Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.     

Collaborative Distribution Alignment for 2D image-based 3D shape retrieval

Retrieving 3D shapes with 2D images has become a popular research area nowadays, and a great deal of work has been devoted to reducing the discrepancy between 3D shapes and 2D images to improve retrieval performance. However, most approaches ignore the semantic information and decision boundaries of the two domains, and cannot achieve both domain alignment and category alignment in one module. In this paper, a novel Collaborative Distribution Alignment (CDA) model is developed to address the above existing challenges. Specifically, we first adopt a dual-stream CNN, following a similarity guided constraint module, to generate discriminative embeddings for input 2D images and 3D shapes (described as multiple views). Subsequently, we explicitly introduce a joint domain-class alignment module to dynamically learn a class-discriminative and domain-agnostic feature space, which can narrow the distance between 2D image and 3D shape instances of the same underlying category, while pushing apart the instances from different categories. Furthermore, we apply a decision boundary refinement module to avoid generating class-ambiguity embeddings by dynamically adjusting inconsistencies between two discriminators. Extensive experiments and evaluations on two challenging benchmarks, MI3DOR and MI3DOR-2, demonstrate the superiority of the proposed CDA method for 2D image-based 3D shape retrieval task.     

Multi-scale and multi-patch transformer for sandstorm image enhancement

Sandstorm is a meteorological phenomenon common in arid and semi-arid regions. A sandstorm can carry large volumes of sand unexpectedly, which leads to severe color deviations and significantly degraded visibility when an image is taken in such a scenario. However, existing image enhancement methods cannot enhance sandstorm images well due to the challenging degradations and the scarcity of sandstorm training data. In this paper, we propose a Transformer with rotary position embedding to perform sandstorm image enhancement via building multi-scale and multi-patch dependencies. Our key insights in this work are 1) a multi-scale Transformer can globally eliminate the color deviations of sandstorm images via aggregating global information, 2) a multi-patch Transformer can recover local details well via learning the spatial variant degradations, and 3) a U-shape Transformer with rotary position embedding as the core unit of multi-scale and multi-patch Transformer can effectively build the long-range dependencies. We also contribute a real-world Sandstorm Image Enhancement (SIE) dataset including 1,400 sandstorm images with different degrees of degradations and various scenes. Experiments performed on synthetic images and real-world sandstorm images demonstrate that our proposed method not only obtains visually pleasing results but also outperforms state-of-the-art methods qualitatively and quantitatively.     

Influencer-defaulter mutation-based optimization algorithms for predicting electricity prices

Efficient electricity price forecasting plays a significant role in our society. In this paper, a novel influencer-defaulter mutation (IDM) mutation operator has been proposed. The IDM operator has been combined with six well-known optimization algorithms to create mutated optimization algorithms whose performance has been tested on twenty-four standard benchmark functions. Further, the artificial neural network is integrated with mutated optimization algorithms to solve the electricity price prediction problem. The policymakers can identify appropriate variables based on the predicted prices to help future market planning. The statistical results prove the efficacy of the IDM operator on the recent optimization algorithms.     

“半翻转”教学模式下评价指标体系研究与实践

研究基于“半翻转”教学模式的线上教学评价指标体系,包括课前活动开展、课中教学活动设计、课后任务以及基于此过程中的评价指标体系设计。最后通过层次分析法设计评价指标权重,设计评价算法得到动态评价结果。该评价指标体系应用在本专业“数据结构与算法”课程中,并得到良好的应用效果。     

Priority-MECE: A Mobile Edge Cloud Ecosystem Based on Priority Tasks Offloading

Mobile Networks and Applications - With the rapid development of Internet of things, the traditional city model is no longer applicable. Therefore, the emerging concept of smart city meets the...     

A medical Chatbot using machine learning and natural language understanding

Multimedia Tools and Applications - For people with busy schedules, travelling to and from a hospital for treatment is considerably time consuming, which leads them to ignore their health problems....     

Stabilization for Schrödinger Equation with Internal Damping and Boundary Disturbance

In this paper, the stabilization for Schrödinger equation subject to internal damping and boundary disturbance at the control end is investigated. Due to its immeasurability, the nonlinear observer system is designed to obtain the state information, and the existence of weak solution and its convergence for the nonlinear observer system are proved. The feedback control is realized by the backstepping transformation. In addition, the adaptive disturbance rejection control is applied to estimate the disturbance. According to the observer and disturbance estimation, the feedback control is finally designed to stabilize the system asymptotically.

     

Rip currents near coastal structures in Lake Michigan: Characterization and assessment for warnings

Rip currents near coastal structures commonly occur in Lake Michigan in the Great Lakes region of the United States. Lack of timely warning due to undocumented characteristics of rip currents and no assessment tool can contribute to tragic drownings incidents. In this paper, we characterized rip current occurrences near breakwater structures and developed an assessment tool for providing timely rip current warnings to beachgoers at the study site, City of Port Washington, WI. Characteristics of rip currents near the structure were observed from field measurements or visual images. Deflection rip currents had speeds of ～ 0.2 m/s and lasted for several hours. The rip current occurrences were associated with environmental proxies. It was found that rip currents can occur even when the water appears calm near the structure. A Structure Rip Checklist and Assessment Matrix (SRiCAM) with a four-tiered risk was developed and validated using observations. Furthermore, the SRiCAM was integrated into cyberinfrastructure with a data contingency plan to provide real-time warnings to the public. The applicability of the SRiCAM to other locations across Lake Michigan was further tested and results are promising. Overall, the SRiCAM has the potential to be widely extended to foster recreational water safety and resilience to rip current hazards in the Great Lakes.