arXiv subjects

Feida Zhu

Publications and source records attributed to Feida Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2023

AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose

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

cs.CV↗

arXiv2023

HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimation

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.

cs.CV↗

arXiv2023

Multi-view Hypergraph Contrastive Policy Learning for Conversational Recommendation

Conversational recommendation systems (CRS) aim to interactively acquire user preferences and accordingly recommend items to users. Accurately learning the dynamic user preferences is of crucial importance for CRS. Previous works learn the user preferences with pairwise relations from the interactive conversation and item knowledge, while largely ignoring the fact that factors for a relationship in CRS are multiplex. Specifically, the user likes/dislikes the items that satisfy some attributes (Like/Dislike view). Moreover social influence is another important factor that affects user preference towards the item (Social view), while is largely ignored by previous works in CRS. The user preferences from these three views are inherently different but also correlated as a whole. The user preferences from the same views should be more similar than that from different views. The user preferences from Like View should be similar to Social View while different from Dislike View. To this end, we propose a novel model, namely Multi-view Hypergraph Contrastive Policy Learning (MHCPL). Specifically, MHCPL timely chooses useful social information according to the interactive history and builds a dynamic hypergraph with three types of multiplex relations from different views. The multiplex relations in each view are successively connected according to their generation order.

cs.IR↗

arXiv2023

Evolve Path Tracer: Early Detection of Malicious Addresses in Cryptocurrency

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.

cs.AI↗

arXiv2023

MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction

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.

cs.CV↗

arXiv2023

GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning

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.

cs.CV↗

arXiv2023

Code Will Tell: Visual Identification of Ponzi Schemes on Ethereum

Ethereum has become a popular blockchain with smart contracts for investors nowadays. Due to the decentralization and anonymity of Ethereum, Ponzi schemes have been easily deployed and caused significant losses to investors. However, there are still no explainable and effective methods to help investors easily identify Ponzi schemes and validate whether a smart contract is actually a Ponzi scheme. To fill the research gap, we propose PonziLens, a novel visualization approach to help investors achieve early identification of Ponzi schemes by investigating the operation codes of smart contracts. Specifically, we conduct symbolic execution of opcode and extract the control flow for investing and rewarding with critical opcode instructions. Then, an intuitive directed-graph based visualization is proposed to display the investing and rewarding flows and the crucial execution paths, enabling easy identification of Ponzi schemes on Ethereum. Two usage scenarios involving both Ponzi and non-Ponzi schemes demonstrate the effectiveness of PonziLens.

cs.HC↗

arXiv2023

NFTDisk: Visual Detection of Wash Trading in NFT Markets

With the growing popularity of Non-Fungible Tokens (NFT), a new type of digital assets, various fraudulent activities have appeared in NFT markets. Among them, wash trading has become one of the most common frauds in NFT markets, which attempts to mislead investors by creating fake trading volumes. Due to the sophisticated patterns of wash trading, only a subset of them can be detected by automatic algorithms, and manual inspection is usually required. We propose NFTDisk, a novel visualization for investors to identify wash trading activities in NFT markets, where two linked visualization modules are presented: a radial visualization module with a disk metaphor to overview NFT transactions and a flow-based visualization module to reveal detailed NFT flows at multiple levels. We conduct two case studies and an in-depth user interview with 14 NFT investors to evaluate NFTDisk. The results demonstrate its effectiveness in exploring wash trading activities in NFT markets.

cs.HC↗

arXiv2022

Heterogeneous Graph Neural Network with Multi-view Representation Learning

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.

cs.LG↗

arXiv2022

Toward Intention Discovery for Early Malice Detection in Bitcoin

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.

cs.LG↗

arXiv2022

Data Provenance via Differential Auditing

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.

cs.CR↗

arXiv2022

Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning

Incorporating Knowledge Graphs (KG) into recommeder system has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs). However, the extremely sparse user-item interactions significantly degrade the performance of the GNN-based models, as: 1) the sparse interaction, means inadequate supervision signals and limits the supervised GNN-based models; 2) the combination of sparse interactions (CF part) and redundant KG facts (KG part) results in an unbalanced information utilization. Besides, the GNN paradigm aggregates local neighbors for node representation learning, while ignoring the non-local KG facts and making the knowledge extraction insufficient. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring contrastive learning in KGR and propose a novel multi-level interactive contrastive learning mechanism. Different from traditional contrastive learning methods which contrast nodes of two generated graph views, interactive contrastive mechanism conducts layer-wise self-supervised learning by contrasting layers of different parts within graphs, which is also an "interaction" action. Specifically, we first construct local and non-local graphs for user/item in KG, exploring more KG facts for KGR. Then an intra-graph level interactive contrastive learning is performed within each graph, which contrasts layers of the CF and KG parts, for more consistent information leveraging. Besides, an inter-graph level interactive contrastive learning is performed between the local and non-local graphs, for sufficiently and coherently extracting non-local KG signals. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts.

cs.IR↗

arXiv2022

PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on

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.

cs.CV↗

arXiv2022

Automatic Noisy Label Correction for Fine-Grained Entity Typing

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.

cs.CL↗

arXiv2022

Declaration-based Prompt Tuning for Visual Question Answering

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.

cs.CV↗

arXiv2022

Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System

Knowledge graph (KG) plays an increasingly important role in recommender systems. Recently, graph neural networks (GNNs) based model has gradually become the theme of knowledge-aware recommendation (KGR). However, there is a natural deficiency for GNN-based KGR models, that is, the sparse supervised signal problem, which may make their actual performance drop to some extent. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring the contrastive learning in KG-aware recommendation and propose a novel multi-level cross-view contrastive learning mechanism, named MCCLK. Different from traditional contrastive learning methods which generate two graph views by uniform data augmentation schemes such as corruption or dropping, we comprehensively consider three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views. Specifically, we consider the user-item graph as a collaborative view, the item-entity graph as a semantic view, and the user-item-entity graph as a structural view. MCCLK hence performs contrastive learning across three views on both local and global levels, mining comprehensive graph feature and structure information in a self-supervised manner. Besides, in semantic view, a k-Nearest-Neighbor (kNN) item-item semantic graph construction module is proposed, to capture the important item-item semantic relation which is usually ignored by previous work. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. The implementations are available at: https://github.com/CCIIPLab/MCCLK.

cs.IR↗

arXiv2021

Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations

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.

cs.CY↗

arXiv2021

Geometry-Entangled Visual Semantic Transformer for Image Captioning

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.

cs.CV↗