Virtual try-on, a rapidly evolving field in computer vision, is transforming e-commerce by improving customer experiences through precise garment warping and seamless integration onto the human body. While existing methods such as TPS and flow address the garment warping but overlook the finer contextual details. In this paper, we introduce a novel graph based warping technique which emphasizes the value of context in garment flow. Our graph based warping module generates warped garment as well as a coarse person image, which is utilised by a simple refinement network to give a coarse virtual tryon image. The proposed work exploits latent diffusion model to generate the final tryon, treating garment transfer as an inpainting task. The diffusion model is conditioned with decoupled cross attention based inversion of visual and textual information. We introduce an occlusion aware warping constraint that generates dense warped garment, without any holes and occlusion. Our method, validated on VITON-HD and Dresscode datasets, showcases substantial state-of-the-art qualitative and quantitative results showing considerable improvement in garment warping, texture preservation, and overall realism.
相關內容
Proportional dynamics, originated from peer-to-peer file sharing systems, models a decentralized price-learning process in Fisher markets. Previously, items in the dynamics operate independently of one another, and each is assumed to belong to a different seller. In this paper, we show how it can be generalized to the setting where each seller brings multiple items and buyers allocate budgets at the granularity of sellers rather than individual items. The generalized dynamics consistently converges to the competitive equilibrium, and interestingly relates to the auto-bidding paradigm currently popular in online advertising auction markets. In contrast to peer-to-peer networks, the proportional rule is not imposed as a protocol in auto-bidding markets. Regarding this incentive concern, we show that buyers have a strong tendency to follow the rule, but it is easy for sellers to profitably deviate (given buyers' commitment to the rule). Based on this observation, we further study the seller-side deviation game and show that it admits a unique pure Nash equilibrium. Though it is generally different from the competitive equilibrium, we show that it attains a good fairness guarantee as long as the market is competitive enough and not severely monopolized.
The efficacy of interpolating via Variably Scaled Kernels (VSKs) is known to be dependent on the definition of a proper scaling function, but no numerical recipes to construct it are available. Previous works suggest that such a function should mimic the target one, but no theoretical evidence is provided. This paper fills both the gaps: it proves that a scaling function reflecting the target one may lead to enhanced approximation accuracy, and it provides a user-independent tool for learning the scaling function by means of Discontinuous Neural Networks ({\delta}NN), i.e., NNs able to deal with possible discontinuities. Numerical evidence supports our claims, as it shows that the key features of the target function can be clearly recovered in the learned scaling function.
Scene recognition based on deep-learning has made significant progress, but there are still limitations in its performance due to challenges posed by inter-class similarities and intra-class dissimilarities. Furthermore, prior research has primarily focused on improving classification accuracy, yet it has given less attention to achieving interpretable, precise scene classification. Therefore, we are motivated to propose EnTri, an ensemble scene recognition framework that employs ensemble learning using a hierarchy of visual features. EnTri represents features at three distinct levels of detail: pixel-level, semantic segmentation-level, and object class and frequency level. By incorporating distinct feature encoding schemes of differing complexity and leveraging ensemble strategies, our approach aims to improve classification accuracy while enhancing transparency and interpretability via visual and textual explanations. To achieve interpretability, we devised an extension algorithm that generates both visual and textual explanations highlighting various properties of a given scene that contribute to the final prediction of its category. This includes information about objects, statistics, spatial layout, and textural details. Through experiments on benchmark scene classification datasets, EnTri has demonstrated superiority in terms of recognition accuracy, achieving competitive performance compared to state-of-the-art approaches, with an accuracy of 87.69%, 75.56%, and 99.17% on the MIT67, SUN397, and UIUC8 datasets, respectively.
Query-focused summarization (QFS) aims to produce summaries that answer particular questions of interest, enabling greater user control and personalization. With the advent of large language models (LLMs), shows their impressive capability of textual understanding through large-scale pretraining, which implies the great potential of extractive snippet generation. In this paper, we systematically investigated two indispensable characteristics that the LLMs-based QFS models should be harnessed, Lengthy Document Summarization and Efficiently Fine-grained Query-LLM Alignment, respectively. Correspondingly, we propose two modules called Query-aware HyperExpert and Query-focused Infini-attention to access the aforementioned characteristics. These innovations pave the way for broader application and accessibility in the field of QFS technology. Extensive experiments conducted on existing QFS benchmarks indicate the effectiveness and generalizability of the proposed approach. Our code is publicly available at //github.com/DCDmllm/IDEAL_Summary.
Recently, constructions of optimal linear codes from simplicial complexes have attracted much attention and some related nice works were presented. Let $q$ be a prime power. In this paper, by using the simplicial complexes of ${\mathbb F}_{q}^m$ with one single maximal element, we construct four families of linear codes over the ring ${\mathbb F}_{q}+u{\mathbb F}_{q}$ ($u^2=0$), which generalizes the results of [IEEE Trans. Inf. Theory 66(6):3657-3663, 2020]. The parameters and Lee weight distributions of these four families of codes are completely determined. Most notably, via the Gray map, we obtain several classes of optimal linear codes over ${\mathbb F}_{q}$, including (near) Griesmer codes and distance-optimal codes.
The discretization of fluid-poromechanics systems is typically highly demanding in terms of computational effort. This is particularly true for models of multiphysics flows in the brain, due to the geometrical complexity of the cerebral anatomy - requiring a very fine computational mesh for finite element discretization - and to the high number of variables involved. Indeed, this kind of problems can be modeled by a coupled system encompassing the Stokes equations for the cerebrospinal fluid in the brain ventricles and Multiple-network Poro-Elasticity (MPE) equations describing the brain tissue, the interstitial fluid, and the blood vascular networks at different space scales. The present work aims to rigorously derive a posteriori error estimates for the coupled Stokes-MPE problem, as a first step towards the design of adaptive refinement strategies or reduced order models to decrease the computational demand of the problem. Through numerical experiments, we verify the reliability and optimal efficiency of the proposed a posteriori estimator and identify the role of the different solution variables in its composition.
The use of trajectory data with abundant spatial-temporal information is pivotal in Intelligent Transport Systems (ITS) and various traffic system tasks. Location-Based Services (LBS) capitalize on this trajectory data to offer users personalized services tailored to their location information. However, this trajectory data contains sensitive information about users' movement patterns and habits, necessitating confidentiality and protection from unknown collectors. To address this challenge, privacy-preserving methods like K-anonymity and Differential Privacy have been proposed to safeguard private information in the dataset. Despite their effectiveness, these methods can impact the original features by introducing perturbations or generating unrealistic trajectory data, leading to suboptimal performance in downstream tasks. To overcome these limitations, we propose a Federated Variational AutoEncoder (FedVAE) approach, which effectively generates a new trajectory dataset while preserving the confidentiality of private information and retaining the structure of the original features. In addition, FedVAE leverages Variational AutoEncoder (VAE) to maintain the original feature space and generate new trajectory data, and incorporates Federated Learning (FL) during the training stage, ensuring that users' data remains locally stored to protect their personal information. The results demonstrate its superior performance compared to other existing methods, affirming FedVAE as a promising solution for enhancing data privacy and utility in location-based applications.
Link prediction on knowledge graphs (KGs) is a key research topic. Previous work mainly focused on binary relations, paying less attention to higher-arity relations although they are ubiquitous in real-world KGs. This paper considers link prediction upon n-ary relational facts and proposes a graph-based approach to this task. The key to our approach is to represent the n-ary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention. The fully-connected attention captures universal inter-vertex interactions, while with edge-aware attentive biases to particularly encode the graph structure and its heterogeneity. In this fashion, our approach fully models global and local dependencies in each n-ary fact, and hence can more effectively capture associations therein. Extensive evaluation verifies the effectiveness and superiority of our approach. It performs substantially and consistently better than current state-of-the-art across a variety of n-ary relational benchmarks. Our code is publicly available.
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas -- feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9%, 7.5%, and 23% better than ConvE on the FB15k-237, WN18RR and YAGO3-10 datasets respectively. The results validate our central hypothesis -- that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191