transformer encoders are equipped with different asymmetric attention masks to model the intra-hand and inter-hand attention, respectively. Moreover, we introduce the mesh alignment refinement module to further enhance the mesh-image alignment. Extensive experiments on the InterHand2.6M benchmark demonstrate promising results over the state-of-the-art hand reconstruction methods.

Zhenyu Xie, Zaiyu Huang, Fuwei Zhao et al.

Image-based virtual try-on is one of the most promising applications of human-centric image generation due to its tremendous real-world potential. In this work, we take a step forwards to explore versatile virtual try-on solutions, which we argue should possess three main properties, namely, they should support unsupervised training, arbitrary garment categories, and controllable garment editing. To this end, we propose a characteristic-preserving end-to-end network, the PAtch-routed SpaTially-Adaptive GAN++ (PASTA-GAN++), to achieve a versatile system for high-resolution unpaired virtual try-on. Specifically, our PASTA-GAN++ consists of an innovative patch-routed disentanglement module to decouple the intact garment into normalized patches, which is capable of retaining garment style information while eliminating the garment spatial information, thus alleviating the overfitting issue during unsupervised training. Furthermore, PASTA-GAN++ introduces a patch-based garment representation and a patch-guided parsing synthesis block, allowing it to handle arbitrary garment categories and support local garment editing. Finally, to obtain try-on results with realistic texture details, PASTA-GAN++ incorporates a novel spatially-adaptive residual module to inject the coarse warped garment feature into the generator. Extensive experiments on our newly collected UnPaired virtual Try-on (UPT) dataset demonstrate the superiority of PASTA-GAN++ over existing SOTAs and its ability for controllable garment editing.

Ling Cheng, Feida Zhu, Yong Wang et al.

Cryptocurrency has been subject to illicit activities probably more often than traditional financial assets due to the pseudo-anonymous nature of its transacting entities. An ideal detection model is expected to achieve all three critical properties of (I) early detection, (II) good interpretability, and (III) versatility for various illicit activities. However, existing solutions cannot meet all these requirements, as most of them heavily rely on deep learning without interpretability and are only available for retrospective analysis of a specific illicit type. To tackle all these challenges, we propose Intention-Monitor for early malice detection in Bitcoin (BTC), where the on-chain record data for a certain address are much scarcer than other cryptocurrency platforms. We first define asset transfer paths with the Decision-Tree based feature Selection and Complement (DT-SC) to build different feature sets for different malice types. Then, the Status/Action Proposal Module (S/A-PM) and the Intention-VAE module generate the status, action, intent-snippet, and hidden intent-snippet embedding. With all these modules, our model is highly interpretable and can detect various illegal activities. Moreover, well-designed loss functions further enhance the prediction speed and model's interpretability. Extensive experiments on three real-world datasets demonstrate that our proposed algorithm outperforms the state-of-the-art methods. Furthermore, additional case studies justify our model can not only explain existing illicit patterns but can also find new suspicious characters.

Xin Mu, Ming Pang, Feida Zhu

Auditing Data Provenance (ADP), i.e., auditing if a certain piece of data has been used to train a machine learning model, is an important problem in data provenance. The feasibility of the task has been demonstrated by existing auditing techniques, e.g., shadow auditing methods, under certain conditions such as the availability of label information and the knowledge of training protocols for the target model. Unfortunately, both of these conditions are often unavailable in real applications. In this paper, we introduce Data Provenance via Differential Auditing (DPDA), a practical framework for auditing data provenance with a different approach based on statistically significant differentials, i.e., after carefully designed transformation, perturbed input data from the target model's training set would result in much more drastic changes in the output than those from the model's non-training set. This framework allows auditors to distinguish training data from non-training ones without the need of training any shadow models with the help of labeled output data. Furthermore, we propose two effective auditing function implementations, an additive one and a multiplicative one. We report evaluations on real-world data sets demonstrating the effectiveness of our proposed auditing technique.

Zuyan Liu, Gaojie Lin, Congyi Wang et al.

With an enormous number of hand images generated over time, unleashing pose knowledge from unlabeled images for supervised hand mesh estimation is an emerging yet challenging topic. To alleviate this issue, semi-supervised and self-supervised approaches have been proposed, but they are limited by the reliance on detection models or conventional ResNet backbones. In this paper, inspired by the rapid progress of Masked Image Modeling (MIM) in visual classification tasks, we propose a novel self-supervised pre-training strategy for regressing 3D hand mesh parameters. Our approach involves a unified and multi-granularity strategy that includes a pseudo keypoint alignment module in the teacher-student framework for learning pose-aware semantic class tokens. For patch tokens with detailed locality, we adopt a self-distillation manner between teacher and student network based on MIM pre-training. To better fit low-level regression tasks, we incorporate pixel reconstruction tasks for multi-level representation learning. Additionally, we design a strong pose estimation baseline using a simple vanilla vision Transformer (ViT) as the backbone and attach a PyMAF head after tokens for regression. Extensive experiments demonstrate that our proposed approach, named HandMIM, achieves strong performance on various hand mesh estimation tasks. Notably, HandMIM outperforms specially optimized architectures, achieving 6.29mm and 8.00mm PAVPE (Vertex-Point-Error) on challenging FreiHAND and HO3Dv2 test sets, respectively, establishing new state-of-the-art records on 3D hand mesh estimation.

Bingxue Zhang, Yang Gao, Feida Zhu et al.

Generative AI deployment poses unprecedented challenges to content safety and privacy. However, existing defense mechanisms are often tailored to specific architectures (e.g., Diffusion Models or GANs), creating fragile "defense silos" that fail against heterogeneous generative threats. This paper identifies a fundamental optimization barrier in naive pixel-space ensemble strategies: due to divergent objective functions, pixel-level gradients from heterogeneous generators become statistically orthogonal, causing destructive interference. To overcome this, we observe that despite disparate low-level mechanisms, high-level feature representations of generated content exhibit alignment across architectures. Based on this, we propose the Architecture-Agnostic Targeted Feature Synergy (ATFS) framework. By introducing a target guidance image, ATFS reformulates multi-model defense as a unified feature space alignment task, enabling intrinsic gradient alignment without complex rectification. Extensive experiments show ATFS achieves SOTA protection in heterogeneous scenarios (e.g., Diffusion+GAN). It converges rapidly, reaching over 90% performance within 40 iterations, and maintains strong attack potency even under tight perturbation budgets. The framework seamlessly extends to unseen architectures (e.g., VQ-VAE) by switching the feature extractor, and demonstrates robust resistance to JPEG compression and scaling. Being computationally efficient and lightweight, ATFS offers a viable pathway to dismantle defense silos and enable universal generative security. Code and models are open-sourced for reproducibility.

Ling Cheng, Feida Zhu, Yong Wang et al.

Bitcoin has been subject to illicit activities more often than probably any other financial assets, due to the pseudo-anonymous nature of its transacting entities. An ideal detection model is expected to achieve all the three properties of (I) early detection, (II) good interpretability, and (III) versatility for various illicit activities. However, existing solutions cannot meet all these requirements, as most of them heavily rely on deep learning without satisfying interpretability and are only available for retrospective analysis of a specific illicit type. First, we present asset transfer paths, which aim to describe addresses' early characteristics. Next, with a decision tree based strategy for feature selection and segmentation, we split the entire observation period into different segments and encode each as a segment vector. After clustering all these segment vectors, we get the global status vectors, essentially the basic unit to describe the whole intention. Finally, a hierarchical self-attention predictor predicts the label for the given address in real time. A survival module tells the predictor when to stop and proposes the status sequence, namely intention. % With the type-dependent selection strategy and global status vectors, our model can be applied to detect various illicit activities with strong interpretability. The well-designed predictor and particular loss functions strengthen the model's prediction speed and interpretability one step further. Extensive experiments on three real-world datasets show that our proposed algorithm outperforms state-of-the-art methods. Besides, additional case studies justify our model can not only explain existing illicit patterns but can also find new suspicious characters.

Dong Guo, Faming Wu, Feida Zhu et al. · pku

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)

Feida Zhu, Zhetong Liang, Xixi Jia et al.

Edge-preserving image smoothing is an important step for many low-level vision problems. Though many algorithms have been proposed, there are several difficulties hindering its further development. First, most existing algorithms cannot perform well on a wide range of image contents using a single parameter setting. Second, the performance evaluation of edge-preserving image smoothing remains subjective, and there lacks a widely accepted datasets to objectively compare the different algorithms. To address these issues and further advance the state of the art, in this work we propose a benchmark for edge-preserving image smoothing. This benchmark includes an image dataset with groundtruth image smoothing results as well as baseline algorithms that can generate competitive edge-preserving smoothing results for a wide range of image contents. The established dataset contains 500 training and testing images with a number of representative visual object categories, while the baseline methods in our benchmark are built upon representative deep convolutional network architectures, on top of which we design novel loss functions well suited for edge-preserving image smoothing. The trained deep networks run faster than most state-of-the-art smoothing algorithms with leading smoothing results both qualitatively and quantitatively. The benchmark is publicly accessible via https://github.com/zhufeida/Benchmark_EPS.

xujie zhang, Xiu Li, Michael Kampffmeyer et al.

Image-based Virtual Try-On (VITON) aims to transfer an in-shop garment image onto a target person. While existing methods focus on warping the garment to fit the body pose, they often overlook the synthesis quality around the garment-skin boundary and realistic effects like wrinkles and shadows on the warped garments. These limitations greatly reduce the realism of the generated results and hinder the practical application of VITON techniques. Leveraging the notable success of diffusion-based models in cross-modal image synthesis, some recent diffusion-based methods have ventured to tackle this issue. However, they tend to either consume a significant amount of training resources or struggle to achieve realistic try-on effects and retain garment details. For efficient and high-fidelity VITON, we propose WarpDiffusion, which bridges the warping-based and diffusion-based paradigms via a novel informative and local garment feature attention mechanism. Specifically, WarpDiffusion incorporates local texture attention to reduce resource consumption and uses a novel auto-mask module that effectively retains only the critical areas of the warped garment while disregarding unrealistic or erroneous portions. Notably, WarpDiffusion can be integrated as a plug-and-play component into existing VITON methodologies, elevating their synthesis quality. Extensive experiments on high-resolution VITON benchmarks and an in-the-wild test set demonstrate the superiority of WarpDiffusion, surpassing state-of-the-art methods both qualitatively and quantitatively.

Weiran Pan, Wei Wei, Feida Zhu et al.

We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently difficult for the model to learn and can exhibit high loss similar to mislabeled samples in the early stages of training. Consequently, setting a threshold on per-sample loss to select correct labels results in a trade-off between precision and recall in sample selection: a lower threshold may miss many correctly labeled hard-to-learn samples (low recall), while a higher threshold may include many mislabeled samples (low precision). To address this issue, our goal is to accurately distinguish correctly labeled yet hard-to-learn samples from mislabeled ones, thus alleviating the trade-off dilemma. We achieve this by considering the trends in model prediction confidence rather than relying solely on loss values. Empirical observations show that only for correctly labeled samples, the model's prediction confidence for the annotated labels typically increases faster than for any other classes. Based on this insight, we propose tracking the confidence gaps between the annotated labels and other classes during training and evaluating their trends using the Mann-Kendall Test. A sample is considered potentially correctly labeled if all its confidence gaps tend to increase. Our method functions as a plug-and-play component that can be seamlessly integrated into existing sample selection techniques. Experiments on several standard benchmarks and real-world datasets demonstrate that our method enhances the performance of existing methods for learning with noisy labels.

Ling Cheng, Jiashu Pu, Ruicheng Liang et al.

Semi-supervised community detection methods are widely used for identifying specific communities due to the label scarcity. Existing semi-supervised community detection methods typically involve two learning stages learning in both initial identification and subsequent adjustment, which often starts from an unreasonable community core candidate. Moreover, these methods encounter scalability issues because they depend on reinforcement learning and generative adversarial networks, leading to higher computational costs and restricting the selection of candidates. To address these limitations, we draw a parallel between crystallization kinetics and community detection to integrate the spontaneity of the annealing process into community detection. Specifically, we liken community detection to identifying a crystal subgrain (core) that expands into a complete grain (community) through a process similar to annealing. Based on this finding, we propose CLique ANNealing (CLANN), which applies kinetics concepts to community detection by integrating these principles into the optimization process to strengthen the consistency of the community core. Subsequently, a learning-free Transitive Annealer was employed to refine the first-stage candidates by merging neighboring cliques and repositioning the community core, enabling a spontaneous growth process that enhances scalability. Extensive experiments on \textbf{43} different network settings demonstrate that CLANN outperforms state-of-the-art methods across multiple real-world datasets, showcasing its exceptional efficacy and efficiency in community detection.

Jianzhe Zhao, Feida Zhu, Lingyan He et al.

With the development of the digital economy, data is increasingly recognized as an essential resource for both work and life. However, due to privacy concerns, data owners tend to maximize the value of data through the circulation of information rather than direct data transfer. Federated learning (FL) provides an effective approach to collaborative training models while preserving privacy. However, as model parameters and training data grow, there are not only real differences in data resources between different data owners, but also mismatches between data and computing resources. These challenges lead to inadequate collaboration among data owners, compute centers, and model owners, reducing the global utility of the three parties and the effectiveness of data assetization. In this work, we first propose a framework for resource-decoupled FL involving three parties. Then, we design a Tripartite Stackelberg Model and theoretically analyze the Stackelberg-Nash equilibrium (SNE) for participants to optimize global utility. Next, we propose the Quality-aware Dynamic Resources-decoupled FL algorithm (QD-RDFL), in which we derive and solve the optimal strategies of all parties to achieve SNE using backward induction. We also design a dynamic optimization mechanism to improve the optimal strategy profile by evaluating the contribution of data quality from data owners to the global model during real training. Finally, our extensive experiments demonstrate that our method effectively encourages the linkage of the three parties involved, maximizing the global utility and value of data assets.

Huiwen Liu, Feida Zhu, Ling Cheng

Existing research on federated learning has been focused on the setting where learning is coordinated by a centralized entity. Yet the greatest potential of future collaborative intelligence would be unleashed in a more open and democratized setting with no central entity in a dominant role, referred to as "decentralized federated learning". New challenges arise accordingly in achieving both correct model training and fair reward allocation with collective effort among all participating nodes, especially with the threat of the Byzantine node jeopardising both tasks. In this paper, we propose a blockchain-based decentralized Byzantine fault-tolerant federated learning framework based on a novel Proof-of-Data (PoD) consensus protocol to resolve both the "trust" and "incentive" components. By decoupling model training and contribution accounting, PoD is able to enjoy not only the benefit of learning efficiency and system liveliness from asynchronous societal-scale PoW-style learning but also the finality of consensus and reward allocation from epoch-based BFT-style voting. To mitigate false reward claims by data forgery from Byzantine attacks, a privacy-aware data verification and contribution-based reward allocation mechanism is designed to complete the framework. Our evaluation results show that PoD demonstrates performance in model training close to that of the centralized counterpart while achieving trust in consensus and fairness for reward allocation with a fault tolerance ratio of 1/3.

Sein Minn, Jill-Jenn Vie, Koh Takeuchi et al.

Intelligent Tutoring Systems have become critically important in future learning environments. Knowledge Tracing (KT) is a crucial part of that system. It is about inferring the skill mastery of students and predicting their performance to adjust the curriculum accordingly. Deep Learning-based KT models have shown significant predictive performance compared with traditional models. However, it is difficult to extract psychologically meaningful explanations from the tens of thousands of parameters in neural networks, that would relate to cognitive theory. There are several ways to achieve high accuracy in student performance prediction but diagnostic and prognostic reasoning is more critical in learning sciences. Since KT problem has few observable features (problem ID and student's correctness at each practice), we extract meaningful latent features from students' response data by using machine learning and data mining techniques. In this work, we present Interpretable Knowledge Tracing (IKT), a simple model that relies on three meaningful latent features: individual skill mastery, ability profile (learning transfer across skills), and problem difficulty. IKT's prediction of future student performance is made using a Tree-Augmented Naive Bayes Classifier (TAN), therefore its predictions are easier to explain than deep learning-based student models. IKT also shows better student performance prediction than deep learning-based student models without requiring a huge amount of parameters. We conduct ablation studies on each feature to examine their contribution to student performance prediction. Thus, IKT has great potential for providing adaptive and personalized instructions with causal reasoning in real-world educational systems.

Ling Cheng, Wei Wei, Feida Zhu et al.

Recent advancements of image captioning have featured Visual-Semantic Fusion or Geometry-Aid attention refinement. However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement. On the other side, models based on Geometry-Aid attention still suffer from the modality gap between visual and semantic information. In this paper, we introduce a novel Geometry-Entangled Visual Semantic Transformer (GEVST) network to realize the complementary advantages of Visual-Semantic Fusion and Geometry-Aid attention refinement. Concretely, a Dense-Cap model proposes some dense captions with corresponding geometry information at first. Then, to empower GEVST with the ability to bridge the modality gap among visual and semantic information, we build four parallel transformer encoders VV(Pure Visual), VS(Semantic fused to Visual), SV(Visual fused to Semantic), SS(Pure Semantic) for final caption generation. Both visual and semantic geometry features are used in the Fusion module and also the Self-Attention module for better attention measurement. To validate our model, we conduct extensive experiments on the MS-COCO dataset, the experimental results show that our GEVST model can obtain promising performance gains.

Zezhi Shao, Yongjun Xu, Wei Wei et al.

Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph. However, on the one hand, most of existing heterogeneous graph embedding methods either insufficiently model the local structure under specific semantic, or neglect the heterogeneity when aggregating information from it. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain versatile node embeddings. To address the problem, we propose a Heterogeneous Graph Neural Network with Multi-View Representation Learning (named MV-HetGNN) for heterogeneous graph embedding by introducing the idea of multi-view representation learning. The proposed model consists of node feature transformation, view-specific ego graph encoding and auto multi-view fusion to thoroughly learn complex structural and semantic information for generating comprehensive node representations. Extensive experiments on three real-world heterogeneous graph datasets show that the proposed MV-HetGNN model consistently outperforms all the state-of-the-art GNN baselines in various downstream tasks, e.g., node classification, node clustering, and link prediction.

Zicun Cong, Xuan Luo, Pei Jian et al.

Machine learning is disruptive. At the same time, machine learning can only succeed by collaboration among many parties in multiple steps naturally as pipelines in an eco-system, such as collecting data for possible machine learning applications, collaboratively training models by multiple parties and delivering machine learning services to end users. Data is critical and penetrating in the whole machine learning pipelines. As machine learning pipelines involve many parties and, in order to be successful, have to form a constructive and dynamic eco-system, marketplaces and data pricing are fundamental in connecting and facilitating those many parties. In this article, we survey the principles and the latest research development of data pricing in machine learning pipelines. We start with a brief review of data marketplaces and pricing desiderata. Then, we focus on pricing in three important steps in machine learning pipelines. To understand pricing in the step of training data collection, we review pricing raw data sets and data labels. We also investigate pricing in the step of collaborative training of machine learning models, and overview pricing machine learning models for end users in the step of machine learning deployment. We also discuss a series of possible future directions.

Wei Wei, Jiayi Liu, Xianling Mao et al.

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

Ling Cheng, Feida Zhu, Huiwen Liu et al.

Since its advent in 2009, Bitcoin, a cryptography-enabled peer-to-peer digital payment system, has been gaining increasing attention from both academia and industry. An effort designed to overcome a cluster of bottlenecks inherent in existing centralized financial systems, Bitcoin has always been championed by the crypto community as an example of the spirit of decentralization. While the decentralized nature of Bitcoin's Proof-of-Work consensus algorithm has often been discussed in great detail, no systematic study has so far been conducted to quantitatively measure the degree of decentralization of Bitcoin from an asset perspective -- How decentralized is Bitcoin as a financial asset? We present in this paper the first systematic investigation of the degree of decentralization for Bitcoin based on its entire transaction history. We proposed both static and dynamic analysis of Bitcoin transaction network with quantifiable decentralization measures developed based on network analysis and market efficiency study. Case studies are also conducted to demonstrate the effectiveness of our proposed metrics.

Wei Wei, Jiayi Liu, Xianling Mao et al.

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leverage target information for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

Feida Zhu, Chaowei Fang, Kai-Kuang Ma

Existing neural networks proposed for low-level image processing tasks are usually implemented by stacking convolution layers with limited kernel size. Every convolution layer merely involves in context information from a small local neighborhood. More contextual features can be explored as more convolution layers are adopted. However it is difficult and costly to take full advantage of long-range dependencies. We propose a novel non-local module, Pyramid Non-local Block, to build up connection between every pixel and all remain pixels. The proposed module is capable of efficiently exploiting pairwise dependencies between different scales of low-level structures. The target is fulfilled through first learning a query feature map with full resolution and a pyramid of reference feature maps with downscaled resolutions. Then correlations with multi-scale reference features are exploited for enhancing pixel-level feature representation. The calculation procedure is economical considering memory consumption and computational cost. Based on the proposed module, we devise a Pyramid Non-local Enhanced Networks for edge-preserving image smoothing which achieves state-of-the-art performance in imitating three classical image smoothing algorithms. Additionally, the pyramid non-local block can be directly incorporated into convolution neural networks for other image restoration tasks. We integrate it into two existing methods for image denoising and single image super-resolution, achieving consistently improved performance.

Shanyan Guan, Ying Tai, Bingbing Ni et al.

The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator. Embedding a given image back to the latent space of StyleGAN enables wide interesting semantic image editing applications. Although previous works are able to yield impressive inversion results based on an optimization framework, which however suffers from the efficiency issue. In this work, we propose a novel collaborative learning framework that consists of an efficient embedding network and an optimization-based iterator. On one hand, with the progress of training, the embedding network gives a reasonable latent code initialization for the iterator. On the other hand, the updated latent code from the iterator in turn supervises the embedding network. In the end, high-quality latent code can be obtained efficiently with a single forward pass through our embedding network. Extensive experiments demonstrate the effectiveness and efficiency of our work.

Wei Wei, Ling Cheng, Xianling Mao et al.

Recently, automatic image caption generation has been an important focus of the work on multimodal translation task. Existing approaches can be roughly categorized into two classes, i.e., top-down and bottom-up, the former transfers the image information (called as visual-level feature) directly into a caption, and the later uses the extracted words (called as semanticlevel attribute) to generate a description. However, previous methods either are typically based one-stage decoder or partially utilize part of visual-level or semantic-level information for image caption generation. In this paper, we address the problem and propose an innovative multi-stage architecture (called as Stack-VS) for rich fine-gained image caption generation, via combining bottom-up and top-down attention models to effectively handle both visual-level and semantic-level information of an input image. Specifically, we also propose a novel well-designed stack decoder model, which is constituted by a sequence of decoder cells, each of which contains two LSTM-layers work interactively to re-optimize attention weights on both visual-level feature vectors and semantic-level attribute embeddings for generating a fine-gained image caption. Extensive experiments on the popular benchmark dataset MSCOCO show the significant improvements on different evaluation metrics, i.e., the improvements on BLEU-4/CIDEr/SPICE scores are 0.372, 1.226 and 0.216, respectively, as compared to the state-of-the-arts.

Feida Zhu, Yizhou Yu

Color and tone stylization strives to enhance unique themes with artistic color and tone adjustments. It has a broad range of applications from professional image postprocessing to photo sharing over social networks. Mainstream photo enhancement softwares provide users with predefined styles, which are often hand-crafted through a trial-and-error process. Such photo adjustment tools lack a semantic understanding of image contents and the resulting global color transform limits the range of artistic styles it can represent. On the other hand, stylistic enhancement needs to apply distinct adjustments to various semantic regions. Such an ability enables a broader range of visual styles. In this paper, we propose a novel deep learning architecture for automatic image stylization, which learns local enhancement styles from image pairs. Our deep learning architecture is an end-to-end deep fully convolutional network performing semantics-aware feature extraction as well as automatic image adjustment prediction. Image stylization can be efficiently accomplished with a single forward pass through our deep network. Experiments on existing datasets for image stylization demonstrate the effectiveness of our deep learning architecture.

Sein Minn, Yi Yu, Michel C. Desmarais et al.

In Intelligent Tutoring System (ITS), tracing the student's knowledge state during learning has been studied for several decades in order to provide more supportive learning instructions. In this paper, we propose a novel model for knowledge tracing that i) captures students' learning ability and dynamically assigns students into distinct groups with similar ability at regular time intervals, and ii) combines this information with a Recurrent Neural Network architecture known as Deep Knowledge Tracing. Experimental results confirm that the proposed model is significantly better at predicting student performance than well known state-of-the-art techniques for student modelling.