Link Traversal-based Query Processing (ltqp), in which a sparql query is evaluated over a web of documents rather than a single dataset, is often seen as a theoretically interesting yet impractical technique. However, in a time where the hypercentralization of data has increasingly come under scrutiny, a decentralized Web of Data with a simple document-based interface is appealing, as it enables data publishers to control their data and access rights. While ltqp allows evaluating complex queries over such webs, it suffers from performance issues (due to the high number of documents containing data) as well as information quality concerns (due to the many sources providing such documents). In existing ltqp approaches, the burden of finding sources to query is entirely in the hands of the data consumer. In this paper, we argue that to solve these issues, data publishers should also be able to suggest sources of interest and guide the data consumer towards relevant and trustworthy data. We introduce a theoretical framework that enables such guided link traversal and study its properties. We illustrate with a theoretic example that this can improve query results and reduce the number of network requests. We evaluate our proposal experimentally on a virtual linked web with specifications and indeed observe that not just the data quality but also the efficiency of querying improves. Under consideration in Theory and Practice of Logic Programming (TPLP).
Google Translate has been prominent for language translation; however, limited work has been done in evaluating the quality of translation when compared to human experts. Sanskrit one of the oldest written languages in the world. In 2022, the Sanskrit language was added to the Google Translate engine. Sanskrit is known as the mother of languages such as Hindi and an ancient source of the Indo-European group of languages. Sanskrit is the original language for sacred Hindu texts such as the Bhagavad Gita. In this study, we present a framework that evaluates the Google Translate for Sanskrit using the Bhagavad Gita. We first publish a translation of the Bhagavad Gita in Sanskrit using Google Translate. Our framework then compares Google Translate version of Bhagavad Gita with expert translations using sentiment and semantic analysis via BERT-based language models. Our results indicate that in terms of sentiment and semantic analysis, there is low level of similarity in selected verses of Google Translate when compared to expert translations. In the qualitative evaluation, we find that Google translate is unsuitable for translation of certain Sanskrit words and phrases due to its poetic nature, contextual significance, metaphor and imagery. The mistranslations are not surprising since the Bhagavad Gita is known as a difficult text not only to translate, but also to interpret since it relies on contextual, philosophical and historical information. Our framework lays the foundation for automatic evaluation of other languages by Google Translate
Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability. This work offers a new generation paradigm that allows flexible control of the output image, such as spatial layout and palette, while maintaining the synthesis quality and model creativity. With compositionality as the core idea, we first decompose an image into representative factors, and then train a diffusion model with all these factors as the conditions to recompose the input. At the inference stage, the rich intermediate representations work as composable elements, leading to a huge design space (i.e., exponentially proportional to the number of decomposed factors) for customizable content creation. It is noteworthy that our approach, which we call Composer, supports various levels of conditions, such as text description as the global information, depth map and sketch as the local guidance, color histogram for low-level details, etc. Besides improving controllability, we confirm that Composer serves as a general framework and facilitates a wide range of classical generative tasks without retraining. Code and models will be made available.
Multi-domain recommender systems benefit from cross-domain representation learning and positive knowledge transfer. Both can be achieved by introducing a specific modeling of input data (i.e. disjoint history) or trying dedicated training regimes. At the same time, treating domains as separate input sources becomes a limitation as it does not capture the interplay that naturally exists between domains. In this work, we efficiently learn multi-domain representation of sequential users' interactions using graph neural networks. We use temporal intra- and inter-domain interactions as contextual information for our method called MAGRec (short for Multi-domAin Graph-based Recommender). To better capture all relations in a multi-domain setting, we learn two graph-based sequential representations simultaneously: domain-guided for recent user interest, and general for long-term interest. This approach helps to mitigate the negative knowledge transfer problem from multiple domains and improve overall representation. We perform experiments on publicly available datasets in different scenarios where MAGRec consistently outperforms state-of-the-art methods. Furthermore, we provide an ablation study and discuss further extensions of our method.
Recent studies in neural network-based monaural speech separation (SS) have achieved a remarkable success thanks to increasing ability of long sequence modeling. However, they would degrade significantly when put under realistic noisy conditions, as the background noise could be mistaken for speaker's speech and thus interfere with the separated sources. To alleviate this problem, we propose a novel network to unify speech enhancement and separation with gradient modulation to improve noise-robustness. Specifically, we first build a unified network by combining speech enhancement (SE) and separation modules, with multi-task learning for optimization, where SE is supervised by parallel clean mixture to reduce noise for downstream speech separation. Furthermore, in order to avoid suppressing valid speaker information when reducing noise, we propose a gradient modulation (GM) strategy to harmonize the SE and SS tasks from optimization view. Experimental results show that our approach achieves the state-of-the-art on large-scale Libri2Mix- and Libri3Mix-noisy datasets, with SI-SNRi results of 16.0 dB and 15.8 dB respectively. Our code is available at GitHub.
This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medical image segmentation tasks due to their incredible semantic feature encoding and global information comprehension abilities. However, most existing approaches ignore a salient aspect of medical video data - the temporal dimension. Our proposed framework explicitly extracts features from neighbouring frames across the temporal dimension and incorporates them with a temporal feature blender, which then tokenises the high-level spatio-temporal feature to form a strong global feature encoded via a Swin Transformer. The final segmentation results are produced via a UNet-like encoder-decoder architecture. Our model outperforms other approaches by a significant margin and improves the segmentation benchmarks on the VFSS2022 dataset, achieving a dice coefficient of 0.8986 and 0.8186 for the two datasets tested. Our studies also show the efficacy of the temporal feature blending scheme and cross-dataset transferability of learned capabilities. Code and models are fully available at https://github.com/SimonZeng7108/Video-SwinUNet.
Exemplar-based image translation refers to the task of generating images with the desired style, while conditioning on certain input image. Most of the current methods learn the correspondence between two input domains and lack the mining of information within the domains. In this paper, we propose a more general learning approach by considering two domain features as a whole and learning both inter-domain correspondence and intra-domain potential information interactions. Specifically, we propose a Cross-domain Feature Fusion Transformer (CFFT) to learn inter- and intra-domain feature fusion. Based on CFFT, the proposed CFFT-GAN works well on exemplar-based image translation. Moreover, CFFT-GAN is able to decouple and fuse features from multiple domains by cascading CFFT modules. We conduct rich quantitative and qualitative experiments on several image translation tasks, and the results demonstrate the superiority of our approach compared to state-of-the-art methods. Ablation studies show the importance of our proposed CFFT. Application experimental results reflect the potential of our method.
Human-designed visual manuals are crucial components in shape assembly activities. They provide step-by-step guidance on how we should move and connect different parts in a convenient and physically-realizable way. While there has been an ongoing effort in building agents that perform assembly tasks, the information in human-design manuals has been largely overlooked. We identify that this is due to 1) a lack of realistic 3D assembly objects that have paired manuals and 2) the difficulty of extracting structured information from purely image-based manuals. Motivated by this observation, we present IKEA-Manual, a dataset consisting of 102 IKEA objects paired with assembly manuals. We provide fine-grained annotations on the IKEA objects and assembly manuals, including decomposed assembly parts, assembly plans, manual segmentation, and 2D-3D correspondence between 3D parts and visual manuals. We illustrate the broad application of our dataset on four tasks related to shape assembly: assembly plan generation, part segmentation, pose estimation, and 3D part assembly.
For successful deployment of robots in multifaceted situations, an understanding of the robot for its environment is indispensable. With advancing performance of state-of-the-art object detectors, the capability of robots to detect objects within their interaction domain is also enhancing. However, it binds the robot to a few trained classes and prevents it from adapting to unfamiliar surroundings beyond predefined scenarios. In such scenarios, humans could assist robots amidst the overwhelming number of interaction entities and impart the requisite expertise by acting as teachers. We propose a novel pipeline that effectively harnesses human gaze and augmented reality in a human-robot collaboration context to teach a robot novel objects in its surrounding environment. By intertwining gaze (to guide the robot's attention to an object of interest) with augmented reality (to convey the respective class information) we enable the robot to quickly acquire a significant amount of automatically labeled training data on its own. Training in a transfer learning fashion, we demonstrate the robot's capability to detect recently learned objects and evaluate the influence of different machine learning models and learning procedures as well as the amount of training data involved. Our multimodal approach proves to be an efficient and natural way to teach the robot novel objects based on a few instances and allows it to detect classes for which no training dataset is available. In addition, we make our dataset publicly available to the research community, which consists of RGB and depth data, intrinsic and extrinsic camera parameters, along with regions of interest.
Physical-layer authentication is a popular alternative to the conventional key-based authentication for internet of things (IoT) devices due to their limited computational capacity and battery power. However, this approach has limitations due to poor robustness under channel fluctuations, reconciliation overhead, and no clear safeguard distance to ensure the secrecy of the generated authentication keys. In this regard, we propose a novel, secure, and lightweight continuous authentication scheme for IoT device authentication. Our scheme utilizes the inherent properties of the IoT devices transmission model as its source for seed generation and device authentication. Specifically, our proposed scheme provides continuous authentication by checking the access time slots and spreading sequences of the IoT devices instead of repeatedly generating and verifying shared keys. Due to this, access to a coherent key is not required in our proposed scheme, resulting in the concealment of the seed information from attackers. Our proposed authentication scheme for IoT devices demonstrates improved performance compared to the benchmark schemes relying on physical-channel. Our empirical results find a near threefold decrease in misdetection rate of illegitimate devices and close to zero false alarm rate in various system settings with varied numbers of active devices up to 200 and signal-to-noise ratio from 0 dB to 30 dB. Our proposed authentication scheme also has a lower computational complexity of at least half the computational cost of the benchmark schemes based on support vector machine and binary hypothesis testing in our studies. This further corroborates the practicality of our scheme for IoT deployments.