scholarly journals 3D Human Pose Estimation via Explicit Compositional Depth Maps

2020 ◽  
Vol 34 (07) ◽  
pp. 12378-12385
Author(s):  
Haiping Wu ◽  
Bin Xiao
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Superior Performance ◽  
Projection Model ◽  
Depth Maps ◽  
3D Camera ◽  
Camera Perspective ◽  
Monocular Image ◽  
Human Pose ◽  
Body Joints

In this work, we tackle the problem of estimating 3D human pose in camera space from a monocular image. First, we propose to use densely-generated limb depth maps to ease the learning of body joints depth, which are well aligned with image cues. Then, we design a lifting module from 2D pixel coordinates to 3D camera coordinates which explicitly takes the depth values as inputs, and is aligned with camera perspective projection model. We show our method achieves superior performance on large-scale 3D pose datasets Human3.6M and MPI-INF-3DHP, and sets the new state-of-the-art.

scholarly journals CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-7 ◽  
Author(s):  
Aboubakar Nasser Samatin Njikam ◽  
Huan Zhao
Keyword(s):  
Text Classification ◽  
Building Block ◽  
Large Scale ◽  
State Of The Art ◽  
Building Blocks ◽  
Training Data ◽  
Superior Performance ◽  
Classification Problems ◽  
Computationally Efficient ◽  
Convolutional Network

This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte.

scholarly journals Discriminative Deep Hashing for Scalable Face Image Retrieval

2017 ◽  
Author(s):  
Jie Lin ◽  
Zechao Li ◽  
Jinhui Tang
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
State Of The Art ◽  
Face Image ◽  
Superior Performance ◽  
Prediction Errors ◽  
Unified Framework ◽  
Multi Scale ◽  
Deep Hashing ◽  
Hash Codes

With the explosive growth of images containing faces, scalable face image retrieval has attracted increasing attention. Due to the amazing effectiveness, deep hashing has become a popular hashing method recently. In this work, we propose a new Discriminative Deep Hashing (DDH) network to learn discriminative and compact hash codes for large-scale face image retrieval. The proposed network incorporates the end-to-end learning, the divide-and-encode module and the desired discrete code learning into a unified framework. Specifically, a network with a stack of convolution-pooling layers is proposed to extract multi-scale and robust features by merging the outputs of the third max pooling layer and the fourth convolutional layer. To reduce the redundancy among hash codes and the network parameters simultaneously, a divide-and-encode module to generate compact hash codes. Moreover, a loss function is introduced to minimize the prediction errors of the learned hash codes, which can lead to discriminative hash codes. Extensive experiments on two datasets demonstrate that the proposed method achieves superior performance compared with some state-of-the-art hashing methods.

scholarly journals 3D SURFACE RECONSTRUCTION FROM MULTI-DATE SATELLITE IMAGES

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 313-320
Author(s):  
S. Bullinger ◽  
C. Bodensteiner ◽  
M. Arens
Keyword(s):  
Large Scale ◽  
Satellite Images ◽  
Stereo Matching ◽  
State Of The Art ◽  
Satellite Image ◽  
Three Dimensional ◽  
Point Clouds ◽  
Reconstruction Algorithms ◽  
Depth Maps ◽  
Median Error

Abstract. The reconstruction of accurate three-dimensional environment models is one of the most fundamental goals in the field of photogrammetry. Since satellite images provide suitable properties for obtaining large-scale environment reconstructions, there exist a variety of Stereo Matching based methods to reconstruct point clouds for satellite image pairs. Recently, a Structure from Motion (SfM) based approach has been proposed, which allows to reconstruct point clouds from multiple satellite images. In this work, we propose an extension of this SfM based pipeline that allows us to reconstruct not only point clouds but watertight meshes including texture information. We provide a detailed description of several steps that are mandatory to exploit state-of-the-art mesh reconstruction algorithms in the context of satellite imagery. This includes a decomposition of finite projective camera calibration matrices, a skew correction of corresponding depth maps and input images as well as the recovery of real-world depth maps from reparameterized depth values. The paper presents an extensive quantitative evaluation on multi-date satellite images demonstrating that the proposed pipeline combined with current meshing algorithms outperforms state-of-the-art point cloud reconstruction algorithms in terms of completeness and median error. We make the source code of our pipeline publicly available.

scholarly journals Rethinking the Fourier-Mellin Transform: Multiple Depths in the Camera’s View

2021 ◽  
Vol 13 (5) ◽  
pp. 1000
Author(s):  
Qingwen Xu ◽  
Haofei Kuang ◽  
Laurent Kneip ◽  
Sören Schwertfeger
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
Feature Detection ◽  
Mellin Transform ◽  
State Of The Art ◽  
Visual Odometry ◽  
Superior Performance ◽  
Fourier Mellin Transform ◽  
And Robotics ◽  
Better Than

Remote sensing and robotics often rely on visual odometry (VO) for localization. Many standard approaches for VO use feature detection. However, these methods will meet challenges if the environments are feature-deprived or highly repetitive. Fourier-Mellin Transform (FMT) is an alternative VO approach that has been shown to show superior performance in these scenarios and is often used in remote sensing. One limitation of FMT is that it requires an environment that is equidistant to the camera, i.e., single-depth. To extend the applications of FMT to multi-depth environments, this paper presents the extended Fourier-Mellin Transform (eFMT), which maintains the advantages of FMT with respect to feature-deprived scenarios. To show the robustness and accuracy of eFMT, we implement an eFMT-based visual odometry framework and test it in toy examples and a large-scale drone dataset. All these experiments are performed on data collected in challenging scenarios, such as, trees, wooden boards and featureless roofs. The results show that eFMT performs better than FMT in the multi-depth settings. Moreover, eFMT also outperforms state-of-the-art VO algorithms, such as ORB-SLAM3, SVO and DSO, in our experiments.

scholarly journals Large-Scale Visual Relationship Understanding

2019 ◽  
Vol 33 ◽  
pp. 9185-9194 ◽  
Author(s):  
Ji Zhang ◽  
Yannis Kalantidis ◽  
Marcus Rohrbach ◽  
Manohar Paluri ◽  
Ahmed Elgammal ◽  
...  
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Scale Up ◽  
Superior Performance ◽  
Matched Pairs ◽  
Detection Model ◽  
Large Numbers ◽  
Shared Space ◽  
Visual Understanding ◽  
Genome Dataset

Large scale visual understanding is challenging, as it requires a model to handle the widely-spread and imbalanced distribution of 〈subject, relation, object〉 triples. In real-world scenarios with large numbers of objects and relations, some are seen very commonly while others are barely seen. We develop a new relationship detection model that embeds objects and relations into two vector spaces where both discriminative capability and semantic affinity are preserved. We learn a visual and a semantic module that map features from the two modalities into a shared space, where matched pairs of features have to discriminate against those unmatched, but also maintain close distances to semantically similar ones. Benefiting from that, our model can achieve superior performance even when the visual entity categories scale up to more than 80,000, with extremely skewed class distribution. We demonstrate the efficacy of our model on a large and imbalanced benchmark based of Visual Genome that comprises 53,000+ objects and 29,000+ relations, a scale at which no previous work has been evaluated at. We show superiority of our model over competitive baselines on the original Visual Genome dataset with 80,000+ categories. We also show state-of-the-art performance on the VRD dataset and the scene graph dataset which is a subset of Visual Genome with 200 categories.

scholarly journals GapClust is a light-weight approach distinguishing rare cells from voluminous single cell expression profiles

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Botao Fa ◽  
Ting Wei ◽  
Yuan Zhou ◽  
Luke Johnston ◽  
Xin Yuan ◽  
...  
Keyword(s):  
Single Cell ◽  
Large Scale ◽  
State Of The Art ◽  
Expression Profiles ◽  
Cell Types ◽  
Superior Performance ◽  
Light Weight ◽  
Memory Efficiency ◽  
Rare Cells ◽  
Cell Expression

AbstractSingle cell RNA sequencing (scRNA-seq) is a powerful tool in detailing the cellular landscape within complex tissues. Large-scale single cell transcriptomics provide both opportunities and challenges for identifying rare cells playing crucial roles in development and disease. Here, we develop GapClust, a light-weight algorithm to detect rare cell types from ultra-large scRNA-seq datasets with state-of-the-art speed and memory efficiency. Benchmarking on diverse experimental datasets demonstrates the superior performance of GapClust compared to other recently proposed methods. When applying our algorithm to an intestine and 68 k PBMC datasets, GapClust identifies the tuft cells and a previously unrecognised subtype of monocyte, respectively.

scholarly journals DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes

2021 ◽  
Vol 13 (22) ◽  
pp. 4569
Author(s):  
Liyang Zhou ◽  
Zhuang Zhang ◽  
Hanqing Jiang ◽  
Han Sun ◽  
Hujun Bao ◽  
...  
Keyword(s):  
Point Cloud ◽  
Large Scale ◽  
State Of The Art ◽  
Depth Estimation ◽  
Surface Mesh ◽  
Depth Maps ◽  
Surface Meshing ◽  
Dense Point ◽  
Dense 3D Reconstruction ◽  
Memory Efficient

This paper presents an accurate and robust dense 3D reconstruction system for detail preserving surface modeling of large-scale scenes from multi-view images, which we named DP-MVS. Our system performs high-quality large-scale dense reconstruction, which preserves geometric details for thin structures, especially for linear objects. Our framework begins with a sparse reconstruction carried out by an incremental Structure-from-Motion. Based on the reconstructed sparse map, a novel detail preserving PatchMatch approach is applied for depth estimation of each image view. The estimated depth maps of multiple views are then fused to a dense point cloud in a memory-efficient way, followed by a detail-aware surface meshing method to extract the final surface mesh of the captured scene. Experiments on ETH3D benchmark show that the proposed method outperforms other state-of-the-art methods on F1-score, with the running time more than 4 times faster. More experiments on large-scale photo collections demonstrate the effectiveness of the proposed framework for large-scale scene reconstruction in terms of accuracy, completeness, memory saving, and time efficiency.

scholarly journals Improving Object Tracking by Added Noise and Channel Attention

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3780 ◽  
Author(s):  
Mustansar Fiaz ◽  
Arif Mahmood ◽  
Ki Yeol Baek ◽  
Sehar Shahzad Farooq ◽  
Soon Ki Jung
Keyword(s):  
Large Scale ◽  
Data Augmentation ◽  
Feature Fusion ◽  
State Of The Art ◽  
Computational Cost ◽  
Training Data ◽  
Superior Performance ◽  
Input Noise ◽  
Offline Learning ◽  
Benchmark Datasets

CNN-based trackers, especially those based on Siamese networks, have recently attracted considerable attention because of their relatively good performance and low computational cost. For many Siamese trackers, learning a generic object model from a large-scale dataset is still a challenging task. In the current study, we introduce input noise as regularization in the training data to improve generalization of the learned model. We propose an Input-Regularized Channel Attentional Siamese (IRCA-Siam) tracker which exhibits improved generalization compared to the current state-of-the-art trackers. In particular, we exploit offline learning by introducing additive noise for input data augmentation to mitigate the overfitting problem. We propose feature fusion from noisy and clean input channels which improves the target localization. Channel attention integrated with our framework helps finding more useful target features resulting in further performance improvement. Our proposed IRCA-Siam enhances the discrimination of the tracker/background and improves fault tolerance and generalization. An extensive experimental evaluation on six benchmark datasets including OTB2013, OTB2015, TC128, UAV123, VOT2016 and VOT2017 demonstrate superior performance of the proposed IRCA-Siam tracker compared to the 30 existing state-of-the-art trackers.

Deep Active Context Estimation for Automated COVID-19 Diagnosis

2021 ◽  
Vol 17 (3s) ◽  
pp. 1-22
Author(s):  
Bingzhi Chen ◽  
Yishu Liu ◽  
Zheng Zhang ◽  
Yingjian Li ◽  
Zhao Zhang ◽  
...  
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Superior Performance ◽  
High Confidence ◽  
Content Type ◽  
Feature Representations ◽  
Spatial Dependencies ◽  
Channel Interactions ◽  
Symptoms And Signs ◽  
Ct Slices

Many studies on automated COVID-19 diagnosis have advanced rapidly with the increasing availability of large-scale CT annotated datasets. Inevitably, there are still a large number of unlabeled CT slices in the existing data sources since it requires considerable consuming labor efforts. Notably, cinical experience indicates that the neighboring CT slices may present similar symptoms and signs. Inspired by such wisdom, we propose DACE, a novel CNN-based deep active context estimation framework, which leverages the unlabeled neighbors to progressively learn more robust feature representations and generate a well-performed classifier for COVID-19 diagnosis. Specifically, the backbone of the proposed DACE framework is constructed by a well-designed Long-Short Hierarchical Attention Network (LSHAN), which effectively incorporates two complementary attention mechanisms, i.e., short-range channel interactions (SCI) module and long-range spatial dependencies (LSD) module, to learn the most discriminative features from CT slices. To make full use of such available data, we design an efficient context estimation criterion to carefully assign the additional labels to these neighbors. Benefiting from two complementary types of informative annotations from -nearest neighbors, i.e., the majority of high-confidence samples with pseudo labels and the minority of low-confidence samples with hand-annotated labels, the proposed LSHAN can be fine-tuned and optimized in an incremental learning manner. Extensive experiments on the Clean-CC-CCII dataset demonstrate the superior performance of our method compared with the state-of-the-art baselines.

scholarly journals An Improved Deep Mutual-Attention Learning Model for Person Re-Identification

Symmetry ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 358
Author(s):  
Miftah Bedru Jamal ◽  
Jiang Zhengang ◽  
Fang Ming
Keyword(s):  
Feature Extraction ◽  
Similarity Measure ◽  
Adaptive Learning ◽  
Large Scale ◽  
State Of The Art ◽  
Background Illumination ◽  
Vast Number ◽  
Proposed Model ◽  
Art Works ◽  
Human Pose

Person re-identification is the task of matching pedestrian images across a network of non-overlapping camera views. It poses aggregated challenges resulted from random human pose, clutter from the background, illumination variations, and other factors. There has been a vast number of studies in recent years with promising success. However, key challenges have not been adequately addressed and continue to result in sub-optimal performance. Attention-based person re-identification gains more popularity in identifying discriminatory features from person images. Its potential in terms of extracting features common to a pair of person images across the feature extraction pipeline has not been be fully exploited. In this paper, we propose a novel attention-based Siamese network driven by a mutual-attention module decomposed into spatial and channel components. The proposed mutual-attention module not only leads feature extraction to the discriminative part of individual images, but also fuses mutual features symmetrically across pairs of person images to get informative regions common to both input images. Our model simultaneously learns feature embedding for discriminative cues and the similarity measure. The proposed model is optimized with multi-task loss, namely classification and verification loss. It is further optimized by a learnable mutual-attention module to facilitate an efficient and adaptive learning. The proposed model is thoroughly evaluated on extensively used large-scale datasets, Market-1501 and Duke-MTMC-ReID. Our experimental results show competitive results with the state-of-the-art works and the effectiveness of the mutual-attention module.

Sign in / Sign up

Export Citation Format

Share Document