We propose a novel constraint called Multiple Spectral filter Operators Preservation (MSFOR) to compute functional maps and based on it, develop an efficient deep functional map architecture called Deep MSFOP for shape matching. The core idea is that, instead of using the general descriptor preservation constraint, we require our maps to preserve multiple spectral filter operators. This allows us to incorporate more informative geometrical information, contained in different frequency bands of functions, into the functional map computing. This can be confirmed by that some previous techniques like wavelet preservation and LBO commutativity are actually our special cases. Moreover, we also develop a very efficient way to compute the maps with MSFOP constraint, which can be conveniently embedded into the deep learning, especially having learnable filter operators. Utilizing the above results, we finally design our Deep MSFOP pipeline, equipped with a suitable unsupervised loss jointly penalizing the functional map and the underlying pointwise map. Our deep functional map has notable advantages, including that the functional map is more geometrically informative and guaranteed to be proper, and the computing is numerically stable. Extensive experimental results on different datasets demonstrate that our approach outperforms the existing state-of-the-art methods, especially in challenging settings like non-isometric and inconsistent topology datasets.
Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal with VideoQA insufficiently by simply taking uniformly sampled frames as visual inputs, which ignores question-relevant visual clues. Moreover, there are no human annotations for question-critical timestamps in existing VideoQA datasets. In light of this, we propose a novel weakly supervised framework to enforce the LMMs to reason out the answers with question-critical moments as visual inputs. Specifically, we fuse the question and answer pairs as event descriptions to find multiple keyframes as target moments, which will be pseudo-labels. With these pseudo-labels as additionally weak supervision, we devise a lightweight Gaussian-based Contrastive Grounding (GCG) module. GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs. Extensive experiments on several VideoQA benchmarks verify the effectiveness of our framework, and we achieve substantial improvements compared to previous state-of-the-art methods.
Despite the remarkable results that can be achieved by data-driven intelligent fault diagnosis techniques, they presuppose the same distribution of training and test data as well as sufficient labeled data. Various operating states often exist in practical scenarios, leading to the problem of domain shift that hinders the effectiveness of fault diagnosis. While recent unsupervised domain adaptation methods enable cross-domain fault diagnosis, they struggle to effectively utilize information from multiple source domains and achieve effective diagnosis faults in multiple target domains simultaneously. In this paper, we innovatively proposed a weighted joint maximum mean discrepancy enabled multi-source-multi-target unsupervised domain adaptation (WJMMD-MDA), which realizes domain adaptation under multi-source-multi-target scenarios in the field of fault diagnosis for the first time. The proposed method extracts sufficient information from multiple labeled source domains and achieves domain alignment between source and target domains through an improved weighted distance loss. As a result, domain-invariant and discriminative features between multiple source and target domains are learned with cross-domain fault diagnosis realized. The performance of the proposed method is evaluated in comprehensive comparative experiments on three datasets, and the experimental results demonstrate the superiority of this method.
In this paper, we consider the channel modeling of a heterogeneous vehicular integrated sensing and communication (ISAC) system, where a dual-functional multi-antenna base station (BS) intends to communicate with a multi-antenna vehicular receiver (MR) and sense the surrounding environments simultaneously. The time-varying complex channel impulse responses (CIRs) of the sensing and communication channels are derived, respectively, in which the sensing and communication channels are correlated with shared clusters. The proposed models show great generality for the capability in covering both monostatic and bistatic sensing scenarios, and as well for considering both static clusters/targets and mobile clusters/targets. Important channel statistical characteristics, including time-varying spatial cross-correlation function (CCF) and temporal auto-correlation function (ACF), are derived and analyzed. Numerically results are provided to show the propagation characteristics of the proposed ISAC channel model. Finally, the proposed model is validated via the agreement between theoretical and simulated as well as measurement results.
The efficient utilization of wind power by wind turbines relies on the ability of their pitch systems to adjust blade pitch angles in response to varying wind speeds. However, the presence of multiple fault types in the pitch system poses challenges in accurately classifying these faults. This paper proposes a novel method based on hard sample mining-enabled contrastive feature learning (HSMCFL) to address this problem. The proposed method employs cosine similarity to identify hard samples and subsequently leverages contrastive feature learning to enhance representation learning through the construction of hard sample pairs. Furthermore, a multilayer perceptron is trained using the learned discriminative representations to serve as an efficient classifier. To evaluate the effectiveness of the proposed method, two real datasets comprising wind turbine pitch system cog belt fracture data are utilized. The fault diagnosis performance of the proposed method is compared against existing methods, and the results demonstrate its superior performance. The proposed approach exhibits significant improvements in fault diagnosis accuracy, providing promising prospects for enhancing the reliability and efficiency of wind turbine pitch system fault diagnosis.
Under the background of 5G, Internet, artificial intelligence technol,ogy and robot technology, warehousing, and logistics robot technology has developed rapidly, and products have been widely used. A practical application is to help warehouse personnel pick up or deliver heavy goods at dispersed locations based on dynamic routes. However, programs that can only accept instructions or pre-set by the system do not have more flexibility, but existing human auto-following techniques either cannot accurately identify specific targets or require a combination of lasers and cameras that are cumbersome and do not accomplish obstacle avoidance well. This paper proposed an algorithm that combines DeepSort and a width-based tracking module to track targets and use artificial potential field local path planning to avoid obstacles. The evaluation is performed in a self-designed flat bounded test field and simulated in ROS. Our method achieves the SOTA results on following and successfully reaching the end-point without hitting obstacles.
This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm called Hybrid Regression Translation (HRT) to combine the advantages of autoregressive and non-autoregressive translation. Specifically, HRT first autoregressively generates a discontinuous sequence (e.g., make a prediction every $k$ tokens, $k>1$) and then fills in all previously skipped tokens at once in a non-autoregressive manner. Thus, we can easily trade off the translation quality and speed by adjusting $k$. In addition, by integrating other modeling techniques (e.g., sequence-level knowledge distillation and deep-encoder-shallow-decoder layer allocation strategy) and a mass of engineering efforts, HRT improves 80\% inference speed and achieves equivalent translation performance with the same-capacity AT counterpart. Our fastest system reaches 6k+ words/second on the GPU latency setting, estimated to be about 3.1x faster than the last year's winner.
Optical reconfigurable intelligent surface (ORIS) is an emerging technology that can achieve reconfigurable optical propagation environments by precisely adjusting signal's reflection and shape through a large number of passive reflecting elements. In this paper, we investigate the performance of an ORIS-assisted dual-hop hybrid radio frequency (RF) and free space optics (FSO) communication system. By jointly considering the physical models of ORIS, RF channel, atmospheric turbulence, and pointing error, the closed-form solutions of the system's precise outage probability, asymptotic outage probability and BER have been derived. It is shown through numerical results that the derivation results are accurate and the RF-FSO links with ORISs show a slightly worse performance than the traditional RF-FSO links. Based on theoretical analysis and simulation results, the system design and effect of each parameter have been discussed.
The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide noisy GPS labels associated with the training images, which act as weak supervisions for learning image-to-image similarities. Such label noise prevents deep neural networks from learning discriminative features for accurate localization. To tackle this challenge, we propose to self-supervise image-to-region similarities in order to fully explore the potential of difficult positive images alongside their sub-regions. The estimated image-to-region similarities can serve as extra training supervision for improving the network in generations, which could in turn gradually refine the fine-grained similarities to achieve optimal performance. Our proposed self-enhanced image-to-region similarity labels effectively deal with the training bottleneck in the state-of-the-art pipelines without any additional parameters or manual annotations in both training and inference. Our method outperforms state-of-the-arts on the standard localization benchmarks by noticeable margins and shows excellent generalization capability on multiple image retrieval datasets. Code of this work is available at https://github.com/yxgeee/SFRS.
The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.