The development of cost-effective, sustainable, and efficient catalysts for liquid organic hydrogen carrier systems is a significant goal. However, all the reported liquid organic hydrogen carrier ...systems relied on the use of precious metal catalysts. Herein, a liquid organic hydrogen carrier system based on non-noble metal catalysis was established. The Mn-catalyzed dehydrogenative coupling of methanol and N,N'-dimethylethylenediamine to form N,N'-(ethane-1,2-diyl)bis(N-methylformamide), and the reverse hydrogenation reaction constitute a hydrogen storage system with a theoretical hydrogen capacity of 5.3 wt%. A rechargeable hydrogen storage could be achieved by a subsequent hydrogenation of the resulting dehydrogenation mixture to regenerate the H
-rich compound. The maximum selectivity for the dehydrogenative amide formation was 97%.
In this study, we show that landmark detection or face alignment task is not a single and independent problem. Instead, its robustness can be greatly improved with auxiliary information. ...Specifically, we jointly optimize landmark detection together with the recognition of heterogeneous but subtly correlated facial attributes, such as gender, expression, and appearance attributes. This is non-trivial since different attribute inference tasks have different learning difficulties and convergence rates. To address this problem, we formulate a novel tasks-constrained deep model, which not only learns the inter-task correlation but also employs dynamic task coefficients to facilitate the optimization convergence when learning multiple complex tasks. Extensive evaluations show that the proposed task-constrained learning (i) outperforms existing face alignment methods, especially in dealing with faces with severe occlusion and pose variation, and (ii) reduces model complexity drastically compared to the state-of-the-art methods based on cascaded deep model.
Deep Learning Face Attributes in the Wild Liu, Ziwei; Luo, Ping; Wang, Xiaogang ...
2015 IEEE International Conference on Computer Vision (ICCV),
12/2015
Conference Proceeding, Journal Article
Open access
Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction in the wild. It cascades two CNNs, LNet and ...ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently. LNet is pre-trained by massive general object categories for face localization, while ANet is pre-trained by massive face identities for attribute prediction. This framework not only outperforms the state-of-the-art with a large margin, but also reveals valuable facts on learning face representation. (1) It shows how the performances of face localization (LNet) and attribute prediction (ANet) can be improved by different pre-training strategies. (2) It reveals that although the filters of LNet are fine-tuned only with image-level attribute tags, their response maps over entire images have strong indication of face locations. This fact enables training LNet for face localization with only image-level annotations, but without face bounding boxes or landmarks, which are required by all attribute recognition works. (3) It also demonstrates that the high-level hidden neurons of ANet automatically discover semantic concepts after pre-training with massive face identities, and such concepts are significantly enriched after fine-tuning with attribute tags. Each attribute can be well explained with a sparse linear combination of these concepts.
Interpersonal relation defines the association, e.g., warm, friendliness, and dominance, between two or more people. We investigate if such fine-grained and high-level relation traits can be ...characterized and quantified from face images in the wild. We address this challenging problem by first studying a deep network architecture for robust recognition of facial expressions. Unlike existing models that typically learn from facial expression labels alone, we devise an effective multitask network that is capable of learning from rich auxiliary attributes such as gender, age, and head pose, beyond just facial expression data. While conventional supervised training requires datasets with complete labels (e.g., all samples must be labeled with gender, age, and expression), we show that this requirement can be relaxed via a novel attribute propagation method. The approach further allows us to leverage the inherent correspondences between heterogeneous attribute sources despite the disparate distributions of different datasets. With the network we demonstrate state-of-the-art results on existing facial expression recognition benchmarks. To predict inter-personal relation, we use the expression recognition network as branches for a Siamese model. Extensive experiments show that our model is capable of mining mutual context of faces for accurate fine-grained interpersonal prediction.
Deep Learning Identity-Preserving Face Space Zhu, Zhenyao; Luo, Ping; Wang, Xiaogang ...
2013 IEEE International Conference on Computer Vision,
12/2013
Conference Proceeding, Journal Article
Open access
Face recognition with large pose and illumination variations is a challenging problem in computer vision. This paper addresses this challenge by proposing a new learning based face representation: ...the face identity-preserving (FIP) features. Unlike conventional face descriptors, the FIP features can significantly reduce intra-identity variances, while maintaining discriminative ness between identities. Moreover, the FIP features extracted from an image under any pose and illumination can be used to reconstruct its face image in the canonical view. This property makes it possible to improve the performance of traditional descriptors, such as LBP 2 and Gabor 31, which can be extracted from our reconstructed images in the canonical view to eliminate variations. In order to learn the FIP features, we carefully design a deep network that combines the feature extraction layers and the reconstruction layer. The former encodes a face image into the FIP features, while the latter transforms them to an image in the canonical view. Extensive experiments on the large MultiPIE face database 7 demonstrate that it significantly outperforms the state-of-the-art face recognition methods.
Since the beginning of 2020, coronavirus disease 2019 (COVID-19) has spread throughout China. This study explains the findings from lung computed tomography images of some patients with COVID-19 ...treated in this medical institution and discusses the difference between COVID-19 and other lung diseases.
Few-layer black phosphorus (BP), as the most alluring graphene analogue owing to its similar structure as graphene and thickness dependent direct band-gap, has now triggered a new wave of research on ...two-dimensional (2D) materials based photonics and optoelectronics. However, a major obstacle of practical applications for few-layer BPs comes from their instabilities of laser-induced optical damage. Herein, we demonstrate that, few-layer BPs, which was fabricated through the liquid exfoliation approach, can be developed as a new and practical saturable absorber (SA) by depositing few-layer BPs with microfiber. The saturable absorption property of few-layer BPs had been verified through an open-aperture z-scan measurement at the telecommunication band. The microfiber-based BP device had been found to show a saturable average power of ~4.5 mW and a modulation depth of 10.9%, which is further confirmed through a balanced twin detection measurement. By integrating this optical SA device into an erbium-doped fiber laser, it was found that it can deliver the mode-locked pulse with duration down to 940 fs with central wavelength tunable from 1532 nm to 1570 nm. The prevention of BP from oxidation through the "lateral interaction scheme" owing to this microfiber-based few-layer BP SA device might partially mitigate the optical damage problem of BP. Our results not only demonstrate that black phosphorus might be another promising SA material for ultrafast photonics, but also provide a practical solution to solve the optical damage problem of black phosphorus by assembling with waveguide structures such as microfiber.
Herein, we report a novel cobalt-catalyzed stereodivergent transfer hydrogenation of alkynes to Z- and E-alkenes. Effective selectivity control is achieved based on a rational catalyst design. ...Moreover, this mild system allows for the transfer hydrogenation of alkynes bearing a wide range of functional groups in good yields using catalyst loadings as low as 0.2 mol %. The general applicability of this procedure is highlighted by the synthesis of more than 50 alkenes with good chemo- and stereoselectivity. A preliminary mechanistic study revealed that E-alkene product was generated via sequential alkyne hydrogenation to give Z-alkene intermediate, followed by a Z to E alkene isomerization process.
Recent advances in clothes recognition have been driven by the construction of clothes datasets. Existing datasets are limited in the amount of annotations and are difficult to cope with the various ...challenges in real-world applications. In this work, we introduce DeepFashion1, a large-scale clothes dataset with comprehensive annotations. It contains over 800,000 images, which are richly annotated with massive attributes, clothing landmarks, and correspondence of images taken under different scenarios including store, street snapshot, and consumer. Such rich annotations enable the development of powerful algorithms in clothes recognition and facilitating future researches. To demonstrate the advantages of DeepFashion, we propose a new deep model, namely FashionNet, which learns clothing features by jointly predicting clothing attributes and landmarks. The estimated landmarks are then employed to pool or gate the learned features. It is optimized in an iterative manner. Extensive experiments demonstrate the effectiveness of FashionNet and the usefulness of DeepFashion.