arXiv subjects

Jie Guo

Publications and source records attributed to Jie Guo.

At least 91 records · Page 5Linked to original sources

arXiv2022

GLPanoDepth: Global-to-Local Panoramic Depth Estimation

In this paper, we propose a learning-based method for predicting dense depth values of a scene from a monocular omnidirectional image. An omnidirectional image has a full field-of-view, providing much more complete descriptions of the scene than perspective images. However, fully-convolutional networks that most current solutions rely on fail to capture rich global contexts from the panorama. To address this issue and also the distortion of equirectangular projection in the panorama, we propose Cubemap Vision Transformers (CViT), a new transformer-based architecture that can model long-range dependencies and extract distortion-free global features from the panorama. We show that cubemap vision transformers have a global receptive field at every stage and can provide globally coherent predictions for spherical signals. To preserve important local features, we further design a convolution-based branch in our pipeline (dubbed GLPanoDepth) and fuse global features from cubemap vision transformers at multiple scales. This global-to-local strategy allows us to fully exploit useful global and local features in the panorama, achieving state-of-the-art performance in panoramic depth estimation.

cs.CV↗

arXiv2021

Temporal Alignment Prediction for Few-Shot Video Classification

The goal of few-shot video classification is to learn a classification model with good generalization ability when trained with only a few labeled videos. However, it is difficult to learn discriminative feature representations for videos in such a setting. In this paper, we propose Temporal Alignment Prediction (TAP) based on sequence similarity learning for few-shot video classification. In order to obtain the similarity of a pair of videos, we predict the alignment scores between all pairs of temporal positions in the two videos with the temporal alignment prediction function. Besides, the inputs to this function are also equipped with the context information in the temporal domain. We evaluate TAP on two video classification benchmarks including Kinetics and Something-Something V2. The experimental results verify the effectiveness of TAP and show its superiority over state-of-the-art methods.

cs.CV↗

arXiv2021

Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems

The vigorous developments of Internet of Things make it possible to extend its computing and storage capabilities to computing tasks in the aerial system with collaboration of cloud and edge, especially for artificial intelligence (AI) tasks based on deep learning (DL). Collecting a large amount of image/video data, Unmanned aerial vehicles (UAVs) can only handover intelligent analysis tasks to the back-end mobile edge computing (MEC) server due to their limited storage and computing capabilities. How to efficiently transmit the most correlated information for the AI model is a challenging topic. Inspired by the task-oriented communication in recent years, we propose a new aerial image transmission paradigm for the scene classification task. A lightweight model is developed on the front-end UAV for semantic blocks transmission with perception of images and channel conditions. In order to achieve the tradeoff between transmission latency and classification accuracy, deep reinforcement learning (DRL) is used to explore the semantic blocks which have the best contribution to the back-end classifier under various channel conditions. Experimental results show that the proposed method can significantly improve classification accuracy compared to the fixed transmission strategy and traditional content perception methods.

cs.CV↗

arXiv2021

Simulation of the band structure of InAs/GaSb type II superlattices utilizing multiple energy band theories

Antimonide type II superlattices is expected to overtake HgCdTe as the preferred materials for infrared detection due to their excellent photoelectric properties and flexible and adjustable band structures. Among these compounds, InAs/GaSb type II superlattices represents the most commonly studied materials. However, the sophisticated physics associated with the antimonide-based bandgap engineering concept started at the beginning of 1990s gave a new impact and interest in development of infrared detector structures within academic and national laboratories. InAs/GaSb superlattices is a type II disconnected band structure with electrons and holes confined in the InAs and GaSb layers, respectively. The electron micro-band and hole micro-band can be regulated separately by adjusting the InAs and GaSb layers, which facilitates the design of superlattice structures and maximizes the amount of energy band offset. These works constituted a theoretical basis for the effective utilization of the InAs/GaSb system in material optimization and designing new SL structures; they also provided an opportunity for the preparation and rapid development of InAs/GaSb T2SLs. In this paper, we systematically review several widely used methods for simulating superlattice band structures, including the kp perturbation method, envelope function approximation, empirical pseudopotential method, empirical tight-binding method, and first-principles calculations. With the limitations of different theoretical methods proposed, the simulation methods have been modified and developed to obtain reliable InAs/GaSb SL energy band calculation results. The objective of this work is to provide a reference for designing InAs/GaSb type II superlattice band structures.

cond-mat.mtrl-sci↗

arXiv2021

SVBRDF Recovery From a Single Image With Highlights using a Pretrained Generative Adversarial Network

Spatially-varying bi-directional reflectance distribution functions (SVBRDFs) are crucial for designers to incorporate new materials in virtual scenes, making them look more realistic. Reconstruction of SVBRDFs is a long-standing problem. Existing methods either rely on extensive acquisition system or require huge datasets which are nontrivial to acquire. We aim to recover SVBRDFs from a single image, without any datasets. A single image contains incomplete information about the SVBRDF, making the reconstruction task highly ill-posed. It is also difficult to separate between the changes in color that are caused by the material and those caused by the illumination, without the prior knowledge learned from the dataset. In this paper, we use an unsupervised generative adversarial neural network (GAN) to recover SVBRDFs maps with a single image as input. To better separate the effects due to illumination from the effects due to the material, we add the hypothesis that the material is stationary and introduce a new loss function based on Fourier coefficients to enforce this stationarity. For efficiency, we train the network in two stages: reusing a trained model to initialize the SVBRDFs and fine-tune it based on the input image. Our method generates high-quality SVBRDFs maps from a single input photograph, and provides more vivid rendering results compared to previous work. The two-stage training boosts runtime performance, making it 8 times faster than previous work.

cs.CV↗

arXiv2021

A Transductive Maximum Margin Classifier for Few-Shot Learning

Few-shot learning aims to train a classifier that can generalize well when just a small number of labeled examples per class are given. We introduce a transductive maximum margin classifier for few-shot learning (FS-TMMC). The basic idea of the classical maximum margin classifier is to solve an optimal prediction function so that the training data can be correctly classified by the resulting classifer with the largest geometric margin. In few-shot learning, it is challenging to find such classifiers with good generalization ability due to the insufficiency of training data in the support set. FS-TMMC leverages the unlabeled query examples to adjust the separating hyperplane of the maximum margin classifier such that the prediction function is optimal on both the support and query sets. Furthermore, we use an efficient and effective quasi-Newton algorithm, the L-BFGS method for optimization. Experimental results on three standard few-shot learning benchmarks including miniImagenet, tieredImagenet and CUB show that our method achieves state-of-the-art performance.

cs.CV↗

arXiv2021

Scale Invariant Domain Generalization Image Recapture Detection

Recapturing and rebroadcasting of images are common attack methods in insurance frauds and face identification spoofing, and an increasing number of detection techniques were introduced to handle this problem. However, most of them ignored the domain generalization scenario and scale variances, with an inferior performance on domain shift situations, and normally were exacerbated by intra-domain and inter-domain scale variances. In this paper, we propose a scale alignment domain generalization framework (SADG) to address these challenges. First, an adversarial domain discriminator is exploited to minimize the discrepancies of image representation distributions among different domains. Meanwhile, we exploit triplet loss as a local constraint to achieve a clearer decision boundary. Moreover, a scale alignment loss is introduced as a global relationship regularization to force the image representations of the same class across different scales to be undistinguishable. Experimental results on four databases and comparison with state-of-the-art approaches show that better performance can be achieved using our framework.

cs.CV↗

arXiv2021

Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections

Model ensembles are becoming one of the most effective approaches for improving object detection performance already optimized for a single detector. Conventional methods directly fuse bounding boxes but typically fail to consider proposal qualities when combining detectors. This leads to a new problem of confidence discrepancy for the detector ensembles. The confidence has little effect on single detectors but significantly affects detector ensembles. To address this issue, we propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors. By simultaneously considering the category and the location on the same validation set, we obtain a more reliable confidence based on statistical probability. We can then rank the detected bounding boxes for assembly. We also introduce a bandit approach to address the confidence imbalance problem caused by the need to deal with different numbers of boxes at different confidence levels. We use our PRAE-based non-maximum suppression (P-NMS) to replace the conventional NMS method in ensemble learning. Experiments on the PASCAL VOC and COCO2017 datasets demonstrate that our PRAE method consistently outperforms state-of-the-art methods by significant margins.

cs.CV↗

arXiv2021

A Survey on Natural Language Video Localization

Natural language video localization (NLVL), which aims to locate a target moment from a video that semantically corresponds to a text query, is a novel and challenging task. Toward this end, in this paper, we present a comprehensive survey of the NLVL algorithms, where we first propose the pipeline of NLVL, and then categorize them into supervised and weakly-supervised methods, following by the analysis of the strengths and weaknesses of each kind of methods. Subsequently, we present the dataset, evaluation protocols and the general performance analysis. Finally, the possible perspectives are obtained by summarizing the existing methods.

cs.CV↗

arXiv2021

Rendering Discrete Participating Media with Geometrical Optics Approximation

We consider the scattering of light in participating media composed of sparsely and randomly distributed discrete particles. The particle size is expected to range from the scale of the wavelength to the scale several orders of magnitude greater than the wavelength, and the appearance shows distinct graininess as opposed to the smooth appearance of continuous media. One fundamental issue in physically-based synthesizing this appearance is to determine necessary optical properties in every local region. Since these optical properties vary spatially, we resort to geometrical optics approximation (GOA), a highly efficient alternative to rigorous Lorenz-Mie theory, to quantitatively represent the scattering of a single particle. This enables us to quickly compute bulk optical properties according to any particle size distribution. Then, we propose a practical Monte Carlo rendering solution to solve the transfer of energy in discrete participating media. Results show that for the first time our proposed framework can simulate a wide range of discrete participating media with different levels of graininess and converges to continuous media as the particle concentration increases.

cs.GR↗

arXiv2020

Partially Observable Online Change Detection via Smooth-Sparse Decomposition

We consider online change detection of high dimensional data streams with sparse changes, where only a subset of data streams can be observed at each sensing time point due to limited sensing capacities. On the one hand, the detection scheme should be able to deal with partially observable data and meanwhile have efficient detection power for sparse changes. On the other, the scheme should be able to adaptively and actively select the most important variables to observe to maximize the detection power. To address these two points, in this paper, we propose a novel detection scheme called CDSSD. In particular, it describes the structure of high dimensional data with sparse changes by smooth-sparse decomposition, whose parameters can be learned via spike-slab variational Bayesian inference. Then the posterior Bayes factor, which incorporates the learned parameters and sparse change information, is formulated as a detection statistic. Finally, by formulating the statistic as the reward of a combinatorial multi-armed bandit problem, an adaptive sampling strategy based on Thompson sampling is proposed. The efficacy and applicability of our method in practice are demonstrated with numerical studies and a real case study.

stat.ML↗

arXiv2020

Hybrid Models for Open Set Recognition

Open set recognition requires a classifier to detect samples not belonging to any of the classes in its training set. Existing methods fit a probability distribution to the training samples on their embedding space and detect outliers according to this distribution. The embedding space is often obtained from a discriminative classifier. However, such discriminative representation focuses only on known classes, which may not be critical for distinguishing the unknown classes. We argue that the representation space should be jointly learned from the inlier classifier and the density estimator (served as an outlier detector). We propose the OpenHybrid framework, which is composed of an encoder to encode the input data into a joint embedding space, a classifier to classify samples to inlier classes, and a flow-based density estimator to detect whether a sample belongs to the unknown category. A typical problem of existing flow-based models is that they may assign a higher likelihood to outliers. However, we empirically observe that such an issue does not occur in our experiments when learning a joint representation for discriminative and generative components. Experiments on standard open set benchmarks also reveal that an end-to-end trained OpenHybrid model significantly outperforms state-of-the-art methods and flow-based baselines.

cs.CV↗

arXiv2020

Image Stitching Based on Planar Region Consensus

Image stitching for two images without a global transformation between them is notoriously difficult. In this paper, noticing the importance of planar structure under perspective geometry, we propose a new image stitching method which stitches images by allowing for the alignment of a set of matched dominant planar regions. Clearly different from previous methods resorting to plane segmentation, the key to our approach is to utilize rich semantic information directly from RGB images to extract planar image regions with a deep Convolutional Neural Network (CNN). We specifically design a new module to make fully use of existing semantic segmentation networks to accommodate planar segmentation. To train the network, a dataset for planar region segmentation is contributed. With the planar region knowledge, a set of local transformations can be obtained by constraining matched regions, enabling more precise alignment in the overlapping area. We also use planar knowledge to estimate a transformation field over the whole image. The final mosaic is obtained by a mesh-based optimization framework which maintains high alignment accuracy and relaxes similarity transformation at the same time. Extensive experiments with quantitative comparisons show that our method can deal with different situations and outperforms the state-of-the-arts on challenging scenes.

cs.CV↗

arXiv2020

FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces

Facial attractiveness enhancement has been an interesting application in Computer Vision and Graphics over these years. It aims to generate a more attractive face via manipulations on image and geometry structure while preserving face identity. In this paper, we propose the first Generative Adversarial Networks (GANs) for enhancing facial attractiveness in both geometry and appearance aspects, which we call "FA-GANs". FA-GANs contain two branches and enhance facial attractiveness in two perspectives: facial geometry and facial appearance. Each branch consists of individual GANs with the appearance branch adjusting the facial image and the geometry branch adjusting the facial landmarks in appearance and geometry aspects, respectively. Unlike the traditional facial manipulations learning from paired faces, which are infeasible to collect before and after enhancement of the same individual, we achieve this by learning the features of attractiveness faces through unsupervised adversarial learning. The proposed FA-GANs are able to extract attractiveness features and impose them on the enhancement results. To better enhance faces, both the geometry and appearance networks are considered to refine the facial attractiveness by adjusting the geometry layout of faces and the appearance of faces independently. To the best of our knowledge, we are the first to enhance the facial attractiveness with GANs in both geometry and appearance aspects. The experimental results suggest that our FA-GANs can generate compelling perceptual results in both geometry structure and facial appearance and outperform current state-of-the-art methods.

cs.CV↗

arXiv2019

Learning Actor Relation Graphs for Group Activity Recognition

Modeling relation between actors is important for recognizing group activity in a multi-person scene. This paper aims at learning discriminative relation between actors efficiently using deep models. To this end, we propose to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors. Thanks to the Graph Convolutional Network, the connections in ARG could be automatically learned from group activity videos in an end-to-end manner, and the inference on ARG could be efficiently performed with standard matrix operations. Furthermore, in practice, we come up with two variants to sparsify ARG for more effective modeling in videos: spatially localized ARG and temporal randomized ARG. We perform extensive experiments on two standard group activity recognition datasets: the Volleyball dataset and the Collective Activity dataset, where state-of-the-art performance is achieved on both datasets. We also visualize the learned actor graphs and relation features, which demonstrate that the proposed ARG is able to capture the discriminative relation information for group activity recognition.

cs.CV↗

arXiv2019

Self-Selective Correlation Ship Tracking Method for Smart Ocean System

In recent years, with the development of the marine industry, navigation environment becomes more complicated. Some artificial intelligence technologies, such as computer vision, can recognize, track and count the sailing ships to ensure the maritime security and facilitates the management for Smart Ocean System. Aiming at the scaling problem and boundary effect problem of traditional correlation filtering methods, we propose a self-selective correlation filtering method based on box regression (BRCF). The proposed method mainly include: 1) A self-selective model with negative samples mining method which effectively reduces the boundary effect in strengthening the classification ability of classifier at the same time; 2) A bounding box regression method combined with a key points matching method for the scale prediction, leading to a fast and efficient calculation. The experimental results show that the proposed method can effectively deal with the problem of ship size changes and background interference. The success rates and precisions were higher than Discriminative Scale Space Tracking (DSST) by over 8 percentage points on the marine traffic dataset of our laboratory. In terms of processing speed, the proposed method is higher than DSST by nearly 22 Frames Per Second (FPS).

cs.CV↗

arXiv2019

Super-Resolution of Brain MRI Images using Overcomplete Dictionaries and Nonlocal Similarity

Recently, the Magnetic Resonance Imaging (MRI) images have limited and unsatisfactory resolutions due to various constraints such as physical, technological and economic considerations. Super-resolution techniques can obtain high-resolution MRI images. The traditional methods obtained the resolution enhancement of brain MRI by interpolations, affecting the accuracy of the following diagnose process. The requirement for brain image quality is fast increasing. In this paper, we propose an image super-resolution (SR) method based on overcomplete dictionaries and inherent similarity of an image to recover the high-resolution (HR) image from a single low-resolution (LR) image. We explore the nonlocal similarity of the image to tentatively search for similar blocks in the whole image and present a joint reconstruction method based on compressive sensing (CS) and similarity constraints. The sparsity and self-similarity of the image blocks are taken as the constraints. The proposed method is summarized in the following steps. First, a dictionary classification method based on the measurement domain is presented. The image blocks are classified into smooth, texture and edge parts by analyzing their features in the measurement domain. Then, the corresponding dictionaries are trained using the classified image blocks. Equally important, in the reconstruction part, we use the CS reconstruction method to recover the HR brain MRI image, considering both nonlocal similarity and the sparsity of an image as the constraints. This method performs better both visually and quantitatively than some existing methods.

cs.CV↗

arXiv2019

Interest-Related Item Similarity Model Based on Multimodal Data for Top-N Recommendation

Nowadays, the recommendation systems are applied in the fields of e-commerce, video websites, social networking sites, etc., which bring great convenience to people's daily lives. The types of the information are diversified and abundant in recommendation systems, therefore the proportion of unstructured multimodal data like text, image and video is increasing. However, due to the representation gap between different modalities, it is intractable to effectively use unstructured multimodal data to improve the efficiency of recommendation systems. In this paper, we propose an end-to-end Multimodal Interest-Related Item Similarity model (Multimodal IRIS) to provide recommendations based on multimodal data source. Specifically, the Multimodal IRIS model consists of three modules, i.e., multimodal feature learning module, the Interest-Related Network (IRN) module and item similarity recommendation module. The multimodal feature learning module adds knowledge sharing unit among different modalities. Then IRN learn the interest relevance between target item and different historical items respectively. At last, the multimodal data feature learning, IRN and item similarity recommendation modules are unified into an integrated system to achieve performance enhancements and to accommodate the addition or absence of different modal data. Extensive experiments on real-world datasets show that, by dealing with the multimodal data which people may pay more attention to when selecting items, the proposed Multimodal IRIS significantly improves accuracy and interpretability on top-N recommendation task over the state-of-the-art methods.

cs.IR↗