1.HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures ⬇️
We present HoliCity, a city-scale 3D dataset with rich structural information. Currently, this dataset has 6,300 real-world panoramas of resolution
$13312 \times 6656$ that are accurately aligned with the CAD model of downtown London with an area of more than 20 km$^2$, in which the median reprojection error of the alignment of an average image is less than half a degree. This dataset aims to be an all-in-one data platform for research of learning abstracted high-level holistic 3D structures that can be derived from city CAD models, e.g., corners, lines, wireframes, planes, and cuboids, with the ultimate goal of supporting real-world applications including city-scale reconstruction, localization, mapping, and augmented reality. The accurate alignment of the 3D CAD models and panoramas also benefits low-level 3D vision tasks such as surface normal estimation, as the surface normal extracted from previous LiDAR-based datasets is often noisy. We conduct experiments to demonstrate the applications of HoliCity, such as predicting surface segmentation, normal maps, depth maps, and vanishing points, as well as test the generalizability of methods trained on HoliCity and other related datasets. HoliCity is available at this https URL.
2.Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning ⬇️
Dexterous manipulation of objects in virtual environments with our bare hands, by using only a depth sensor and a state-of-the-art 3D hand pose estimator (HPE), is challenging. While virtual environments are ruled by physics, e.g. object weights and surface frictions, the absence of force feedback makes the task challenging, as even slight inaccuracies on finger tips or contact points from HPE may make the interactions fail. Prior arts simply generate contact forces in the direction of the fingers' closures, when finger joints penetrate virtual objects. Although useful for simple grasping scenarios, they cannot be applied to dexterous manipulations such as in-hand manipulation. Existing reinforcement learning (RL) and imitation learning (IL) approaches train agents that learn skills by using task-specific rewards, without considering any online user input. In this work, we propose to learn a model that maps noisy input hand poses to target virtual poses, which introduces the needed contacts to accomplish the tasks on a physics simulator. The agent is trained in a residual setting by using a model-free hybrid RL+IL approach. A 3D hand pose estimation reward is introduced leading to an improvement on HPE accuracy when the physics-guided corrected target poses are remapped to the input space. As the model corrects HPE errors by applying minor but crucial joint displacements for contacts, this helps to keep the generated motion visually close to the user input. Since HPE sequences performing successful virtual interactions do not exist, a data generation scheme to train and evaluate the system is proposed. We test our framework in two applications that use hand pose estimates for dexterous manipulations: hand-object interactions in VR and hand-object motion reconstruction in-the-wild.
3.Multi-Level Temporal Pyramid Network for Action Detection ⬇️
Currently, one-stage frameworks have been widely applied for temporal action detection, but they still suffer from the challenge that the action instances span a wide range of time. The reason is that these one-stage detectors, e.g., Single Shot Multi-Box Detector (SSD), extract temporal features only applying a single-level layer for each head, which is not discriminative enough to perform classification and regression. In this paper, we propose a Multi-Level Temporal Pyramid Network (MLTPN) to improve the discrimination of the features. Specially, we first fuse the features from multiple layers with different temporal resolutions, to encode multi-layer temporal information. We then apply a multi-level feature pyramid architecture on the features to enhance their discriminative abilities. Finally, we design a simple yet effective feature fusion module to fuse the multi-level multi-scale features. By this means, the proposed MLTPN can learn rich and discriminative features for different action instances with different durations. We evaluate MLTPN on two challenging datasets: THUMOS'14 and Activitynet v1.3, and the experimental results show that MLTPN obtains competitive performance on Activitynet v1.3 and outperforms the state-of-the-art approaches on THUMOS'14 significantly.
4.Convolutional neural network based deep-learning architecture for intraprostatic tumour contouring on PSMA PET images in patients with primary prostate cancer ⬇️
Accurate delineation of the intraprostatic gross tumour volume (GTV) is a prerequisite for treatment approaches in patients with primary prostate cancer (PCa). Prostate-specific membrane antigen positron emission tomography (PSMA-PET) may outperform MRI in GTV detection. However, visual GTV delineation underlies interobserver heterogeneity and is time consuming. The aim of this study was to develop a convolutional neural network (CNN) for automated segmentation of intraprostatic tumour (GTV-CNN) in PSMA-PET.
Methods: The CNN (3D U-Net) was trained on [68Ga]PSMA-PET images of 152 patients from two different institutions and the training labels were generated manually using a validated technique. The CNN was tested on two independent internal (cohort 1: [68Ga]PSMA-PET, n=18 and cohort 2: [18F]PSMA-PET, n=19) and one external (cohort 3: [68Ga]PSMA-PET, n=20) test-datasets. Accordance between manual contours and GTV-CNN was assessed with Dice-Sørensen coefficient (DSC). Sensitivity and specificity were calculated for the two internal test-datasets by using whole-mount histology.
Results: Median DSCs for cohorts 1-3 were 0.84 (range: 0.32-0.95), 0.81 (range: 0.28-0.93) and 0.83 (range: 0.32-0.93), respectively. Sensitivities and specificities for GTV-CNN were comparable with manual expert contours: 0.98 and 0.76 (cohort 1) and 1 and 0.57 (cohort 2), respectively. Computation time was around 6 seconds for a standard dataset.
Conclusion: The application of a CNN for automated contouring of intraprostatic GTV in [68Ga]PSMA- and [18F]PSMA-PET images resulted in a high concordance with expert contours and in high sensitivities and specificities in comparison with histology reference. This robust, accurate and fast technique may be implemented for treatment concepts in primary PCa. The trained model and the study's source code are available in an open source repository.
5.A Study on Visual Perception of Light Field Content ⬇️
The effective design of visual computing systems depends heavily on the anticipation of visual attention, or saliency. While visual attention is well investigated for conventional 2D images and video, it is nevertheless a very active research area for emerging immersive media. In particular, visual attention of light fields (light rays of a scene captured by a grid of cameras or micro lenses) has only recently become a focus of research. As they may be rendered and consumed in various ways, a primary challenge that arises is the definition of what visual perception of light field content should be. In this work, we present a visual attention study on light field content. We conducted perception experiments displaying them to users in various ways and collected corresponding visual attention data. Our analysis highlights characteristics of user behaviour in light field imaging applications. The light field data set and attention data are provided with this paper.
6.Decomposition of Longitudinal Deformations via Beltrami Descriptors ⬇️
We present a mathematical model to decompose a longitudinal deformation into normal and abnormal components. The goal is to detect and extract subtle quivers from periodic motions in a video sequence. It has important applications in medical image analysis. To achieve this goal, we consider a representation of the longitudinal deformation, called the Beltrami descriptor, based on quasiconformal theories. The Beltrami descriptor is a complex-valued matrix. Each longitudinal deformation is associated to a Beltrami descriptor and vice versa. To decompose the longitudinal deformation, we propose to carry out the low rank and sparse decomposition of the Beltrami descriptor. The low rank component corresponds to the periodic motions, whereas the sparse part corresponds to the abnormal motions of a longitudinal deformation. Experiments have been carried out on both synthetic and real video sequences. Results demonstrate the efficacy of our proposed model to decompose a longitudinal deformation into regular and irregular components.
7.Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition ⬇️
Cross-domain few-shot learning (FSL) is proposed recently to transfer knowledge from general-domain known classes (e.g., ImageNet) to novel classes in other domains, and recognize novel classes with only few training samples. In this paper, we go further to define a more challenging scenario that transfers knowledge from general-domain known classes to novel classes in distant domains which are significantly different from the general domain, e.g., medical data. To solve this challenging problem, we propose to exploit mid-level features, which are more transferable, yet under-explored in recent main-stream FSL works. To boost the discriminability of mid-level features, we propose a residual-prediction task for the training on known classes. In this task, we view the current training sample as a sample from a pseudo-novel class, so as to provide simulated novel-class data. However, this simulated data is from the same domain as known classes, and shares high-level patterns with other known classes. Therefore, we then use high-level patterns from other known classes to represent it and remove this high-level representation from the simulated data, outputting a residual term containing discriminative information of it that could not be represented by high-level patterns from other known classes. Then, mid-level features from multiple mid-layers are dynamically weighted to predict this residual term, which encourages the mid-level features to be discriminative. Notably, our method can be applied to both the regular in-domain FSL setting by emphasizing high-level & transformed mid-level features and the distant-domain FSL setting by emphasizing mid-level features. Experiments under both settings on six public datasets (including two challenging medical datasets) validate the rationale of the proposed method, demonstrating state-of-the-art performance on both settings.
8.Associative Partial Domain Adaptation ⬇️
Partial Adaptation (PDA) addresses a practical scenario in which the target domain contains only a subset of classes in the source domain. While PDA should take into account both class-level and sample-level to mitigate negative transfer, current approaches mostly rely on only one of them. In this paper, we propose a novel approach to fully exploit multi-level associations that can arise in PDA. Our Associative Partial Domain Adaptation (APDA) utilizes intra-domain association to actively select out non-trivial anomaly samples in each source-private class that sample-level weighting cannot handle. Additionally, our method considers inter-domain association to encourage positive transfer by mapping between nearby target samples and source samples with high label-commonness. For this, we exploit feature propagation in a proposed label space consisting of source ground-truth labels and target probabilistic labels. We further propose a geometric guidance loss based on the label commonness of each source class to encourage positive transfer. Our APDA consistently achieves state-of-the-art performance across public datasets.
9.Cascade Graph Neural Networks for RGB-D Salient Object Detection ⬇️
In this paper, we study the problem of salient object detection (SOD) for RGB-D images using both color and depth information.A major technical challenge in performing salient object detection fromRGB-D images is how to fully leverage the two complementary data sources. Current works either simply distill prior knowledge from the corresponding depth map for handling the RGB-image or blindly fuse color and geometric information to generate the coarse depth-aware representations, hindering the performance of RGB-D saliency this http URL this work, we introduceCascade Graph Neural Networks(Cas-Gnn),a unified framework which is capable of comprehensively distilling and reasoning the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection. Cas-Gnn processes the two data sources individually and employs a novelCascade Graph Reasoning(CGR) module to learn powerful dense feature embeddings, from which the saliency map can be easily inferred. Contrast to the previous approaches, the explicitly modeling and reasoning of high-level relations between complementary data sources allows us to better overcome challenges such as occlusions and ambiguities. Extensive experiments demonstrate that Cas-Gnn achieves significantly better performance than all existing RGB-DSOD approaches on several widely-used benchmarks.
10.SimPatch: A Nearest Neighbor Similarity Match between Image Patches ⬇️
Measuring the similarity between patches in images is a fundamental building block in various tasks. Naturally, the patch-size has a major impact on the matching quality, and on the consequent application performance. We try to use large patches instead of relatively small patches so that each patch contains more information. We use different feature extraction mechanisms to extract the features of each individual image patches which forms a feature matrix and find out the nearest neighbor patches in the image. The nearest patches are calculated using two different nearest neighbor algorithms in this paper for a query patch for a given image and the results have been demonstrated in this paper.
11.Deep Ordinal Regression Forests ⬇️
Ordinal regression is a type of regression techniques used for predicting an ordinal variable. Recent methods formulate an ordinal regression problem as a series of binary classification problems. Such methods cannot ensure the global ordinal relationship is preserved since the relationships among different binary classifiers are neglected. We propose a novel ordinal regression approach called Deep Ordinal Regression Forests (DORFs), which is constructed with the differentiable decision trees for obtaining precise and stable global ordinal relationships. The advantages of the proposed DORFs are twofold. First, instead of learning a series of binary classifiers independently, the proposed method learns an ordinal distribution for ordinal regression. Second, the differentiable decision trees can be trained together with the ordinal distribution in an end-to-end manner. The effectiveness of the proposed DORFs is verified on two ordinal regression tasks, i.e., facial age estimation and image aesthetic assessment, showing significant improvements and better stability over the state-of-the-art ordinal regression methods.
12.Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis ⬇️
The collected data from industrial machines are often imbalanced, which poses a negative effect on learning algorithms. However, this problem becomes more challenging for a mixed type of data or while there is overlapping between classes. Class-imbalance problem requires a robust learning system which can timely predict and classify the data. We propose a new adversarial network for simultaneous classification and fault detection. In particular, we restore the balance in the imbalanced dataset by generating faulty samples from the proposed mixture of data distribution. We designed the discriminator of our model to handle the generated faulty samples to prevent outlier and overfitting. We empirically demonstrate that; (i) the discriminator trained with a generator to generates samples from a mixture of normal and faulty data distribution which can be considered as a fault detector; (ii), the quality of the generated faulty samples outperforms the other synthetic resampling techniques. Experimental results show that the proposed model performs well when comparing to other fault diagnosis methods across several evaluation metrics; in particular, coalescing of generative adversarial network (GAN) and feature matching function is effective at recognizing faulty samples.
13.A Surgery of the Neural Architecture Evaluators ⬇️
Neural architecture search (NAS) recently received extensive attention due to its effectiveness in automatically designing effective neural architectures. A major challenge in NAS is to conduct a fast and accurate evaluation of neural architectures. Commonly used fast architecture evaluators include one-shot evaluators (including weight sharing and hypernet-based ones) and predictor-based evaluators. Despite their high evaluation efficiency, the evaluation correlation of these evaluators is still questionable. In this paper, we conduct an extensive assessment of both the one-shot and predictor-based evaluator on the NAS-Bench-201 benchmark search space, and break up how and why different factors influence the evaluation correlation and other NAS-oriented criteria.
14.Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems ⬇️
Multispectral pedestrian detection is capable of adapting to insufficient illumination conditions by leveraging color-thermal modalities. On the other hand, it is still lacking of in-depth insights on how to fuse the two modalities effectively. Compared with traditional pedestrian detection, we find multispectral pedestrian detection suffers from modality imbalance problems which will hinder the optimization process of dual-modality network and depress the performance of detector. Inspired by this observation, we propose Modality Balance Network (MBNet) which facilitates the optimization process in a much more flexible and balanced manner. Firstly, we design a novel Differential Modality Aware Fusion (DMAF) module to make the two modalities complement each other. Secondly, an illumination aware feature alignment module selects complementary features according to the illumination conditions and aligns the two modality features adaptively. Extensive experimental results demonstrate MBNet outperforms the state-of-the-arts on both the challenging KAIST and CVC-14 multispectral pedestrian datasets in terms of the accuracy and the computational efficiency. Code is available at this https URL.
15.Deep Robust Clustering by Contrastive Learning ⬇️
Recently, many unsupervised deep learning methods have been proposed to learn clustering with unlabelled data. By introducing data augmentation, most of the latest methods look into deep clustering from the perspective that the original image and its tansformation should share similar semantic clustering assignment. However, the representation features before softmax activation function could be quite different even the assignment probability is very similar since softmax is only sensitive to the maximum value. This may result in high intra-class diversities in the representation feature space, which will lead to unstable local optimal and thus harm the clustering performance. By investigating the internal relationship between mutual information and contrastive learning, we summarized a general framework that can turn any maximizing mutual information into minimizing contrastive loss. We apply it to both the semantic clustering assignment and representation feature and propose a novel method named Deep Robust Clustering by Contrastive Learning (DRC). Different to existing methods, DRC aims to increase inter-class diver-sities and decrease intra-class diversities simultaneously and achieve more robust clustering results. Extensive experiments on six widely-adopted deep clustering benchmarks demonstrate the superiority of DRC in both stability and accuracy. e.g., attaining 71.6% mean accuracy on CIFAR-10, which is 7.1% higher than state-of-the-art results.
16.A Multi-Task Learning Approach for Human Action Detection and Ergonomics Risk Assessment ⬇️
We propose a new approach to Human Action Evaluation (HAE) in long videos using graph-based multi-task modeling. Previous works in activity assessment either directly compute a metric using a detected skeleton or use the scene information to regress the activity score. These approaches are insufficient for accurate activity assessment since they only compute an average score over a clip, and do not consider the correlation between the joints and body dynamics. Moreover, they are highly scene-dependent which makes the generalizability of these methods questionable. We propose a novel multi-task framework for HAE that utilizes a Graph Convolutional Network backbone to embed the interconnection between human joints in the features. In this framework, we solve the Human Action Detection (HAD) problem as an auxiliary task to improve activity assessment. The HAD head is powered by an Encoder-Decoder Temporal Convolutional Network to detect activities in long videos and HAE uses a Long-Short-Term-Memory-based architecture. We evaluate our method on the UW-IOM and TUM Kitchen datasets and discuss the success and failure cases on these two datasets.
17.Single-stage intake gesture detection using CTC loss and extended prefix beam search ⬇️
Accurate detection of individual intake gestures is a key step towards automatic dietary monitoring. Both inertial sensor data of wrist movements and video data depicting the upper body have been used for this purpose. The most advanced approaches to date use a two-stage approach, in which (i) frame-level intake probabilities are learned from the sensor data using a deep neural network, and then (ii) sparse intake events are detected by finding the maxima of the frame-level probabilities. In this study, we propose a single-stage approach which directly decodes the probabilities learned from sensor data into sparse intake detections. This is achieved by weakly supervised training using Connectionist Temporal Classification (CTC) loss, and decoding using a novel extended prefix beam search decoding algorithm. Benefits of this approach include (i) end-to-end training for detections, (ii) consistency with the fuzzy nature of intake gestures, and (iii) avoidance of hard-coded rules. Across two separate datasets, we quantify these benefits by showing relative
$F_1$ score improvements between 2.0% and 6.2% over the two-stage approach for intake detection and eating vs. drinking recognition tasks, for both video and inertial sensors.
18.Leveraging Localization for Multi-camera Association ⬇️
We present McAssoc, a deep learning approach to the as-sociation of detection bounding boxes in different views ofa multi-camera system. The vast majority of the academiahas been developing single-camera computer vision algo-rithms, however, little research attention has been directedto incorporating them into a multi-camera system. In thispaper, we designed a 3-branch architecture that leveragesdirect association and additional cross localization infor-mation. A new metric, image-pair association accuracy(IPAA) is designed specifically for performance evaluationof cross-camera detection association. We show in the ex-periments that localization information is critical to suc-cessful cross-camera association, especially when similar-looking objects are present. This paper is an experimentalwork prior to MessyTable, which is a large-scale bench-mark for instance association in mutliple cameras.
19.Global Context Aware Convolutions for 3D Point Cloud Understanding ⬇️
Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data, however, could have arbitrary rotations, especially those acquired from 3D scanning. Recent works show that it is possible to design point cloud convolutions with rotation invariance property, but such methods generally do not perform as well as translation-invariant only convolution. We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive. To address this problem, we propose a novel convolution operator that enhances feature distinction by integrating global context information from the input point cloud to the convolution. To this end, a globally weighted local reference frame is constructed in each point neighborhood in which the local point set is decomposed into bins. Anchor points are generated in each bin to represent global shape features. A convolution can then be performed to transform the points and anchor features into final rotation-invariant features. We conduct several experiments on point cloud classification, part segmentation, shape retrieval, and normals estimation to evaluate our convolution, which achieves state-of-the-art accuracy under challenging rotations.
20.Textual Description for Mathematical Equations ⬇️
Reading of mathematical expression or equation in the document images is very challenging due to the large variability of mathematical symbols and expressions. In this paper, we pose reading of mathematical equation as a task of generation of the textual description which interprets the internal meaning of this equation. Inspired by the natural image captioning problem in computer vision, we present a mathematical equation description (MED) model, a novel end-to-end trainable deep neural network based approach that learns to generate a textual description for reading mathematical equation images. Our MED model consists of a convolution neural network as an encoder that extracts features of input mathematical equation images and a recurrent neural network with attention mechanism which generates description related to the input mathematical equation images. Due to the unavailability of mathematical equation image data sets with their textual descriptions, we generate two data sets for experimental purpose. To validate the effectiveness of our MED model, we conduct a real-world experiment to see whether the students are able to write equations by only reading or listening their textual descriptions or not. Experiments conclude that the students are able to write most of the equations correctly by reading their textual descriptions only.
21.Exploring Rich and Efficient Spatial Temporal Interactions for Real Time Video Salient Object Detection ⬇️
The current main stream methods formulate their video saliency mainly from two independent venues, i.e., the spatial and temporal branches. As a complementary component, the main task for the temporal branch is to intermittently focus the spatial branch on those regions with salient movements. In this way, even though the overall video saliency quality is heavily dependent on its spatial branch, however, the performance of the temporal branch still matter. Thus, the key factor to improve the overall video saliency is how to further boost the performance of these branches efficiently. In this paper, we propose a novel spatiotemporal network to achieve such improvement in a full interactive fashion. We integrate a lightweight temporal model into the spatial branch to coarsely locate those spatially salient regions which are correlated with trustworthy salient movements. Meanwhile, the spatial branch itself is able to recurrently refine the temporal model in a multi-scale manner. In this way, both the spatial and temporal branches are able to interact with each other, achieving the mutual performance improvement. Our method is easy to implement yet effective, achieving high quality video saliency detection in real-time speed with 50 FPS.
22.A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception ⬇️
Previous video salient object detection (VSOD) approaches have mainly focused on designing fancy networks to achieve their performance improvements. However, with the slow-down in development of deep learning techniques recently, it may become more and more difficult to anticipate another breakthrough via fancy networks solely. To this end, this paper proposes a universal learning scheme to get a further 3% performance improvement for all state-of-the-art (SOTA) methods. The major highlight of our method is that we resort the "motion quality"---a brand new concept, to select a sub-group of video frames from the original testing set to construct a new training set. The selected frames in this new training set should all contain high-quality motions, in which the salient objects will have large probability to be successfully detected by the "target SOTA method"---the one we want to improve. Consequently, we can achieve a significant performance improvement by using this new training set to start a new round of network training. During this new round training, the VSOD results of the target SOTA method will be applied as the pseudo training objectives. Our novel learning scheme is simple yet effective, and its semi-supervised methodology may have large potential to inspire the VSOD community in the future.
23.Few Shot Learning Framework to Reduce Inter-observer Variability in Medical Images ⬇️
Most computer aided pathology detection systems rely on large volumes of quality annotated data to aid diagnostics and follow up procedures. However, quality assuring large volumes of annotated medical image data can be subjective and expensive. In this work we present a novel standardization framework that implements three few-shot learning (FSL) models that can be iteratively trained by atmost 5 images per 3D stack to generate multiple regional proposals (RPs) per test image. These FSL models include a novel parallel echo state network (ParESN) framework and an augmented U-net model. Additionally, we propose a novel target label selection algorithm (TLSA) that measures relative agreeability between RPs and the manually annotated target labels to detect the "best" quality annotation per image. Using the FSL models, our system achieves 0.28-0.64 Dice coefficient across vendor image stacks for intra-retinal cyst segmentation. Additionally, the TLSA is capable of automatically classifying high quality target labels from their noisy counterparts for 60-97% of the images while ensuring manual supervision on remaining images. Also, the proposed framework with ParESN model minimizes manual annotation checking to 12-28% of the total number of images. The TLSA metrics further provide confidence scores for the automated annotation quality assurance. Thus, the proposed framework is flexible to extensions for quality image annotation curation of other image stacks as well.
24.A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset ⬇️
Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy networks over large-scale training sets. However, do we really need large-scale training set for salient object detection (SOD)? In this paper, we provide a deeper insight into the interrelationship between the SOD performances and the training sets. To alleviate the conventional demands for large-scale training data, we provide a feasible way to construct a novel small-scale training set, which only contains 4K images. Moreover, we propose a novel bi-stream network to take full advantage of our proposed small training set, which is consisted of two feature backbones with different structures, achieving complementary semantical saliency fusion via the proposed gate control unit. To our best knowledge, this is the first attempt to use a small-scale training set to outperform state-of-the-art models which are trained on large-scale training sets; nevertheless, our method can still achieve the leading state-of-the-art performance on five benchmark datasets.
25.Polysemy Deciphering Network for Robust Human-Object Interaction Detection ⬇️
Human-Object Interaction (HOI) detection is important to human-centric scene understanding tasks. Existing works tend to assume that the same verb has similar visual characteristics in different HOI categories, an approach that ignores the diverse semantic meanings of the verb. To address this issue, in this paper, we propose a novel Polysemy Deciphering Network (PD-Net) that decodes the visual polysemy of verbs for HOI detection in three distinct ways. First, we refine features for HOI detection to be polysemyaware through the use of two novel modules: namely, Language Prior-guided Channel Attention (LPCA) and Language Prior-based Feature Augmentation (LPFA). LPCA highlights important elements in human and object appearance features for each HOI category to be identified; moreover, LPFA augments human pose and spatial features for HOI detection using language priors, enabling the verb classifiers to receive language hints that reduce intra-class variation for the same verb. Second, we introduce a novel Polysemy-Aware Modal Fusion module (PAMF), which guides PD-Net to make decisions based on feature types deemed more important according to the language priors. Third, we propose to relieve the verb polysemy problem through sharing verb classifiers for semantically similar HOI categories. Furthermore, to expedite research on the verb polysemy problem, we build a new benchmark dataset named HOI-VerbPolysemy (HOIVP), which includes common verbs (predicates) that have diverse semantic meanings in the real world. Finally, through deciphering the visual polysemy of verbs, our approach is demonstrated to outperform state-of-the-art methods by significant margins on the HICO-DET, V-COCO, and HOI-VP databases. Code and data in this paper will be released at this https URL.
26.An Indexing Scheme and Descriptor for 3D Object Retrieval Based on Local Shape Querying ⬇️
A binary descriptor indexing scheme based on Hamming distance called the Hamming tree for local shape queries is presented. A new binary clutter resistant descriptor named Quick Intersection Count Change Image (QUICCI) is also introduced. This local shape descriptor is extremely small and fast to compare. Additionally, a novel distance function called Weighted Hamming applicable to QUICCI images is proposed for retrieval applications. The effectiveness of the indexing scheme and QUICCI is demonstrated on 828 million QUICCI images derived from the SHREC2017 dataset, while the clutter resistance of QUICCI is shown using the clutterbox experiment.
27.Predicting Visual Importance Across Graphic Design Types ⬇️
This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along with a new dataset and applications. Previous methods for predicting saliency or visual importance are trained individually on specialized datasets, making them limited in application and leading to poor generalization on novel image classes, while requiring a user to know which model to apply to which input. UMSI is a deep learning-based model simultaneously trained on images from different design classes, including posters, infographics, mobile UIs, as well as natural images, and includes an automatic classification module to classify the input. This allows the model to work more effectively without requiring a user to label the input. We also introduce Imp1k, a new dataset of designs annotated with importance information. We demonstrate two new design interfaces that use importance prediction, including a tool for adjusting the relative importance of design elements, and a tool for reflowing designs to new aspect ratios while preserving visual importance. The model, code, and importance dataset are available at this https URL .
28.Diagnosis of Autism in Children using Facial Analysis and Deep Learning ⬇️
In this paper, we introduce a deep learning model to classify children as either healthy or potentially autistic with 94.6% accuracy using Deep Learning. Autistic patients struggle with social skills, repetitive behaviors, and communication, both verbal and nonverbal. Although the disease is considered to be genetic, the highest rates of accurate diagnosis occur when the child is tested on behavioral characteristics and facial features. Patients have a common pattern of distinct facial deformities, allowing researchers to analyze only an image of the child to determine if the child has the disease. While there are other techniques and models used for facial analysis and autism classification on their own, our proposal bridges these two ideas allowing classification in a cheaper, more efficient method. Our deep learning model uses MobileNet and two dense layers in order to perform feature extraction and image classification. The model is trained and tested using 3,014 images, evenly split between children with autism and children without it. 90% of the data is used for training, and 10% is used for testing. Based on our accuracy, we propose that the diagnosis of autism can be done effectively using only a picture. Additionally, there may be other diseases that are similarly diagnosable.
29.Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning ⬇️
Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual training data for a part of the classes from a dataset. When the number of classes is large, classes are usually represented by semantic class prototypes learned automatically from unannotated text collections. This typically leads to much lower performances than with manually designed semantic prototypes such as attributes. While most ZSL works focus on the visual aspect and reuse standard semantic prototypes learned from generic text collections, we focus on the problem of semantic class prototype design for large scale ZSL. More specifically, we investigate the use of noisy textual metadata associated to photos as text collections, as we hypothesize they are likely to provide more plausible semantic embeddings for visual classes if exploited appropriately. We thus make use of a source-based voting strategy to improve the robustness of semantic prototypes. Evaluation on the large scale ImageNet dataset shows a significant improvement in ZSL performances over two strong baselines, and over usual semantic embeddings used in previous works. We show that this improvement is obtained for several embedding methods, leading to state of the art results when one uses automatically created visual and text features.
30.Improving Explainability of Image Classification in Scenarios with Class Overlap: Application to COVID-19 and Pneumonia ⬇️
Trust in predictions made by machine learning models is increased if the model generalizes well on previously unseen samples and when inference is accompanied by cogent explanations of the reasoning behind predictions. In the image classification domain, generalization can also be assessed through accuracy, sensitivity, and specificity, and one measure to assess explainability is how well the model localizes the object of interest within an image. However, in multi-class settings, both generalization and explanation through localization are degraded when available training data contains features with significant overlap between classes. We propose a method to enhance explainability of image classification through better localization by mitigating the model uncertainty induced by class overlap. Our technique performs discriminative localization on images that contain features with significant class overlap, without explicitly training for localization. Our method is particularly promising in real-world class overlap scenarios, such as COVID19 vs pneumonia, where expertly labeled data for localization is not available. This can be useful for early, rapid, and trustworthy screening for COVID-19.
31.Integration of 3D Knowledge for On-Board UAV Visual Tracking ⬇️
Visual tracking from an unmanned aerial vehicle (UAV) poses challenges such as occlusions or background clutter. In order to achieve more robust on-board UAV visual tracking, a pipeline combining information extracted from a visual tracker and a sparse 3D reconstruction of the static environment is introduced. The 3D reconstruction is based on an image-based structure-from-motion (SfM) component and thus allows to utilize a state estimator in a pseudo-3D space. Thereby improved handling of occlusion situations and background clutter is realized. Evaluation is done on prototypical image sequences captured from a UAV with low-altitude oblique views. The experimental results demonstrate the benefit of the proposed approach compared to only relying on visual cues or using a state estimation in the image space.
32.Investigation of Speaker-adaptation methods in Transformer based ASR ⬇️
End-to-end models are fast replacing conventional hybrid models in automatic speech recognition. A transformer is a sequence-to-sequence framework solely based on attention, that was initially applied to machine translation task. This end-to-end framework has been shown to give promising results when used for automatic speech recognition as well. In this paper, we explore different ways of incorporating speaker information while training a transformer-based model to improve its performance. We present speaker information in the form of speaker embeddings for each of the speakers. Two broad categories of speaker embeddings are used: (i)fixed embeddings, and (ii)learned embeddings. We experiment using speaker embeddings learned along with the model training, as well as one-hot vectors and x-vectors. Using these different speaker embeddings, we obtain an average relative improvement of 1% to 3% in the token error rate. We report results on the NPTEL lecture database. NPTEL is an open-source e-learning portal providing content from top Indian universities.
33.ESPRESSO: Entropy and ShaPe awaRe timE-Series SegmentatiOn for processing heterogeneous sensor data ⬇️
Extracting informative and meaningful temporal segments from high-dimensional wearable sensor data, smart devices, or IoT data is a vital preprocessing step in applications such as Human Activity Recognition (HAR), trajectory prediction, gesture recognition, and lifelogging. In this paper, we propose ESPRESSO (Entropy and ShaPe awaRe timE-Series SegmentatiOn), a hybrid segmentation model for multi-dimensional time-series that is formulated to exploit the entropy and temporal shape properties of time-series. ESPRESSO differs from existing methods that focus upon particular statistical or temporal properties of time-series exclusively. As part of model development, a novel temporal representation of time-series
$WCAC$ was introduced along with a greedy search approach that estimate segments based upon the entropy metric. ESPRESSO was shown to offer superior performance to four state-of-the-art methods across seven public datasets of wearable and wear-free sensing. In addition, we undertake a deeper investigation of these datasets to understand how ESPRESSO and its constituent methods perform with respect to different dataset characteristics. Finally, we provide two interesting case-studies to show how applying ESPRESSO can assist in inferring daily activity routines and the emotional state of humans.
34.In-Depth DCT Coefficient Distribution Analysis for First Quantization Estimation ⬇️
The exploitation of traces in JPEG double compressed images is of utter importance for investigations. Properly exploiting such insights, First Quantization Estimation (FQE) could be performed in order to obtain source camera model identification (CMI) and therefore reconstruct the history of a digital image. In this paper, a method able to estimate the first quantization factors for JPEG double compressed images is presented, employing a mixed statistical and Machine Learning approach. The presented solution is demonstrated to work without any a-priori assumptions about the quantization matrices. Experimental results and comparisons with the state-of-the-art show the goodness of the proposed technique.
35.Multi-Task Driven Explainable Diagnosis of COVID-19 using Chest X-ray Images ⬇️
With increasing number of COVID-19 cases globally, all the countries are ramping up the testing numbers. While the RT-PCR kits are available in sufficient quantity in several countries, others are facing challenges with limited availability of testing kits and processing centers in remote areas. This has motivated researchers to find alternate methods of testing which are reliable, easily accessible and faster. Chest X-Ray is one of the modalities that is gaining acceptance as a screening modality. Towards this direction, the paper has two primary contributions. Firstly, we present the COVID-19 Multi-Task Network which is an automated end-to-end network for COVID-19 screening. The proposed network not only predicts whether the CXR has COVID-19 features present or not, it also performs semantic segmentation of the regions of interest to make the model explainable. Secondly, with the help of medical professionals, we manually annotate the lung regions of 9000 frontal chest radiographs taken from ChestXray-14, CheXpert and a consolidated COVID-19 dataset. Further, 200 chest radiographs pertaining to COVID-19 patients are also annotated for semantic segmentation. This database will be released to the research community.
36.Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluation ⬇️
We propose a transformation network for generating visually-protected images for privacy-preserving DNNs. The proposed transformation network is trained by using a plain image dataset so that plain images are transformed into visually protected ones. Conventional perceptual encryption methods have a weak visual-protection performance and some accuracy degradation in image classification. In contrast, the proposed network enables us not only to strongly protect visual information but also to maintain the image classification accuracy that using plain images achieves. In an image classification experiment, the proposed network is demonstrated to strongly protect visual information on plain images without any performance degradation under the use of CIFAR datasets. In addition, it is shown that the visually protected images are robust against a DNN-based attack, called inverse transformation network attack (ITN-Attack) in an experiment.
37.The Ensemble Method for Thorax Diseases Classification ⬇️
A common problem found in real-word medical image classification is the inherent imbalance of the positive and negative patterns in the dataset where positive patterns are usually rare. Moreover, in the classification of multiple classes with neural network, a training pattern is treated as a positive pattern in one output node and negative in all the remaining output nodes. In this paper, the weights of a training pattern in the loss function are designed based not only on the number of the training patterns in the class but also on the different nodes where one of them treats this training pattern as positive and the others treat it as negative. We propose a combined approach of weights calculation algorithm for deep network training and the training optimization from the state-of-the-art deep network architecture for thorax diseases classification problem. Experimental results on the Chest X-Ray image dataset demonstrate that this new weighting scheme improves classification performances, also the training optimization from the EfficientNet improves the performance furthermore. We compare the ensemble method with several performances from the previous study of thorax diseases classifications to provide the fair comparisons against the proposed method.
38.NuI-Go: Recursive Non-Local Encoder-Decoder Network for Retinal Image Non-Uniform Illumination Removal ⬇️
Retinal images have been widely used by clinicians for early diagnosis of ocular diseases. However, the quality of retinal images is often clinically unsatisfactory due to eye lesions and imperfect imaging process. One of the most challenging quality degradation issues in retinal images is non-uniform which hinders the pathological information and further impairs the diagnosis of ophthalmologists and computer-aided this http URL address this issue, we propose a non-uniform illumination removal network for retinal image, called NuI-Go, which consists of three Recursive Non-local Encoder-Decoder Residual Blocks (NEDRBs) for enhancing the degraded retinal images in a progressive manner. Each NEDRB contains a feature encoder module that captures the hierarchical feature representations, a non-local context module that models the context information, and a feature decoder module that recovers the details and spatial dimension. Additionally, the symmetric skip-connections between the encoder module and the decoder module provide long-range information compensation and reuse. Extensive experiments demonstrate that the proposed method can effectively remove the non-uniform illumination on retinal images while well preserving the image details and color. We further demonstrate the advantages of the proposed method for improving the accuracy of retinal vessel segmentation.
39.Parts-Based Articulated Object Localization in Clutter Using Belief Propagation ⬇️
Robots working in human environments must be able to perceive and act on challenging objects with articulations, such as a pile of tools. Articulated objects increase the dimensionality of the pose estimation problem, and partial observations under clutter create additional challenges. To address this problem, we present a generative-discriminative parts-based recognition and localization method for articulated objects in clutter. We formulate the problem of articulated object pose estimation as a Markov Random Field (MRF). Hidden nodes in this MRF express the pose of the object parts, and edges express the articulation constraints between parts. Localization is performed within the MRF using an efficient belief propagation method. The method is informed by both part segmentation heatmaps over the observation, generated by a neural network, and the articulation constraints between object parts. Our generative-discriminative approach allows the proposed method to function in cluttered environments by inferring the pose of occluded parts using hypotheses from the visible parts. We demonstrate the efficacy of our methods in a tabletop environment for recognizing and localizing hand tools in uncluttered and cluttered configurations.
40.Fatigue Assessment using ECG and Actigraphy Sensors ⬇️
Fatigue is one of the key factors in the loss of work efficiency and health-related quality of life, and most fatigue assessment methods were based on self-reporting, which may suffer from many factors such as recall bias. To address this issue, we developed an automated system using wearable sensing and machine learning techniques for objective fatigue assessment. ECG/Actigraphy data were collected from subjects in free-living environments. Preprocessing and feature engineering methods were applied, before interpretable solution and deep learning solution were introduced. Specifically, for interpretable solution, we proposed a feature selection approach which can select less correlated and high informative features for better understanding system's decision-making process. For deep learning solution, we used state-of-the-art self-attention model, based on which we further proposed a consistency self-attention (CSA) mechanism for fatigue assessment. Extensive experiments were conducted, and very promising results were achieved.
41.Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas ⬇️
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images. However, data quantity and quality remain a key determinant of, and a significant limit on, the potential of such applications. In our previous work, we explored synthesis of anatomic and molecular MR image network (SAMR) in patients with post-treatment malignant glioms. Now, we extend it and propose Confidence Guided SAMR (CG-SAMR) that synthesizes data from lesion information to multi-modal anatomic sequences, including T1-weighted (T1w), gadolinium enhanced T1w (Gd-T1w), T2-weighted (T2w), and fluid-attenuated inversion recovery (FLAIR), and the molecular amide proton transfer-weighted (APTw) sequence. We introduce a module which guides the synthesis based on confidence measure about the intermediate results. Furthermore, we extend the proposed architecture for unsupervised synthesis so that unpaired data can be used for training the network. Extensive experiments on real clinical data demonstrate that the proposed model can perform better than the state-of-theart synthesis methods.