LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 13

Search options

  1. Book ; Online: The style transformer with common knowledge optimization for image-text retrieval

    Li, Wenrui / Ma, Zhengyu / Shi, Jinqiao / Fan, Xiaopeng

    2023  

    Abstract: Image-text retrieval which associates different modalities has drawn broad attention due to its excellent research value and broad real-world application. However, most of the existing methods haven't taken the high-level semantic relationships ("style ... ...

    Abstract Image-text retrieval which associates different modalities has drawn broad attention due to its excellent research value and broad real-world application. However, most of the existing methods haven't taken the high-level semantic relationships ("style embedding") and common knowledge from multi-modalities into full consideration. To this end, we introduce a novel style transformer network with common knowledge optimization (CKSTN) for image-text retrieval. The main module is the common knowledge adaptor (CKA) with both the style embedding extractor (SEE) and the common knowledge optimization (CKO) modules. Specifically, the SEE uses the sequential update strategy to effectively connect the features of different stages in SEE. The CKO module is introduced to dynamically capture the latent concepts of common knowledge from different modalities. Besides, to get generalized temporal common knowledge, we propose a sequential update strategy to effectively integrate the features of different layers in SEE with previous common feature units. CKSTN demonstrates the superiorities of the state-of-the-art methods in image-text retrieval on MSCOCO and Flickr30K datasets. Moreover, CKSTN is constructed based on the lightweight transformer which is more convenient and practical for the application of real scenes, due to the better performance and lower parameters.
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Multimedia
    Subject code 004
    Publishing date 2023-03-01
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Book ; Online: PrUE

    Wang, Shaopu / Chen, Xiaojun / Kou, Mengzhen / Shi, Jinqiao

    Distilling Knowledge from Sparse Teacher Networks

    2022  

    Abstract: Although deep neural networks have enjoyed remarkable success across a wide variety of tasks, their ever-increasing size also imposes significant overhead on deployment. To compress these models, knowledge distillation was proposed to transfer knowledge ... ...

    Abstract Although deep neural networks have enjoyed remarkable success across a wide variety of tasks, their ever-increasing size also imposes significant overhead on deployment. To compress these models, knowledge distillation was proposed to transfer knowledge from a cumbersome (teacher) network into a lightweight (student) network. However, guidance from a teacher does not always improve the generalization of students, especially when the size gap between student and teacher is large. Previous works argued that it was due to the high certainty of the teacher, resulting in harder labels that were difficult to fit. To soften these labels, we present a pruning method termed Prediction Uncertainty Enlargement (PrUE) to simplify the teacher. Specifically, our method aims to decrease the teacher's certainty about data, thereby generating soft predictions for students. We empirically investigate the effectiveness of the proposed method with experiments on CIFAR-10/100, Tiny-ImageNet, and ImageNet. Results indicate that student networks trained with sparse teachers achieve better performance. Besides, our method allows researchers to distill knowledge from deeper networks to improve students further. Our code is made public at: \url{https://github.com/wangshaopu/prue}.

    Comment: To appear in ECML PKDD 2022
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Artificial Intelligence ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2022-07-03
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Article ; Online: Broadband mid-infrared coherent light source from fiber-laser-pumped difference frequency generators based on cascaded crystals.

    Feng, Xi / Shi, Jinqiao / Liu, Pei / Zhang, Zhaowei

    Optics express

    2020  Volume 28, Issue 10, Page(s) 14310–14318

    Abstract: We present difference frequency generators (DFGs) using cascaded PPLN crystals, each with a distinct poling-period, as the parametric gain medium. We show that the phase-matching bandwidth of cascaded crystals is the combination of that of each ... ...

    Abstract We present difference frequency generators (DFGs) using cascaded PPLN crystals, each with a distinct poling-period, as the parametric gain medium. We show that the phase-matching bandwidth of cascaded crystals is the combination of that of each individual crystal. In the non-phase-matched section of cascaded crystals, there exists periodic backward and forward frequency-conversion processes. Nonetheless, we demonstrate that such a periodic back-conversion process would not compromise the parametric gain bandwidth of cascaded nonlinear crystals. By using two PPLN crystals with poling periods of 31 µm and 29 µm, we experimentally obtained mid-infrared light sources having instantaneous-bandwidth covering 2.8-3.9 µm, which was roughly twice as much as that from a system based on a single crystal. Moreover, our numerical results show that light sources with an instantaneous-bandwidth covering 2.5-5 µm could be obtained by cascading more crystals. This scheme represents a promising technical route to transform conventional DFGs into a device capable of generating spatially-coherent light emission with very broad instantaneous-bandwidth.
    Language English
    Publishing date 2020-05-11
    Publishing country United States
    Document type Journal Article
    ZDB-ID 1491859-6
    ISSN 1094-4087 ; 1094-4087
    ISSN (online) 1094-4087
    ISSN 1094-4087
    DOI 10.1364/OE.391686
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  4. Book ; Online: Event Causality Extraction with Event Argument Correlations

    Cui, Shiyao / Sheng, Jiawei / Cong, Xin / Li, QuanGang / Liu, Tingwen / Shi, Jinqiao

    2023  

    Abstract: Event Causality Identification (ECI), which aims to detect whether a causality relation exists between two given textual events, is an important task for event causality understanding. However, the ECI task ignores crucial event structure and cause- ... ...

    Abstract Event Causality Identification (ECI), which aims to detect whether a causality relation exists between two given textual events, is an important task for event causality understanding. However, the ECI task ignores crucial event structure and cause-effect causality component information, making it struggle for downstream applications. In this paper, we explore a novel task, namely Event Causality Extraction (ECE), aiming to extract the cause-effect event causality pairs with their structured event information from plain texts. The ECE task is more challenging since each event can contain multiple event arguments, posing fine-grained correlations between events to decide the causeeffect event pair. Hence, we propose a method with a dual grid tagging scheme to capture the intra- and inter-event argument correlations for ECE. Further, we devise a event type-enhanced model architecture to realize the dual grid tagging scheme. Experiments demonstrate the effectiveness of our method, and extensive analyses point out several future directions for ECE.

    Comment: Accepted to COLING2022
    Keywords Computer Science - Computation and Language
    Subject code 380
    Publishing date 2023-01-27
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Book ; Online: Enhancing Multimodal Entity and Relation Extraction with Variational Information Bottleneck

    Cui, Shiyao / Cao, Jiangxia / Cong, Xin / Sheng, Jiawei / Li, Quangang / Liu, Tingwen / Shi, Jinqiao

    2023  

    Abstract: This paper studies the multimodal named entity recognition (MNER) and multimodal relation extraction (MRE), which are important for multimedia social platform analysis. The core of MNER and MRE lies in incorporating evident visual information to enhance ... ...

    Abstract This paper studies the multimodal named entity recognition (MNER) and multimodal relation extraction (MRE), which are important for multimedia social platform analysis. The core of MNER and MRE lies in incorporating evident visual information to enhance textual semantics, where two issues inherently demand investigations. The first issue is modality-noise, where the task-irrelevant information in each modality may be noises misleading the task prediction. The second issue is modality-gap, where representations from different modalities are inconsistent, preventing from building the semantic alignment between the text and image. To address these issues, we propose a novel method for MNER and MRE by Multi-Modal representation learning with Information Bottleneck (MMIB). For the first issue, a refinement-regularizer probes the information-bottleneck principle to balance the predictive evidence and noisy information, yielding expressive representations for prediction. For the second issue, an alignment-regularizer is proposed, where a mutual information-based item works in a contrastive manner to regularize the consistent text-image representations. To our best knowledge, we are the first to explore variational IB estimation for MNER and MRE. Experiments show that MMIB achieves the state-of-the-art performances on three public benchmarks.
    Keywords Computer Science - Multimedia ; Computer Science - Computation and Language
    Subject code 004
    Publishing date 2023-04-05
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Article: Identification of the Causal Agent of Brown Leaf Spot on Kiwifruit and Its Sensitivity to Different Active Ingredients of Biological Fungicides

    Chen, Jia / Ran, Fei / Shi, Jinqiao / Chen, Tingting / Zhao, Zhibo / Zhang, Zhuzhu / He, Linan / Li, Wenzhi / Wang, Bingce / Chen, Xuetang / Wang, Weizhen / Long, Youhua

    Pathogens. 2022 June 10, v. 11, no. 6

    2022  

    Abstract: Kiwifruit (Actinidia chinensis) is an important commercial crop in China, and the occurrence of diseases may cause significant economic loss in its production. In the present study, a new pathogen that causes brown leaf spot disease on kiwifruit was ... ...

    Abstract Kiwifruit (Actinidia chinensis) is an important commercial crop in China, and the occurrence of diseases may cause significant economic loss in its production. In the present study, a new pathogen that causes brown leaf spot disease on kiwifruit was reported. The fungus was isolated from an infected sample and identified as Fusarium graminearum based on morphological and molecular evaluation. Koch’s postulates were confirmed when the pathogen was re-isolated from plants with artificially induced symptoms and identified as F. graminearum. Based on the biological characteristics of the pathogen, it was determined that: its optimal growth temperature was 25 °C; optimal pH was 7; most suitable carbon source was soluble starch; most suitable nitrogen source was yeast powder; and best photoperiod was 12 h light/12 h dark. Further investigations were conducted by determining 50% effective concentrations (EC₅₀) of several active ingredients of biological fungicides against F. graminearum. The results showed that among the studied fungicides, tetramycin and honokiol had the highest antifungal activity against this pathogen. Our findings provide a scientific basis for the prevention and treatment of brown leaf spot disease on kiwifruit.
    Keywords Actinidia chinensis ; Fusarium graminearum ; antifungal properties ; carbon ; financial economics ; honokiol ; kiwifruit ; leaf spot ; nitrogen ; pH ; pathogens ; starch ; temperature ; yeasts ; China
    Language English
    Dates of publication 2022-0610
    Publishing place Multidisciplinary Digital Publishing Institute
    Document type Article
    ZDB-ID 2695572-6
    ISSN 2076-0817
    ISSN 2076-0817
    DOI 10.3390/pathogens11060673
    Database NAL-Catalogue (AGRICOLA)

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Article: Correction: Chen et al. Identification of the Causal Agent of Brown Leaf Spot on Kiwifruit and Its Sensitivity to Different Active Ingredients of Biological Fungicides.

    Chen, Jia / Ran, Fei / Shi, Jinqiao / Chen, Tingting / Zhao, Zhibo / Zhang, Zhuzhu / He, Linan / Li, Wenzhi / Wang, Bingce / Chen, Xuetang / Wang, Weizhen / Long, Youhua

    Pathogens (Basel, Switzerland)

    2023  Volume 12, Issue 11

    Abstract: In the original publication [ ... ]. ...

    Abstract In the original publication [...].
    Language English
    Publishing date 2023-11-08
    Publishing country Switzerland
    Document type Published Erratum
    ZDB-ID 2695572-6
    ISSN 2076-0817
    ISSN 2076-0817
    DOI 10.3390/pathogens12111327
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  8. Article ; Online: First Report of Crown Gall of Kiwifruit (

    He, Linan / Shi, Jinqiao / Zhao, Zhibo / Ran, Fei / Mo, Feixu / Long, Youhua / Yin, Xianhui / Li, Wenzhi / Chen, Tingting / Chen, Jia

    International journal of molecular sciences

    2021  Volume 23, Issue 1

    Abstract: Kiwifruit is moderately sweet and sour and quite popular among consumers; it has been widely planted in some areas of the world. In 2019, the crown gall disease of kiwifruit was discovered in the main kiwifruit-producing area of Guizhou Province, China. ... ...

    Abstract Kiwifruit is moderately sweet and sour and quite popular among consumers; it has been widely planted in some areas of the world. In 2019, the crown gall disease of kiwifruit was discovered in the main kiwifruit-producing area of Guizhou Province, China. This disease can weaken and eventually cause the death of the tree. The phylogeny, morphological and biological characteristics of the bacteria were described, and were related to diseases. The pathogenicity of this species follows the Koch hypothesis, confirming that
    MeSH term(s) Actinidia/microbiology ; Agrobacterium/pathogenicity ; Agrobacterium/physiology ; Base Sequence ; China ; Fruit/microbiology ; Molecular Diagnostic Techniques/methods ; Nucleic Acid Amplification Techniques/methods ; Phylogeny ; Plant Tumors/microbiology ; RNA, Ribosomal, 16S/genetics ; Species Specificity
    Chemical Substances RNA, Ribosomal, 16S
    Language English
    Publishing date 2021-12-24
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2019364-6
    ISSN 1422-0067 ; 1422-0067 ; 1661-6596
    ISSN (online) 1422-0067
    ISSN 1422-0067 ; 1661-6596
    DOI 10.3390/ijms23010207
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  9. Article: Identification of the Causal Agent of Brown Leaf Spot on Kiwifruit and Its Sensitivity to Different Active Ingredients of Biological Fungicides.

    Chen, Jia / Ran, Fei / Shi, Jinqiao / Chen, Tingting / Zhao, Zhibo / Zhang, Zhuzhu / He, Linan / Li, Wenzhi / Wang, Bingce / Chen, Xuetang / Wang, Weizhen / Long, Youhua

    Pathogens (Basel, Switzerland)

    2022  Volume 11, Issue 6

    Abstract: Kiwifruit ( ...

    Abstract Kiwifruit (
    Language English
    Publishing date 2022-06-10
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2695572-6
    ISSN 2076-0817
    ISSN 2076-0817
    DOI 10.3390/pathogens11060673
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  10. Book ; Online: Label Enhanced Event Detection with Heterogeneous Graph Attention Networks

    Cui, Shiyao / Yu, Bowen / Cong, Xin / Liu, Tingwen / Li, Quangang / Shi, Jinqiao

    2020  

    Abstract: Event Detection (ED) aims to recognize instances of specified types of event triggers in text. Different from English ED, Chinese ED suffers from the problem of word-trigger mismatch due to the uncertain word boundaries. Existing approaches injecting ... ...

    Abstract Event Detection (ED) aims to recognize instances of specified types of event triggers in text. Different from English ED, Chinese ED suffers from the problem of word-trigger mismatch due to the uncertain word boundaries. Existing approaches injecting word information into character-level models have achieved promising progress to alleviate this problem, but they are limited by two issues. First, the interaction between characters and lexicon words is not fully exploited. Second, they ignore the semantic information provided by event labels. We thus propose a novel architecture named Label enhanced Heterogeneous Graph Attention Networks (L-HGAT). Specifically, we transform each sentence into a graph, where character nodes and word nodes are connected with different types of edges, so that the interaction between words and characters is fully reserved. A heterogeneous graph attention networks is then introduced to propagate relational message and enrich information interaction. Furthermore, we convert each label into a trigger-prototype-based embedding, and design a margin loss to guide the model distinguish confusing event labels. Experiments on two benchmark datasets show that our model achieves significant improvement over a range of competitive baseline methods.
    Keywords Computer Science - Computation and Language
    Subject code 006
    Publishing date 2020-12-03
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top