Search

A systematic comparison of fiber-based gas pressure sensors using different types of hollow-core photonic crystal fibers (PCFs) is conducted. The sensor was fabricated by splicing a segment of hollow-core silica capillary between a single mode fiber (SMF) and a hollow-core PCF. A Fabry-Perot (FP) cavity configuration is thus formed with the capillary tube as the sensing cavity, while the PCF acts as gas passage to the external environment. External pressure change would lead to the variation in the refractive index of air in the sensing cavity, resulting in a wavelength shift of the interference dips. The pressure sensitivity is measured to be around 4 nm/MPa, with a high linearity of 99.7% or above, regardless of the type of the PCFs we used as gas inlet. Among the four different PCFs, the large-mode-area (LMA) PCF shows the highest fringe contrast in the reflection spectrum. Modal analysis reveals that this is due to the high reflectivity caused by the solid core of LMA-PCF. Our experimental results also indicate that the length of the sensing cavity, as well as the offset fusion splice will influence the fringe contrast. The sensor has potential application in gas pressure sensing for advantages of high sensitivity, compact size and ease of fabrication.

High protein diet reduces food intake and improves glucose homeostasis in rodents and humans with obesity and diabetes, but the mechanistic site (s) of action remain unclear. Small intestinal lipid and glucose sensing regulates energy and glucose homeostasis, but the metabolic role of gut protein sensing remains elusive. In this study, we infused 8% casein hydrolysate as protein source into the upper small intestine (USI) and performed fasting-refeeding studies. We found that USI casein infusion (1.28 kcal/min) suppressed food intake up to 6h in chow but not high fat (HF) - fed rats (chow USI: sal 47±2 vs. cas 36±2 kcal, n=18, p In summary, these data illustrate that USI protein sensing increases glucose tolerance in chow and HF rats via CaSR, and lowers feeding in chow but not HF rats. Future studies are needed to dissect the metabolic role of CaSR not only for USI but also ileal protein sensing in energy balance and glucose homeostasis in obesity and diabetes. Disclosure R.J.W.Li: None. D.Barros: None. Y.Lim: None. S.Zhang: None. A.Gao: None. T.K.Lam: None.

Three-dimensional (3D) point clouds are important data representations in visualization applications. The rapidly growing utility and popularity of point cloud processing strongly motivate a plethora of research activities on large-scale point cloud processing and feature extraction. In this work, we investigate point cloud resampling based on hypergraph signal processing (HGSP). We develop a novel method to extract sharp object features and reduce the data size of point cloud representation. By directly estimating hypergraph spectrum based on hypergraph stationary processing, we design a spectral kernel-based filter to capture high-dimensional interactions among point signal nodes and to better preserve object surface outlines. Experimental results validate the effectiveness of hypergraph in representing point clouds, and demonstrate the robustness of the proposed algorithm under noise.

Efficient processing and feature extraction of large-scale point clouds are important in related computer vision and cyber-physical systems. This work investigates point cloud resampling based on hypergraph signal processing (HGSP) to better explore the underlying relationship among different points in the point cloud and to extract contour-enhanced features. Specifically, we design hypergraph spectral filters to capture multilateral interactions among the signal nodes of point clouds and to better preserve their surface outlines. Without the need and the computation to first construct the underlying hypergraph, our low complexity approach directly estimates hypergraph spectrum of point clouds by leveraging hypergraph stationary processes from the observed 3D coordinates. Evaluating the proposed resampling methods with several metrics, our test results validate the high efficacy of hypergraph characterization of point clouds and demonstrate the robustness of hypergraph-based resampling under noisy observations.

Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG datasets, i.e., they always assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-annotated negative samples are absolutely background. In this paper, we argue that both assumptions are inapplicable to SGG: there are numerous "noisy" groundtruth predicate labels that break these two assumptions, and these noisy samples actually harm the training of unbiased SGG models. To this end, we propose a novel model-agnostic NoIsy label CorrEction strategy for SGG: NICE. NICE can not only detect noisy samples but also reassign more high-quality predicate labels to them. After the NICE training, we can obtain a cleaner version of SGG dataset for model training. Specifically, NICE consists of three components: negative Noisy Sample Detection (Neg-NSD), positive NSD (Pos-NSD), and Noisy Sample Correction (NSC). Firstly, in Neg-NSD, we formulate this task as an out-of-distribution detection problem, and assign pseudo labels to all detected noisy negative samples. Then, in Pos-NSD, we use a clustering-based algorithm to divide all positive samples into multiple sets, and treat the samples in the noisiest set as noisy positive samples. Lastly, in NSC, we use a simple but effective weighted KNN to reassign new predicate labels to noisy positive samples. Extensive results on different backbones and tasks have attested to the effectiveness and generalization abilities of each component of NICE., Comment: Accepted by CVPR 2022

Outdoor radio map estimation is an important tool for network planning and resource management in modern Internet of Things (IoT) and cellular systems. Radio map describes spatial signal strength distribution and provides network coverage information. A practical goal is to estimate fine-resolution radio maps from sparse radio strength measurements. However, non-uniformly positioned measurements and access obstacles can make it difficult for accurate radio map estimation (RME) and spectrum planning in many outdoor environments. In this work, we develop a two-phase learning framework for radio map estimation by integrating radio propagation model and designing a conditional generative adversarial network (cGAN). We first explore global information to extract the radio propagation patterns. We then focus on the local features to estimate the effect of shadowing on radio maps in order to train and optimize the cGAN. Our experimental results demonstrate the efficacy of the proposed framework for radio map estimation based on generative models from sparse observations in outdoor scenarios.

The revolution of artificial intelligence (AI) is transforming major industries worldwide. With accurate inferencing, AI has caught the attention of many engineers and scientists. Promisingly, hardware-in the-loop (HIL) emulation can adopt this type of modeling method as one of the alternatives after comprehensive investigation. This paper proposes an approach for emulating power electronic motor drive transients for advanced transportation applications (ATAs) using machine learning building blocks (MLBBs) without any traditional circuit-oriented transient solver. The more electric aircraft (MEA) power system is chosen as a case study to validate the real-time emulation performance of MLBBs. Inside MLBBs, neural networks (NNs) have been applied to build component-level, device-level, and system-level models for various equipment. These models are well trained in a cluster and transplanted into the field-programmable gate array (FPGA) based hardware platform. Finally, MLBB emulation results are compared with PSCAD/EMTDC for system-level and SaberRD for device-level, which showed high consistency for model accuracy and high speed-up for hardware execution.

YouTube, a world-famous video sharing website, maintains a list of the top trending videos on the platform. Due to its huge amount of users, it enables researchers to understand people's preference by analyzing the trending videos. Trending videos vary from country to country. By analyzing such differences and changes, we can tell how users' preferences differ over locations. Previous work focuses on analyzing such culture preferences from videos' metadata, while the culture information hidden within the visual content has not been discovered. In this study, we explore culture preferences among countries using the thumbnails of YouTube trending videos. We first process the thumbnail images of the videos using object detectors. The collected object information is then used for various statistical analysis. In particular, we examine the data from three perspectives: geographical locations, video genres and users' reactions. Experimental results indicate that the users from similar cultures shares interests in watching similar videos on YouTube. Our study demonstrates that discovering the culture preference through the thumbnails can be an effective mechanism for video social media analysis.

Glioma stem-like cells (GSCs) are a subset of tumor cells that initiate malignant growth and promote the therapeutic resistance of glioblastoma, the most lethal primary brain tumor. Ribosome biogenesis is an essential cellular process to maintain cell growth, but its regulatory mechanism in GSCs remains largely unknown. Here, we show that WD repeat domain 12 (WDR12), a component of the Pes1-Bop1 complex (PeBoW), is required for ribosome biogenesis in GSCs. WDR12 is preferentially expressed in GSCs compared to non-stem tumor cells and normal brain cells. High levels of WDR12 are associated with glioblastoma progression and poor prognosis. Silencing WDR12 results in the degradation of PeBoW complex components and prevents the maturation of 28S rRNA, thereby inhibiting ribosome biogenesis in GSCs. Subsequently, WDR12 depletion compromises GSC proliferation, inhibits GSC-derived orthotopic tumor growth, and extends animal survival. Together, our results suggest that WDR12 is crucial for ribosome biogenesis in GSCs, and is thus a potential target for GSC-directed therapy of glioblastoma.

We address the problem of retrieving a specific moment from an untrimmed video by natural language. It is a challenging problem because a target moment may take place in the context of other temporal moments in the untrimmed video. Existing methods cannot tackle this challenge well since they do not fully consider the temporal contexts between temporal moments. In this paper, we model the temporal context between video moments by a set of predefined two-dimensional maps under different temporal scales. For each map, one dimension indicates the starting time of a moment and the other indicates the duration. These 2D temporal maps can cover diverse video moments with different lengths, while representing their adjacent contexts at different temporal scales. Based on the 2D temporal maps, we propose a Multi-Scale Temporal Adjacency Network (MS-2D-TAN), a single-shot framework for moment localization. It is capable of encoding the adjacent temporal contexts at each scale, while learning discriminative features for matching video moments with referring expressions. We evaluate the proposed MS-2D-TAN on three challenging benchmarks, i.e., Charades-STA, ActivityNet Captions, and TACoS, where our MS-2D-TAN outperforms the state of the art.

Interpreting model knowledge is an essential topic to improve human understanding of deep black-box models. Traditional methods contribute to providing intuitive instance-wise explanations which allocating importance scores for low-level features (e.g, pixels for images). To adapt to the human way of thinking, one strand of recent researches has shifted its spotlight to mining important concepts. However, these concept-based interpretation methods focus on computing the contribution of each discovered concept on the class level and can not precisely give instance-wise explanations. Besides, they consider each concept as an independent unit, and ignore the interactions among concepts. To this end, in this paper, we propose a novel COncept-based NEighbor Shapley approach (dubbed as CONE-SHAP) to evaluate the importance of each concept by considering its physical and semantic neighbors, and interpret model knowledge with both instance-wise and class-wise explanations. Thanks to this design, the interactions among concepts in the same image are fully considered. Meanwhile, the computational complexity of Shapley Value is reduced from exponential to polynomial. Moreover, for a more comprehensive evaluation, we further propose three criteria to quantify the rationality of the allocated contributions for the concepts, including coherency, complexity, and faithfulness. Extensive experiments and ablations have demonstrated that our CONE-SHAP algorithm outperforms existing concept-based methods and simultaneously provides precise explanations for each instance and class.

Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective context encoding module to incorporate spatial and feature channel context, resulting in better modeling of intra-class variations. To train our model, we develop a multi-task loss for learning video matching, leading to video features with better generalization. Extensive experimental results on two challenging benchmarks, show that our method outperforms the prior arts with a sizable margin on Something-Something-V2 and competitive results on Kinetics.

Low levels of reactive oxygen species (ROS) are crucial for maintaining cancer stem cells (CSCs) and their ability to resist therapy, but the ROS regulatory mechanisms in CSCs remains to be explored. Here, we discover that prohibitin (PHB) specifically regulates mitochondrial ROS production in glioma stem-like cells (GSCs) and facilitates GSC radiotherapeutic resistance. We find that PHB is upregulated in GSCs and is associated with malignant gliomas progression and poor prognosis. PHB binds to peroxiredoxin3 (PRDX3), a mitochondrion-specific peroxidase, and stabilizes PRDX3 protein through the ubiquitin-proteasome pathway. Knockout of PHB dramatically elevates ROS levels, thereby inhibiting GSC self-renewal. Importantly, deletion or pharmacological inhibition of PHB potently slows tumor growth and sensitizes tumors to radiotherapy, thus providing significant survival benefits in GSC-derived orthotopic tumors and glioblastoma patient-derived xenografts. These results reveal a selective role of PHB in mitochondrial ROS regulation in GSCs and suggest that targeting PHB improves radiotherapeutic efficacy in glioblastoma., How ROS levels are regulated in cancer stem cells and their contribution to cancer resistance is currently not clear. Here, the authors show that prohibitin regulates mitochondrial ROS production stabilizing the peroxidase PRDX3 and this accounts for radiotherapy resistance in glioma stem-like cells.

3D visual grounding aims at grounding a natural language description about a 3D scene, usually represented in the form of 3D point clouds, to the targeted object region. Point clouds are sparse, noisy, and contain limited semantic information compared with 2D images. These inherent limitations make the 3D visual grounding problem more challenging. In this study, we propose 2D Semantics Assisted Training (SAT) that utilizes 2D image semantics in the training stage to ease point-cloud-language joint representation learning and assist 3D visual grounding. The main idea is to learn auxiliary alignments between rich, clean 2D object representations and the corresponding objects or mentioned entities in 3D scenes. SAT takes 2D object semantics, i.e., object label, image feature, and 2D geometric feature, as the extra input in training but does not require such inputs during inference. By effectively utilizing 2D semantics in training, our approach boosts the accuracy on the Nr3D dataset from 37.7% to 49.2%, which significantly surpasses the non-SAT baseline with the identical network architecture and inference input. Our approach outperforms the state of the art by large margins on multiple 3D visual grounding datasets, i.e., +10.4% absolute accuracy on Nr3D, +9.9% on Sr3D, and +5.6% on ScanRef., ICCV 2021 Oral

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the two-stage learning framework via ablative study. Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition. Specifically, we develop an adaptive calibration function that enables us to adjust the classification scores for each data point. We then introduce a generalized re-weight method in the two-stage learning to balance the class prior, which provides a flexible and unified solution to diverse scenarios in visual recognition tasks. We validate our method by extensive experiments on four tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Our approach achieves the state-of-the-art results across all four recognition tasks with a simple and unified framework. The code and models will be made publicly available at: https://github.com/Megvii-BaseDetection/DisAlign, Accepted by CVPR 2021

We aim to address the problem of Natural Language Video Localization (NLVL)-localizing the video segment corresponding to a natural language description in a long and untrimmed video. State-of-the-art NLVL methods are almost in one-stage fashion, which can be typically grouped into two categories: 1) anchor-based approach: it first pre-defines a series of video segment candidates (e.g., by sliding window), and then does classification for each candidate; 2) anchor-free approach: it directly predicts the probabilities for each video frame as a boundary or intermediate frame inside the positive segment. However, both kinds of one-stage approaches have inherent drawbacks: the anchor-based approach is susceptible to the heuristic rules, further limiting the capability of handling videos with variant length. While the anchor-free approach fails to exploit the segment-level interaction thus achieving inferior results. In this paper, we propose a novel Boundary Proposal Network (BPNet), a universal two-stage framework that gets rid of the issues mentioned above. Specifically, in the first stage, BPNet utilizes an anchor-free model to generate a group of high-quality candidate video segments with their boundaries. In the second stage, a visual-language fusion layer is proposed to jointly model the multi-modal interaction between the candidate and the language query, followed by a matching score rating layer that outputs the alignment score for each candidate. We evaluate our BPNet on three challenging NLVL benchmarks (i.e., Charades-STA, TACoS and ActivityNet-Captions). Extensive experiments and ablative studies on these datasets demonstrate that the BPNet outperforms the state-of-the-art methods., AAAI 2021

Transferring the sentiment of an image is an unexplored research topic in the area of computer vision. This work proposes a novel framework consisting of a reference image retrieval step and a global sentiment transfer step to transfer sentiments of images according to a given sentiment tag. The proposed image retrieval algorithm is based on the SSIM index. The retrieved reference images by the proposed algorithm are more content-related against the algorithm based on the perceptual loss. Therefore can lead to a better image sentiment transfer result. In addition, we propose a global sentiment transfer step, which employs an optimization algorithm to iteratively transfer sentiment of images based on feature maps produced by the Densenet121 architecture. The proposed sentiment transfer algorithm can transfer the sentiment of images while ensuring the content structure of the input image intact. The qualitative and quantitative experiments demonstrate that the proposed sentiment transfer framework outperforms existing artistic and photorealistic style transfer algorithms in making reliable sentiment transfer results with rich and exact details.

Scene graph generation is an important visual understanding task with a broad range of vision applications. Despite recent tremendous progress, it remains challenging due to the intrinsic long-tailed class distribution and large intra-class variation. To address these issues, we introduce a novel confidence-aware bipartite graph neural network with adaptive message propagation mechanism for unbiased scene graph generation. In addition, we propose an efficient bi-level data resampling strategy to alleviate the imbalanced data distribution problem in training our graph network. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including Visual Genome, Open Images V4/V6, demonstrating its effectiveness and generality., Comment: Accepted by CVPR2021

Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation task, mainly due to its continuously-evolving semantic label space, partial pixelwise ground-truth annotations, and constrained data availability. To ad- dress this, we propose an incremental learning strategy that can fast adapt deep segmentation models without catastrophic forgetting, using a streaming input data with pixel annotations on the novel classes only. To this end, we develop a uni ed learning strategy based on the Expectation-Maximization (EM) framework, which integrates an iterative relabeling strategy that lls in the missing labels and a rehearsal-based incremental learning step that balances the stability-plasticity of the model. Moreover, our EM algorithm adopts an adaptive sampling method to select informative train- ing data and a class-balancing training strategy in the incremental model updates, both improving the e cacy of model learning. We validate our approach on the PASCAL VOC 2012 and ADE20K datasets, and the results demonstrate its superior performance over the existing incremental methods., Comment: Accepted by ACM MM'21

Along with increasingly popular virtual reality applications, the three-dimensional (3D) point cloud has become a fundamental data structure to characterize 3D objects and surroundings. To process 3D point clouds efficiently, a suitable model for the underlying structure and outlier noises is always critical. In this work, we propose a hypergraph-based new point cloud model that is amenable to efficient analysis and processing. We introduce tensor-based methods to estimate hypergraph spectrum components and frequency coefficients of point clouds in both ideal and noisy settings. We establish an analytical connection between hypergraph frequencies and structural features. We further evaluate the efficacy of hypergraph spectrum estimation in two common applications of sampling and denoising of point clouds for which we provide specific hypergraph filter design and spectral properties. Experimental results demonstrate the strength of hypergraph signal processing as a tool in characterizing the underlying properties of 3D point clouds.

Short-form video social media shifts away from the traditional media paradigm by telling the audience a dynamic story to attract their attention. In particular, different combinations of everyday objects can be employed to represent a unique scene that is both interesting and understandable. Offered by the same company, TikTok and Douyin are popular examples of such new media that has become popular in recent years, while being tailored for different markets (e.g. the United States and China). The hypothesis that they express cultural differences together with media fashion and social idiosyncrasy is the primary target of our research. To that end, we first employ the Faster Regional Convolutional Neural Network (Faster R-CNN) pre-trained with the Microsoft Common Objects in COntext (MS-COCO) dataset to perform object detection. Based on a suite of objects detected from videos, we perform statistical analysis including label statistics, label similarity, and label-person distribution. We further use the Two-Stream Inflated 3D ConvNet (I3D) pre-trained with the Kinetics dataset to categorize and analyze human actions. By comparing the distributional results of TikTok and Douyin, we uncover a wealth of similarity and contrast between the two closely related video social media platforms along the content dimensions of object quantity, object categories, and human action categories., Accepted by IEEE Big Data 2020

Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually generate the sequence results token by token from left to right, leaving the right-to-left contexts unexploited. In this work, we introduce a bidirectional speech transformer to utilize the different directional contexts simultaneously. Specifically, the outputs of our proposed transformer include a left-to-right target, and a right-to-left target. In inference stage, we use the introduced bidirectional beam search method, which can not only generate left-to-right candidates but also generate right-to-left candidates, and determine the best hypothesis by the score. To demonstrate our proposed speech transformer with a bidirectional decoder(STBD), we conduct extensive experiments on the AISHELL-1 dataset. The results of experiments show that STBD achieves a 3.6\% relative CER reduction(CERR) over the unidirectional speech transformer baseline. Besides, the strongest model in this paper called STBD-Big can achieve 6.64\% CER on the test set, without language model rescoring and any extra data augmentation strategies., Comment: Accepted by InterSpeech 2020

Zhan et al. reveal that glioma stem-like cells (GSCs) evade type I IFN suppression through MBD3/NuRD complex–mediated STAT1 downregulation, thereby allowing GSCs to initiate a tumor in the inhospitable microenvironment in glioblastoma (GBM)., Type I interferons (IFNs) are known to mediate antineoplastic effects during tumor progression. Type I IFNs can be produced by multiple cell types in the tumor microenvironment; however, the molecular mechanisms by which tumor cells evade the inhibition of immune microenvironment remain unknown. Here we demonstrate that glioma stem-like cells (GSCs) evade type I IFN suppression through downregulation of STAT1 to initiate tumor growth under inhospitable conditions. The downregulation of STAT1 is mediated by MBD3, an epigenetic regulator. MBD3 is preferentially expressed in GSCs and recruits NuRD complex to STAT1 promoter to suppress STAT1 expression by histone deacetylation. Importantly, STAT1 overexpression or MBD3 depletion induces p21 transcription, resensitizes GSCs to IFN suppression, attenuates GSC tumor growth, and prolongs animal survival. Our findings demonstrate that inactivation of STAT1 signaling by MBD3/NuRD provides GSCs with a survival advantage to escape type I IFN suppression, suggesting that targeting MBD3 may represent a promising therapeutic opportunity to compromise GSC tumorigenic potential., Graphical Abstract

Background: Wilms tumor is the most common pediatric renal cancer. However, genetic bases behind Wilms tumor remain largely unknown. H19 is a critical maternally imprinted gene. Previous studies indicated that Single nucleotide polymorphisms (SNPs) in the H19 can modify the risk of several human malignancies. Epigenetic errors at the H19 locus lead to biallele silencing in Wilms tumors. Genetic variations in the H19 may be related to Wilms tumor susceptibility.Methods: We conducted a four-center study to investigate whether H19 SNPs was a predisposing factor to Wilms tumor. Three polymorphisms in the H19 (rs2839698 G>A, rs3024270 C>G, rs217727 G>A) were genotyped in 355 cases and 1070 cancer-free controls,using Taqman method. Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated to evaluate the strength of the associations.Results: We found that all of these three polymorphisms were significantly associated with Wilms tumor risk alterations. Carriers of 1, 2 and 1-2 risk genotypes were inclined to develop Wilms tumor compared with those without risk genotype [adjusted odds ratio (OR)=1.36, 95% confidence interval (CI)=1.02-1.80, P =0.037; adjusted OR=1.84, 95% CI=1.27-2.67, P =0.001; adjusted OR=1.50, 95% CI=1.17-1.92, P =0.002, respectively]. The stratified analysis further revealed that rs2839698 AA, rs217727 AA, and 1-2 risk genotypes could strongly increase Wilms tumor risk among children above 18 months of age, males, and with clinical stage I+II disease.Conclusion: Our findings indicate that genetic variations in the H19 may confer Wilms tumor risk.

Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive setting of one-way few-shot segmentation or suffer from incomplete coverage of object regions. In this paper, we propose a novel few-shot semantic segmentation framework based on the prototype representation. Our key idea is to decompose the holistic class representation into a set of part-aware prototypes, capable of capturing diverse and fine-grained object features. In addition, we propose to leverage unlabeled data to enrich our part-aware prototypes, resulting in better modeling of intra-class variations of semantic objects. We develop a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images. Extensive experimental evaluations on two benchmarks show that our method outperforms the prior art with a sizable margin (Code is available at: https://github.com/Xiangyi1996/PPNet-PyTorch).

We address the problem of retrieving a specific moment from an untrimmed video by a query sentence. This is a challenging problem because a target moment may take place in relations to other temporal moments in the untrimmed video. Existing methods cannot tackle this challenge well since they consider temporal moments individually and neglect the temporal dependencies. In this paper, we model the temporal relations between video moments by a two-dimensional map, where one dimension indicates the starting time of a moment and the other indicates the end time. This 2D temporal map can cover diverse video moments with different lengths, while representing their adjacent relations. Based on the 2D map, we propose a Temporal Adjacent Network (2D-TAN), a single-shot framework for moment localization. It is capable of encoding the adjacent temporal relation, while learning discriminative features for matching video moments with referring expressions. We evaluate the proposed 2D-TAN on three challenging benchmarks, i.e., Charades-STA, ActivityNet Captions, and TACoS, where our 2D-TAN outperforms the state-of-the-art., This paper is accepted by AAAI 2020

Background: Obesity plays crucial roles in the development of cardiovascular diseases. However, the mechanisms that link obesity and cardiovascular diseases remain elusive. Compelling evidence indicates that adipokines play an important role in obesity-related cardiovascular diseases. Here, we found a new adipokine-named family with sequence similarity 19, member A5 (FAM19A5), a protein with unknown function that was predicted to be distantly related to the CC-chemokine family. We aimed to test whether adipose-derived FAM19A5 regulates vascular pathology on injury. Methods: DNA cloning, protein expression, purification, and N-terminal sequencing were applied to characterize FAM19A5. Adenovirus infection and siRNA transfection were performed to regulate FAM19A5 expression. Balloon and wire injury were performed in vivo on the rat carotid arteries and mouse femoral arteries, respectively. Bioinformatics analysis, radioactive ligand-receptor binding assays, receptor internalization, and calcium mobilization assays were used to identify the functional receptor for FAM19A5. Results: We first characterized FAM19A5 as a secreted protein, and the first 43 N-terminal amino acids were the signal peptides. Both FAM19A5 mRNA and protein were abundantly expressed in the adipose tissue but were downregulated in obese mice. Overexpression of FAM19A5 markedly inhibited vascular smooth muscle cell proliferation and migration and neointima formation in the carotid arteries of balloon-injured rats. Accordingly, FAM19A5 silencing in adipocytes significantly promoted vascular smooth muscle cell activation. Adipose-specific FAM19A5 transgenic mice showed greater attenuation of neointima formation compared with wild-type littermates fed with or without Western-style diet. We further revealed that sphingosine-1-phosphate receptor 2 was the functional receptor for FAM19A5, with a dissociation constant ( K d ) of 0.634 nmol/L. Inhibition of sphingosine-1-phosphate receptor 2 or its downstream G12/13-RhoA signaling circumvented the suppressive effects of FAM19A5 on vascular smooth muscle cell proliferation and migration. Conclusions: We revealed that a novel adipokine, FAM19A5, was capable of inhibiting postinjury neointima formation via sphingosine-1-phosphate receptor 2-G12/13-RhoA signaling. Downregulation of FAM19A5 during obesity may trigger cardiometabolic diseases.