Reprimo (RPRM) as a Potential Preventive and Therapeutic Target for Radiation-Induced Brain Injury via Multiple Mechanisms.

Patients receiving cranial radiotherapy for primary and metastatic brain tumors may experience radiation-induced brain injury (RIBI). Thus far, there has been a lack of effective preventive and therapeutic strategies for RIBI. Due to its complicated underlying pathogenic mechanisms, it is rather difficult to develop a single approach to target them simultaneously. We have recently reported that Reprimo (RPRM), a tumor suppressor gene, is a critical player in DNA damage repair, and RPRM deletion significantly confers radioresistance to mice. Herein, by using an RPRM knockout (KO) mouse model established in our laboratory, we found that RPRM deletion alleviated RIBI in mice via targeting its multiple underlying mechanisms. Specifically, RPRM knockout significantly reduced hippocampal DNA damage and apoptosis shortly after mice were exposed to whole-brain irradiation (WBI). For the late-delayed effect of WBI, RPRM knockout obviously ameliorated a radiation-induced decline in neurocognitive function and dramatically diminished WBI-induced neurogenesis inhibition. Moreover, RPRM KO mice exhibited a significantly lower level of acute and chronic inflammation response and microglial activation than wild-type (WT) mice post-WBI. Finally, we uncovered that RPRM knockout not only protected microglia against radiation-induced damage, thus preventing microglial activation, but also protected neurons and decreased the induction of CCL2 in neurons after irradiation, in turn attenuating the activation of microglial cells nearby through paracrine CCL2. Taken together, our results indicate that RPRM plays a crucial role in the occurrence of RIBI, suggesting that RPRM may serve as a novel potential target for the prevention and treatment of RIBI.

Electron Beam Irradiation as a General Approach for the Rapid Synthesis of Covalent Organic Frameworks under Ambient Conditions.

Crystalline porous materials such as covalent organic frameworks (COFs) are advanced materials to tackle challenges of catalysis and separation in industrial processes. Their synthetic routes often require elevated temperatures, closed systems with high pressure, and long reaction times, hampering their industrial applications. Here we use a traditionally unperceived strategy to assemble highly crystalline COFs by electron beam irradiation with controlled received dosage, contrasting sharply with the previous observation that radiation damages the crystallinity of solids. Such synthesis by electron beam irradiation can be achieved under ambient conditions within minutes, and the process is amendable for large-scale production. The intense and targeted energy input to the reactants leads to new reaction pathways that favor COF formation in nearly quantitative yield. This strategy is applicable not only to known COFs but also to new series of flexible COFs that are difficult to obtain using traditional methods.

Synthesis of 4-Azaindolines Using Phase-Transfer Catalysis via an Intramolecular Mannich Reaction.

A series of bifunctional asymmetric phase-transfer catalysts containing novel fluorine-containing urea groups derived from cinchona alkaloids have been synthesized and successfully applied in the asymmetric intramolecular Mannich reaction. The 4-azaindoline products bearing multiple substrates were obtained in excellent yield (90-99%), with high enantioselectivity (up to 95%) and diastereoselectivity (up to >99:1).

Clinical characteristics of 145 patients with corona virus disease 2019 (COVID-19) in Taizhou, Zhejiang, China.

OBJECTIVE: The aim of this study was to investigate the clinical characteristics of Corona Virus Disease 2019 in Taizhou, China. METHODS: A single center retrospective observational study was performed between Jan 1, 2020 and Mar 11, 2020 at Taizhou Public Health Medical Center, Zhejiang, China. All patients with confirmed Corona Virus Disease 2019 were enrolled, and their clinical data were gathered by reviewing electronic medical records. Outcomes of severely ill patients and non-severely ill patients were compared. RESULTS: Of 145 hospitalized patients with COVID-19, the average age was 47.5 years old (standard deviation, 14.6) and 54.5% were men. Hypertension was the most common comorbidity (15.2%), followed by diabetes mellitus (9.7%). Common symptoms included dry cough (81.4%), fever (75.2%), anorexia (42.8%), fatigue (40.7%), chest tightness (32.4%), diarrhea (26.9%) and dizziness (20%). According to imaging examination, 79.3% patients showed bilateral pneumonia, 18.6% showed unilateral pneumonia, 61.4% showed ground-glass opacity, and 2.1% showed no abnormal result. Compared with non-severely ill patients, severely ill patients were older (mean, years, 52.8 vs. 45.3, p < 0.01), had a higher proportion of diabetes mellitus (16.3% vs. 6.9%, p = 0.08), had a higher body mass index (mean, 24.78 vs. 23.20, p = 0.02) and were more likely to have fever (90.7% vs. 68.6%, p = 0.01), anorexia (60.5% vs. 35.3%, p = 0.01), chest tightness (60.5% vs.20.6%, p < 0.01) and dyspnea (7.0% vs. 0%, p = 0.03). Of the 43 severely ill patients, 6 (14%) received high-flow nasal cannula oxygen therapy, and 1 (2.3%) received invasive mechanical ventilation. CONCLUSIONS: Older patients or patients with comorbidities such as obesity or diabetes mellitus were more likely to have severe condition. Treatments of COVID-19 is still experimental and more clinical trials are needed.

A comprehensive study of CD44 rs 187115 variant and cancer risk in a central Chinese population.

The rs187115, an intronic variant of CD44 gene, has been previously reported to play a potential role in genetic susceptibility to cancer. Here, we comprehensively examined the association between CD44 rs187115 variant and cancer risk (breast cancer, cervical cancer, lung cancer, gastric cancer, liver cancer, colon cancer, and rectal cancer) in a central Chinese population. The rs187115 variant was genotyped with the polymerase chain reaction-restriction fragment length polymorphism assay. In this study, we observed that rs187115 was associated with the risk of cervical, lung, and liver cancer, but not with the risk of breast, gastric, colon, rectal or colorectal cancer. Of note, the G allele and G allele genotypes of rs187115 conferred an increased risk of cervical, lung, and liver cancer. To improve the statistical strength, a followed meta-analysis was conducted. The results demonstrated that rs187115 was significantly associated with cancer risk, and the significant association remained in the stratification analysis by ethnicity, genotyping method, and cancer type. Collectively, the CD44 rs187115 variant may be associated with the risk of cervical, lung, and liver cancer in the central Chinese population, and may be used as a potential biomarker for cancer predisposition in the Asian population, especially in the Chinese population.

Direct enantio- and diastereoselective Mannich reactions of isatin-derived ketimines with oxo-indanecarboxylates catalyzed by chiral thiourea derived from hydroquinidine.

A highly diastereo- and enantioselective Mannich reaction of isatin-derived ketimines with oxo-indanecarboxylates catalyzed by chiral thiourea derived from hydroquinidine has been developed. A series of 3-substituted 3-amino-oxindoles containing assembled bicyclic rings linked by a C-C bond were constructed by this protocol in excellent yields (92-99%) with high enantioselectivities (85-99% ee) and diastereoselectivities (up to >99 : 1 dr).

A single low dose of Fe ions can cause long-term biological responses in NL20 human bronchial epithelial cells.

Space radiation cancer risk may be a potential obstacle for long-duration spaceflight. Among all types of cancer space radiation may induce, lung cancer has been estimated to be the largest potential risk. Although previous animal study has shown that Fe ions, the most important contributor to the total dose equivalent of space radiation, induced a higher incidence of lung tumorigenesis per dose than X-rays, the underlying mechanisms at cellular level remained unclear. Therefore, in the present study, we investigated long-term biological changes in NL20 human bronchial epithelial cells after exposure to Fe ion or X-ray irradiation. We found that compared with sham control, the progeny of NL20 cells irradiated with 0.1 Gy of Fe ions showed slightly increased micronucleus formation, significantly decreased cell proliferation, disturbed cell cycle distribution, and obviously elevated intracellular ROS levels accompanied by reduced SOD1 and SOD2 expression, but the progeny of NL20 cells irradiated with 0.9 Gy of X-rays did not show any significant changes. More importantly, Fe ion exposure caused much greater soft-agar colony formation than X-rays did in the progeny of irradiated NL20 cells, clearly suggesting higher cell transformation potential of Fe ions compared with X-rays. These data may shed the light on the potential lung tumorigenesis risk from Fe ion exposure. In addition, ATM inhibition by Ku55933 reversed some of the changes in the progeny of Fe ion-irradiated cells but not others such as soft-agar colony formation, suggesting complex processes from DNA damage to carcinogenesis. These data indicate that even a single low dose of Fe ions can induce long-term biological responses such as cell transformation, etc., suggesting unignorable health risk from space radiation to astronauts.

A novel incomplete hesitant fuzzy information supplement and clustering method for large-scale group decision-making.

Clustering is an effective means to reduce the scaling of large-scale group decision-making (LSGDM). However, there are many problems with clustering methods, such as incomplete or ambiguous information usually provided by different decision makers. Traditional clustering methods may not be able to handle these situations effectively, resulting in incomplete decision-making information. Calculating the clustering centers may become very complex and time-consuming. Inappropriate distance weights may also lead to incorrect cluster assignments, and these problems will seriously affect the clustering results. This research provides a novel incomplete hesitant fuzzy information supplement and clustering approach for large-scale group decision-making in order to address the aforementioned difficulties. First, the approach takes into account the trust degradation and the inhibition of relationships of distrust in the process of trust propagation, and then it builds a global and local network of trust. A novel supplemental formula is provided that takes into account the decision-preference maker's as well as the trust-neighbor's information, allowing the decision-neighbor maker's recommendation to be realized. Therefore, an improved distance function can be proposed to calculate the weights by combining the relative standard deviation theory and selecting the selected clustering centers by using the density peaks in order to optimize the selection of clustering centers and reduce the complexity and scaling of the decision. Finally, an example is presented to demonstrate how the proposed method can be applied. The consistency index and comparison experiments are used to evaluate if the suggested approach is effective and reliable.

Reprimo (RPRM) mediates neuronal ferroptosis via CREB-Nrf2/SCD1 pathways in radiation-induced brain injury.

Neuronal ferroptosis has been found to contribute to degenerative brain disorders and traumatic and hemorrhagic brain injury, but whether radiation-induced brain injury (RIBI), a critical deleterious effect of cranial radiation therapy for primary and metastatic brain tumors, involves neuronal ferroptosis remains unclear. We have recently discovered that deletion of reprimo (RPRM), a tumor suppressor gene, ameliorates RIBI, in which its protective effect on neurons is one of the underlying mechanisms. In this study, we found that whole brain irradiation (WBI) induced ferroptosis in mouse brain, manifesting as alterations in mitochondrial morphology, iron accumulation, lipid peroxidation and a dramatic reduction in glutathione peroxidase 4 (GPX4) level. Moreover, the hippocampal ferroptosis induced by ionizing irradiation (IR) mainly happened in neurons. Intriguingly, RPRM deletion protected the brain and primary neurons against IR-induced ferroptosis. Mechanistically, RPRM deletion prevented iron accumulation by reversing the significant increase in the expression of iron storage protein ferritin heavy chain (Fth), ferritin light chain (Ftl) and iron importer transferrin receptor 1 (Tfr1), as well as enhancing the expression of iron exporter ferroportin (Fpn) after IR. RPRM deletion also inhibited lipid peroxidation by abolishing the reduction of GPX4 and stearoyl coenzyme A desaturase-1 (SCD1) induced by IR. Importantly, RPRM deletion restored or even increased the expression of nuclear factor, erythroid 2 like 2 (Nrf2) in irradiated neurons. On top of that, compromised cyclic AMP response element (CRE)-binding protein (CREB) signaling was found to be responsible for the down-regulation of Nrf2 and SCD1 after irradiation, specifically, RPRM bound to CREB and promoted its degradation after IR, leading to a reduction of CREB protein level, which in turn down-regulated Nrf2 and SCD1. Thus, RPRM deletion recovered Nrf2 and SCD1 through its impact on CREB. Taken together, neuronal ferroptosis is involved in RIBI, RPRM deletion prevents IR-induced neuronal ferroptosis through restoring CREB-Nrf2/SCD1 pathways.

Towards Lightweight Super-Resolution with Dual Regression Learning.

Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks by learning a mapping from low-resolution (LR) images to high-resolution (HR) images. However, the SR problem is typically an ill-posed problem and existing methods would come with several limitations. First, the possible mapping space of SR can be extremely large since there may exist many different HR images that can be super-resolved from the same LR image. As a result, it is hard to directly learn a promising SR mapping from such a large space. Second, it is often inevitable to develop very large models with extremely high computational cost to yield promising SR performance. In practice, one can use model compression techniques to obtain compact models by reducing model redundancy. Nevertheless, it is hard for existing model compression methods to accurately identify the redundant components due to the extremely large SR mapping space. To alleviate the first challenge, we propose a dual regression learning scheme to reduce the space of possible SR mappings. Specifically, in addition to the mapping from LR to HR images, we learn an additional dual regression mapping to estimate the downsampling kernel and reconstruct LR images. In this way, the dual mapping acts as a constraint to reduce the space of possible mappings. To address the second challenge, we propose a dual regression compression (DRC) method to reduce model redundancy in both layer-level and channel-level based on channel pruning. Specifically, we first develop a channel number search method that minimizes the dual regression loss to determine the redundancy of each layer. Given the searched channel numbers, we further exploit the dual regression manner to evaluate the importance of channels and prune the redundant ones. Extensive experiments show the effectiveness of our method in obtaining accurate and efficient SR models.

Loss of RSR1 function increases the abscisic acid content and improves rice quality performance at high temperature.

Rice starch regulator1 (RSR1) participates in the regulation of starch synthesis in rice, but it's function on starch synthesis and quality formation in response to high temperature is unknown. RSR1 mutation resulted in a significant increase in the abscisic acid (ABA) content in rice grains under both normal and high temperature, and the effect of high temperature on grain filling and quality formation of the rsr1 mutants was significantly reduced. The grain size, 1000-kernels weight, amylose content, gelatinization temperature, and starch viscosity of the rsr1 mutants were less sensitive to high temperature. Loss of RSR1 function increased the expression levels of starch synthesis-related genes and reduced their responses to high temperature to some extent. Besides, the percentage of germinated seeds from rsr1 mutants was significantly lower than that of the wild-type, and the difference was more significant under ABA treatment. The shoot lengths of the rsr1 mutants were remarkably shorter than those of the wild-type, which was further exacerbated by ABA treatment. These results indicated that loss function of RSR1 can improve rice quality performance at high temperature by moderately increasing the ABA content of rice grains, which provides theoretical significance for the cultivation of better-quality rice with high-temperature resistance.

Cell-free DNA methylation reveals cell-specific tissue injury and correlates with disease severity and patient outcomes in COVID-19.

BACKGROUND: The recently identified methylation patterns specific to cell type allows the tracing of cell death dynamics at the cellular level in health and diseases. This study used COVID-19 as a disease model to investigate the efficacy of cell-specific cell-free DNA (cfDNA) methylation markers in reflecting or predicting disease severity or outcome. METHODS: Whole genome methylation sequencing of cfDNA was performed for 20 healthy individuals, 20 cases with non-hospitalized COVID-19 and 12 cases with severe COVID-19 admitted to intensive care unit (ICU). Differentially methylated regions (DMRs) and gene ontology pathway enrichment analyses were performed to explore the locus-specific methylation difference between cohorts. The proportion of cfDNA derived from lung and immune cells to a given sample (i.e. tissue fraction) at cell-type resolution was estimated using a novel algorithm, which reflects lung injuries and immune response in COVID-19 patients and was further used to evaluate clinical severity and patient outcome. RESULTS: COVID­19 patients had globally reduced cfDNA methylation level compared with healthy controls. Compared with non-hospitalized COVID-19 patients, the cfDNA methylation pattern was significantly altered in severe patients with the identification of 11,156 DMRs, which were mainly enriched in pathways related to immune response. Markedly elevated levels of cfDNA derived from lung and more specifically alveolar epithelial cells, bronchial epithelial cells, and lung endothelial cells were observed in COVID-19 patients compared with healthy controls. Compared with non-hospitalized patients or healthy controls, severe COVID-19 had significantly higher cfDNA derived from B cells, T cells and granulocytes and lower cfDNA from natural killer cells. Moreover, cfDNA derived from alveolar epithelial cells had the optimal performance to differentiate COVID-19 with different severities, lung injury levels, SOFA scores and in-hospital deaths, with the area under the receiver operating characteristic curve of 0.958, 0.941, 0.919 and 0.955, respectively. CONCLUSION: Severe COVID-19 has a distinct cfDNA methylation signature compared with non-hospitalized COVID-19 and healthy controls. Cell type-specific cfDNA methylation signature enables the tracing of COVID-19 related cell deaths in lung and immune cells at cell-type resolution, which is correlated with clinical severities and outcomes, and has extensive application prospects to evaluate tissue injuries in diseases with multi-organ dysfunction.

[Efficacies of bone-marrow-derived mononuclear cells with a hydroxylapatite composite in the treatment of osteonecrosis of the femoral head].

OBJECTIVE: To evaluate the efficacies of core decompression and implantation of concentrated autologous bone marrow containing mononuclear cells (BMMCs) with porous hydroxylapatite composite in the treatment of osteonecrosis of the femoral head. METHODS: A total of 35 patients with 57 osteonecrosis hips with ARCO stage I, stage II and stage IIIA disease were treated by BMMCs with a porous hydroxylapatite composite. The mean age at surgery was 39.4 (26-58) years and the mean period of follow-up 28 (12-40) months. In the control group, cell-free porous hydroxylapatite composite was implanted into 17 patients (27 hips) with osteonecrosis of the femoral head and the outcomes were compared. RESULTS: At the last follow-up, postoperative Harris hip scores significantly increased in both groups (P < 0.0001). The magnitude of increase was significantly greater in the BMMCs group compared with the control group (28.3% ± 0.9% vs 18.4% ± 1.7%, P < 0.01). Postoperative visual analog scale (VAS) scores significantly decreased in both groups (P < 0.01). The magnitude of decrease was significantly greater in the BMMCs group compared with the control group (-70.2% ± 2.1% vs -51.7% ± 2.9%, P < 0.001). The clinical success rate was significantly higher in the BMMCs group compared with the control group (75.4% vs 37.0%, P < 0.01). The radiological success rates were similar between the BMMCs and control groups (59.6% vs 40.7%, P = 0.1046). CONCLUSION: The combined regimen of core decompression and implantation of concentrated autologous BMMCs with porous hydroxylapatite composite appears to confer benefits in the treatment of in stages I-IIIA osteonecrosis of the femoral head.

Structured Knowledge Distillation for Dense Prediction.

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the distillation scheme for image classification and perform knowledge distillation for each pixel separately, leading to sub-optimal performance. Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem. Specifically, we study two structured distillation schemes: i) pair-wise distillation that distills the pair-wise similarities by building a static graph; and ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by experiments on three dense prediction tasks: semantic segmentation, depth estimation and object detection. Code is available at https://git.io/StructKD.

Protocol for IPO11 deletion and re-expression in H460 lung cancer cells using CRISPR-Cas9 and plasmid transfection.

Exploring the essential role of Importin 11 (IPO11) in the nuclear translocation of its potential cargo proteins requires an efficient means of IPO11 deletion and re-expression. Here, we present a protocol for the generation of IPO11 deletion using CRISPR-Cas9 and re-expression using plasmid transfection in H460 non-small cell lung cancer cells. We describe steps for lentiviral transduction of H460 cells, single clone selection, and expansion and validation of cell colonies. We then detail plasmid transfection and validation of transfection efficiency. For complete details on the use and execution of this protocol, please refer to Zhang et al.1.

Effects of Music, Massage, Exercise, or Acupuncture in the Treatment of Depression Among College Students: A Network Meta-Analysis.

Objective: To assess the therapeutic impacts of exercise, massage, and music interventions on college students experiencing depression by employing a mesh meta-analysis approach. This research intends to offer valuable insights to aid in the development of non-pharmaceutical treatment strategies for depression. Methods: We conducted a thorough search across various databases including Cochrane, PubMed, Embase, Web of Science, CNKI, and Wanfang to explore the effects of music, massage, aerobic exercise, fitness Qigong, yoga, tai chi, ball games, strength training, dance, whole body vibration training, and high-intensity interval training on the treatment of depression in college students. The search period was from January 1, 2023, which marks the establishment of each database. Subsequently, a mesh meta-analysis was performed using the "Stata 15.1" software, incorporating outcome indicators from 24 included literature comprising a total of 1458 patients. Results: Based on the ranking of the optimal intervention effects of various non-pharmaceutical methods, the order, from highest to lowest probability, was as follows: high-intensity interval training (96%), yoga (94.90%), dance (78.30%), music (73.30%), ball games (62.50%), strength training (51.70%), aerobic training (45.30%), tai chi (35.40%), vibration training (27.30%), massage (20.10%), qigong (14.30%), and no intervention (1.00%). This ranking aligns closely with the findings obtained from pairwise comparisons between different interventions. Conclusion: High-intensity interval training is likely to yield the most effective therapeutic results for college students with depression. In the pairwise comparison of different interventions, High-intensity interval training is also better than most interventions. However, to establish its intervention effect more conclusively, further validation through additional high-quality randomized controlled trials is necessary.

Multiplex time-reducing quantitative polymerase chain reaction assay for determination of telomere length in blood and tissue DNA.

In this paper we describe a multiplex time-reducing quantitative polymerase chain reaction (qPCR) method for determination of telomere length. This multiplex qPCR assay enables two pairs of primers to simultaneously amplify telomere and single copy gene (albumin) templates, thus reducing analysis time and labor compared with the previously established singleplex assay. The chemical composition of the master mix and primers for the telomere and albumin were systematically optimized. The thermal cycling program was designed to ensure complete separation of the melting processes of the telomere and albumin. Semi-log standard curves of DNA concentration versus cycle threshold (C (t)) were established, with a linear relationship over an 81-fold DNA concentration range. The well-performed intra-assay (RSD range 2.4-4.7%) and inter-assay (RSD range: 3.1-5.0%) reproducibility were demonstrated to ensure measurement stability. Using wild-type, Lewis lung carcinoma and H22 liver carcinoma C57BL/6 mouse models, significantly different telomere lengths among different DNA samples were not observed in wild-type mice. However, the relative telomere lengths of the tumor DNA in the two strains of tumor-bearing mice were significantly shorter than the lengths in the surrounding non-tumor DNA of tumor-bearing mice and the tissue DNA of wild-type mice. These results suggest that the shortening of telomere lengths may be regarded as an important indicator for cancer control and prevention. Quantification of telomere lengths was further confirmed by the traditional Southern blotting method. This method could be successfully used to reduce the time needed for rapid, precise measurement of telomere lengths in biological samples.

Improved spatial learning performance of fat-1 mice is associated with enhanced neurogenesis and neuritogenesis by docosahexaenoic acid.

Docosahexaenoic acid (DHA), an n-3 long chain polyunsaturated fatty acid (LC-PUFA), highly enriched in the central nervous system, is critical for brain development and function. It has been shown that DHA deficiency impairs cognitive performance whereas DHA supplementation improves the condition. However, the mechanisms underlying the role of DHA in brain development and function remain to be elucidated. By using transgenic fat-1 mice rich in endogenous n-3 PUFA, we show that increased brain DHA significantly enhances hippocampal neurogenesis shown by an increased number of proliferating neurons and neuritogenesis, evidenced by increased density of dendritic spines of CA1 pyramidal neurons in the hippocampus. Concurrently, fat-1 mice exhibit a better spatial learning performance in the Morris water maze compared with control WT littermates. In vitro experiments further demonstrate that DHA promotes differentiation and neurite outgrowth of neuronal cells derived from mouse ES cells and increases the proliferation of cells undergoing differentiation into neuronal lineages from the ES cells. These results together provide direct evidence for a promoting effect of DHA on neurogenesis and neuritogenesis and suggest that this effect may be a mechanism underlying its beneficial effect on behavioral performance.

Few-Shot Image and Sentence Matching via Aligned Cross-Modal Memory.

Image and sentence matching has attracted much attention recently, and many effective methods have been proposed to deal with it. But even the current state-of-the-arts still cannot well associate those challenging pairs of images and sentences containing few-shot content in their regions and words. In fact, such a few-shot matching problem is seldom studied and has become a bottleneck for further performance improvement in real-world applications. In this work, we formulate this challenging problem as few-shot image and sentence matching, and accordingly propose an Aligned Cross-Modal Memory (ACMM) model to deal with it. The model can not only softly align few-shot regions and words in a weakly-supervised manner, but also persistently store and update cross-modal prototypical representations of few-shot classes as references, without using any groundtruth region-word correspondence. The model can also adaptively balance the relative importance between few-shot and common content in the image and sentence, which leads to better measurement of overall similarity. We perform extensive experiments in terms of both few-shot and conventional image and sentence matching, and demonstrate the effectiveness of the proposed model by achieving the state-of-the-art results on two public benchmark datasets.

Distillation-Guided Residual Learning for Binary Convolutional Neural Networks.

It is challenging to bridge the performance gap between binary convolutional neural network (BCNN) and floating-point CNN (FCNN). This performance gap is mainly caused by the inferior modeling capability and training strategy of BCNN, which leads to substantial residuals in intermediate feature maps between BCNN and FCNN. To minimize the performance gap, we enforce BCNN to produce similar intermediate feature maps with the ones of FCNN. This intuition leads to a more effective training strategy for BCNN, i.e., optimizing each binary convolutional block with blockwise distillation loss derived from FCNN. The goal of minimizing the residuals in intermediate feature maps also motivates us to update the binary convolutional block architecture to facilitate the optimization of blockwise distillation loss. Specifically, a lightweight shortcut branch is inserted into each binary convolutional block to complement residuals at each block. Benefited from its squeeze-and-interaction (SI) structure, this shortcut branch introduces a fraction of parameters, e.g., less than 10% overheads, but effectively boosts the modeling capability of binary convolution blocks in BCNN. Extensive experiments on ImageNet demonstrate the superior performance of our method in both classification efficiency and accuracy, e.g., BCNN trained with our methods achieves the accuracy of 60.45% on ImageNet, better than many state-of-the-art ones.