Search

Telomerase represents an essential molecular machinery for tumor occurrence and progression and a potential therapeutic target for cancer treatment. Sensitive and reliable analysis of telomerase activity is of significant importance for the diagnosis and treatment of cancer. In this study, we developed a telomerase-activated nanoscintillator probe for deep-tissue and background-free imaging of telomerase activity and screening telomerase inhibitors in tumor-bearing living mice models. The probe was constructed by modifying lanthanide-doped nanoscintillators with aptamer-containing DNA anchor strands which hybridized with quencher labelled–oligonucleotide strands and telomerase primers. The X-ray-induced fluorescence of the probe was quenched originally but turned on upon telomerase-catalyzed extension of the primer. Benefiting from exceptional tissue penetrating properties and negligible autofluorescence of X-ray excitation, this probe enabled direct detection of telomerase activity in vivo via fluorescence imaging. Furthermore, with the direct, readable fluorescent signals, the probe enabled the screening of telomerase inhibitors in living cells and whole-animal models in the native states of telomerase. This strategy would inspire the development of low autofluorescence and deep tissue bioimaging probes for disease diagnosis and drug development in high-level living settings.

The vaporization enthalpies of chelate-based ionic liquids were measured by thermogravimetric analysis and discussed based on the micro-biphasic separation model.

Chelate-based ionic liquids (ChILs) are a type of chelating compound which can melt at low temperature (

Fashion is the way we present ourselves to the world and has become one of the world's largest industries. Fashion, mainly conveyed by vision, has thus attracted much attention from computer vision researchers in recent years. Given the rapid development, this paper provides a comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion: (1) Fashion detection includes landmark detection, fashion parsing, and item retrieval, (2) Fashion analysis contains attribute recognition, style learning, and popularity prediction, (3) Fashion synthesis involves style transfer, pose transformation, and physical simulation, and (4) Fashion recommendation comprises fashion compatibility, outfit matching, and hairstyle suggestion. For each task, the benchmark datasets and the evaluation protocols are summarized. Furthermore, we highlight promising directions for future research., Accepted by ACM Computing Surveys (2021). 39 pages including 2 pages of supplementary materials and 7 pages of reference

With the prevalence of RGB-D cameras, multi-modal video data have become more available for human action recognition. One main challenge for this task lies in how to effectively leverage their complementary information. In this work, we propose a Modality Compensation Network (MCN) to explore the relationships of different modalities, and boost the representations for human action recognition. We regard RGB/optical flow videos as source modalities, skeletons as auxiliary modality. Our goal is to extract more discriminative features from source modalities, with the help of auxiliary modality. Built on deep Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) networks, our model bridges data from source and auxiliary modalities by a modality adaptation block to achieve adaptive representation learning, that the network learns to compensate for the loss of skeletons at test time and even at training time. We explore multiple adaptation schemes to narrow the distance between source and auxiliary modal distributions from different levels, according to the alignment of source and auxiliary data in training. In addition, skeletons are only required in the training phase. Our model is able to improve the recognition performance with source data when testing. Experimental results reveal that MCN outperforms state-of-the-art approaches on four widely-used action recognition benchmarks., Accepted by IEEE Trans. on Image Processing, 2020. Project page: http://39.96.165.147/Projects/MCN_tip2020_ssj/MCN_tip_2020_ssj.html

Background Mirror syndrome (MS) is defined as maternal edema with fetal hydrops and placental edema with different etiologies, such as rhesus isoimmunization and twin-twin transfusion syndrome. Herein, we showcased a unique MS case secondary to fetomaternal hemorrhage (FMH). Case presentation A 32-year-old gravida 2 para 0 woman diagnosed with fetal hydrops was admitted to our hospital. Maternal laboratory tests revealed anemia, slightly increased creatinine and uric acid levels, hypoproteinemia, and significantly increased alpha-fetoprotein and hemoglobin-F levels. Therefore, FMH was diagnosed initially. Two days after admission, the woman had unexpectedly progressive anasarca and started to feel chest distress, palpitations, lethargy, and oliguria, and MS was suspected. An emergency cesarean section was performed to terminate the pregnancy. The maternal clinical symptoms and laboratory tests rapidly improved after delivery. A very preterm infant with a 2080-g birthweight at 31 weeks gestation survived after emergency cesarean section, active resuscitation, emergency blood transfusion, abdominocentesis, and advanced life support. Conclusions FMH could develop into MS, providing new insights into the etiology of MS. Once MS is diagnosed, emergency cesarean section might be an alternative treatment. The very preterm infant survived with a favorable long-term outcome, and a well-trained perinatal work team is needed for such cases.

Online action detection is a brand new challenge and plays a critical role in visual surveillance analytics. It goes one step further than a conventional action recognition task, which recognizes human actions from well-segmented clips. Online action detection is desired to identify the action type and localize action positions on the fly from the untrimmed stream data. In this paper, we propose a multi-modality multi-task recurrent neural network, which incorporates both RGB and Skeleton networks. We design different temporal modeling networks to capture specific characteristics from various modalities. Then, a deep long short-term memory subnetwork is utilized effectively to capture the complex long-range temporal dynamics, naturally avoiding the conventional sliding window design and thus ensuring high computational efficiency. Constrained by a multi-task objective function in the training phase, this network achieves superior detection performance and is capable of automatically localizing the start and end points of actions more accurately. Furthermore, embedding subtask of regression provides the ability to forecast the action prior to its occurrence. We evaluate the proposed method and several other methods in action detection and forecasting on the online action detection data set and gaming action data set datasets. Experimental results demonstrate that our model achieves the state-of-the-art performance on both tasks.

In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking, proposal-based matching), we tackle the problem from a novel perspective, \textbf{co-grounding}, with an elegant one-stage framework. We enhance the single-frame grounding accuracy by semantic attention learning and improve the cross-frame grounding consistency with co-grounding feature learning. Semantic attention learning explicitly parses referring cues in different attributes to reduce the ambiguity in the complex expression. Co-grounding feature learning boosts visual feature representations by integrating temporal correlation to reduce the ambiguity caused by scene dynamics. Experiment results demonstrate the superiority of our framework on the video grounding datasets VID and LiOTB in generating accurate and stable results across frames. Our model is also applicable to referring expression comprehension in images, illustrated by the improved performance on the RefCOCO dataset. Our project is available at https://sijiesong.github.io/co-grounding., Comment: Accepted to CVPR2021. The project page is at https://sijiesong.github.io/co-grounding

In this paper, we address self-supervised representation learning from human skeletons for action recognition. Previous methods, which usually learn feature presentations from a single reconstruction task, may come across the overfitting problem, and the features are not generalizable for action recognition. Instead, we propose to integrate multiple tasks to learn more general representations in a self-supervised manner. To realize this goal, we integrate motion prediction, jigsaw puzzle recognition, and contrastive learning to learn skeleton features from different aspects. Skeleton dynamics can be modeled through motion prediction by predicting the future sequence. And temporal patterns, which are critical for action recognition, are learned through solving jigsaw puzzles. We further regularize the feature space by contrastive learning. Besides, we explore different training strategies to utilize the knowledge from self-supervised tasks for action recognition. We evaluate our multi-task self-supervised learning approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Our experiments on the NW-UCLA, NTU RGB+D, and PKUMMD datasets show remarkable performance for action recognition, demonstrating the superiority of our method in learning more discriminative and general features. Our project website is available at https://langlandslin.github.io/projects/MSL/., Accepted by ACMMM 2020

In this paper, we tackle the problem of pose-guided person image generation with unpaired data, which is a challenging problem due to non-rigid spatial deformation. Instead of learning a fixed mapping directly between human bodies as previous methods, we propose a new pathway to decompose a single fixed mapping into two subtasks, namely, semantic parsing transformation and appearance generation. First, to simplify the learning for non-rigid deformation, a semantic generative network is developed to transform semantic parsing maps between different poses. Second, guided by semantic parsing maps, we render the foreground and background image, respectively. A foreground generative network learns to synthesize semantic-aware textures, and another background generative network learns to predict missing background regions caused by pose changes. Third, we enable pseudo-label training with unpaired data, and demonstrate that end-to-end training of the overall network further refines the semantic map prediction and final results accordingly. Moreover, our method is generalizable to other person image generation tasks defined on semantic maps, e.g., clothing texture transfer, controlled image manipulation, and virtual try-on. Experimental results on DeepFashion and Market-1501 datasets demonstrate the superiority of our method, especially in keeping better body shapes and clothing attributes, as well as rendering structure-coherent backgrounds.

Human action analytics has attracted a lot of attention for decades in computer vision. It is important to extract discriminative spatio-temporal features to model the spatial and temporal evolutions of different actions. In this paper, we propose a spatial and temporal attention model to explore the spatial and temporal discriminative features for human action recognition and detection from skeleton data. We build our networks based on the recurrent neural networks with long short-term memory units. The learned model is capable of selectively focusing on discriminative joints of skeletons within each input frame and paying different levels of attention to the outputs of different frames. To ensure effective training of the network for action recognition, we propose a regularized cross-entropy loss to drive the learning process and develop a joint training strategy accordingly. Moreover, based on temporal attention, we develop a method to generate the action temporal proposals for action detection. We evaluate the proposed method on the SBU Kinect Interaction data set, the NTU RGB + D data set, and the PKU-MMD data set, respectively. Experiment results demonstrate the effectiveness of our proposed model on both action recognition and action detection.

Temporal modeling in videos is a fundamental yet challenging problem in computer vision. In this paper, we propose a novel Temporal Bilinear (TB) model to capture the temporal pairwise feature interactions between adjacent frames. Compared with some existing temporal methods which are limited in linear transformations, our TB model considers explicit quadratic bilinear transformations in the temporal domain for motion evolution and sequential relation modeling. We further leverage the factorized bilinear model in linear complexity and a bottleneck network design to build our TB blocks, which also constrains the parameters and computation cost. We consider two schemes in terms of the incorporation of TB blocks and the original 2D spatial convolutions, namely wide and deep Temporal Bilinear Networks (TBN). Finally, we perform experiments on several widely adopted datasets including Kinetics, UCF101 and HMDB51. The effectiveness of our TBNs is validated by comprehensive ablation analyses and comparisons with various state-of-the-art methods., Accepted by AAAI 2019

This paper presents a new framework for action recognition with multi-modal data. A skeleton-indexed feature learning procedure is developed to further exploit the detailed local features from RGB and optical flow videos. In particular, the proposed framework is built based on a deep Convolutional Network (ConvNet) and a Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM). A skeleton-indexed transform layer is designed to automatically extract visual features around key joints, and a part-aggregated pooling is developed to uniformly regulate the visual features from different body parts and actors. Besides, several fusion schemes are explored to take advantage of multi-modal data. The proposed deep architecture is end-to-end trainable and can better incorporate different modalities to learn effective feature representations. Quantitative experiment results on two datasets, the NTU RGB+D dataset and the MSR dataset, demonstrate the excellent performance of our scheme over other state-of-the-arts. To our knowledge, the performance obtained by the proposed framework is currently the best on the challenging NTU RGB+D dataset.

Background Bilirubin-induced neurological dysfunction (BIND), a severe complication of extreme neonatal hyperbilirubinemia, could develop into permanent neurodevelopmental impairments. Several studies have demonstrated that inflammation and nerve cell death play important roles in bilirubin-induced neurotoxicity; however, the underlying mechanism remains unidentified. Methods The present study was intended to investigate whether pyroptosis, a highly inflammatory form of programmed cell death, participated in the bilirubin-mediated toxicity on cultured rat cortical astrocytes. Further, VX-765, a potent and selective competitive drug, was used to inhibit the activation of caspase-1. The effects of VX-765 on astrocytes treated with bilirubin, including the cell viability, morphological changes of the cell membrane and nucleus, and the production of pro-inflammation cytokines, were observed. Results Stimulation of the astrocytes with unconjugated bilirubin (UCB) at the conditions mimicking those of jaundiced newborns significantly increased the activation of caspase-1. Further, caspase-1 activation was inhibited by treatment with VX-765. Compared with UCB-treated astrocytes, the relative cell viability of VX-765-pretreated astrocytes was improved; meanwhile, the formation of plasma membrane pores was prevented, as measured by lactate dehydrogenase release, trypan blue staining, and ethidium bromide (EtBr) uptake. Moreover, DNA fragmentation was partly attenuated and the release of IL-1β and IL-18 was apparently decreased. Conclusion Pyroptosis is involved in the process of UCB-induced rat cortical astrocytes’ injury in vitro and may be the missing link of cell death and inflammatory response exacerbating UCB-related neurotoxicity. More importantly, the depression of caspase-1 activation, the core link of pyroptosis, attenuated UCB-induced cellular dysfunction and cytokine release, which might shed light on a new therapeutic approach to BIND.