arXiv subjects

Jiebo Luo

Publications and source records attributed to Jiebo Luo.

At least 271 records · Page 15Linked to original sources

arXiv2021

DAIL: Dataset-Aware and Invariant Learning for Face Recognition

To achieve good performance in face recognition, a large scale training dataset is usually required. A simple yet effective way to improve recognition performance is to use a dataset as large as possible by combining multiple datasets in the training. However, it is problematic and troublesome to naively combine different datasets due to two major issues. First, the same person can possibly appear in different datasets, leading to an identity overlapping issue between different datasets. Naively treating the same person as different classes in different datasets during training will affect back-propagation and generate non-representative embeddings. On the other hand, manually cleaning labels may take formidable human efforts, especially when there are millions of images and thousands of identities. Second, different datasets are collected in different situations and thus will lead to different domain distributions. Naively combining datasets will make it difficult to learn domain invariant embeddings across different datasets. In this paper, we propose DAIL: Dataset-Aware and Invariant Learning to resolve the above-mentioned issues. To solve the first issue of identity overlapping, we propose a dataset-aware loss for multi-dataset training by reducing the penalty when the same person appears in multiple datasets. This can be readily achieved with a modified softmax loss with a dataset-aware term. To solve the second issue, domain adaptation with gradient reversal layers is employed for dataset invariant learning. The proposed approach not only achieves state-of-the-art results on several commonly used face recognition validation sets, including LFW, CFP-FP, and AgeDB-30, but also shows great benefit for practical use.

cs.CV↗

arXiv2021

Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods

Representation learning with small labeled data have emerged in many problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address it, many efforts have been made on training sophisticated models with few labeled data in an unsupervised and semi-supervised fashion. In this paper, we will review the recent progresses on these two major categories of methods. A wide spectrum of models will be categorized in a big picture, where we will show how they interplay with each other to motivate explorations of new ideas. We will review the principles of learning the transformation equivariant, disentangled, self-supervised and semi-supervised representations, all of which underpin the foundation of recent progresses. Many implementations of unsupervised and semi-supervised generative models have been developed on the basis of these criteria, greatly expanding the territory of existing autoencoders, generative adversarial nets (GANs) and other deep networks by exploring the distribution of unlabeled data for more powerful representations. We will discuss emerging topics by revealing the intrinsic connections between unsupervised and semi-supervised learning, and propose in future directions to bridge the algorithmic and theoretical gap between transformation equivariance for unsupervised learning and supervised invariance for supervised learning, and unify unsupervised pretraining and supervised finetuning. We will also provide a broader outlook of future directions to unify transformation and instance equivariances for representation learning, connect unsupervised and semi-supervised augmentations, and explore the role of the self-supervised regularization for many learning problems.

cs.CV↗

arXiv2020

Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language

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

cs.CV↗

arXiv2020

Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$)

We propose to tackle the problem of multiview 2D/3D rigid registration for intervention via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$). $\text{POINT}^2$ learns to establish 2D point-to-point correspondences between the pre- and intra-intervention images by tracking a set of random POIs. The 3D pose of the pre-intervention volume is then estimated through a triangulation layer. In $\text{POINT}^2$, the unified framework of the POI tracker and the triangulation layer enables learning informative 2D features and estimating 3D pose jointly. In contrast to existing approaches, $\text{POINT}^2$ only requires a single forward-pass to achieve a reliable 2D/3D registration. As the POI tracker is shift-invariant, $\text{POINT}^2$ is more robust to the initial pose of the 3D pre-intervention image. Extensive experiments on a large-scale clinical cone-beam CT (CBCT) dataset show that the proposed $\text{POINT}^2$ method outperforms the existing learning-based method in terms of accuracy, robustness and running time. Furthermore, when used as an initial pose estimator, our method also improves the robustness and speed of the state-of-the-art optimization-based approaches by ten folds.

cs.CV↗

arXiv2020

TAP: Text-Aware Pre-training for Text-VQA and Text-Caption

In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answering and image caption generation, respectively. In contrast to the conventional vision-language pre-training that fails to capture scene text and its relationship with the visual and text modalities, TAP explicitly incorporates scene text (generated from OCR engines) in pre-training. With three pre-training tasks, including masked language modeling (MLM), image-text (contrastive) matching (ITM), and relative (spatial) position prediction (RPP), TAP effectively helps the model learn a better aligned representation among the three modalities: text word, visual object, and scene text. Due to this aligned representation learning, even pre-trained on the same downstream task dataset, TAP already boosts the absolute accuracy on the TextVQA dataset by +5.4%, compared with a non-TAP baseline. To further improve the performance, we build a large-scale dataset based on the Conceptual Caption dataset, named OCR-CC, which contains 1.4 million scene text-related image-text pairs. Pre-trained on this OCR-CC dataset, our approach outperforms the state of the art by large margins on multiple tasks, i.e., +8.3% accuracy on TextVQA, +8.6% accuracy on ST-VQA, and +10.2 CIDEr score on TextCaps.

cs.CV↗

arXiv2020

Grounding-Tracking-Integration

In this paper, we study Tracking by Language that localizes the target box sequence in a video based on a language query. We propose a framework called GTI that decomposes the problem into three sub-tasks: Grounding, Tracking, and Integration. The three sub-task modules operate simultaneously and predict the box sequence frame-by-frame. "Grounding" predicts the referred region directly from the language query. "Tracking" localizes the target based on the history of the grounded regions in previous frames. "Integration" generates final predictions by synergistically combining grounding and tracking. With the "integration" task as the key, we explore how to indicate the quality of the grounded regions in each frame and achieve the desired mutually beneficial combination. To this end, we propose an "RT-integration" method that defines and predicts two scores to guide the integration: 1) R-score represents the Region correctness whether the grounding prediction accurately covers the target, and 2) T-score represents the Template quality whether the region provides informative visual cues to improve tracking in future frames. We present our real-time GTI implementation with the proposed RT-integration, and benchmark the framework on LaSOT and Lingual OTB99 with highly promising results. Moreover, we produce a disambiguated version of LaSOT queries to facilitate future tracking by language studies.

cs.CV↗

arXiv2020

Face Off: Polarized Public Opinions on Personal Face Mask Usage during the COVID-19 Pandemic

In spite of a growing body of scientific evidence on the effectiveness of individual face mask usage for reducing transmission rates, individual face mask usage has become a highly polarized topic within the United States. A series of policy shifts by various governmental bodies have been speculated to have contributed to the polarization of face masks. A typical method to investigate the effects of these policy shifts is to use surveys. However, survey-based approaches have multiple limitations: biased responses, limited sample size, badly crafted questions may skew responses and inhibit insight, and responses may prove quickly irrelevant as opinions change in response to a dynamic topic. We propose a novel approach to 1) accurately gauge public sentiment towards face masks in the United States during COVID-19 using a multi-modal demographic inference framework with topic modeling and 2) determine whether face mask policy shifts contributed to polarization towards face masks using offline change point analysis on Twitter data. First, we infer several key demographics of individual Twitter users such as their age, gender, and whether they are a college student using a multi-modal demographic prediction framework and analyze the average sentiment for each respective demographic. Next, we conduct topic analysis using latent Dirichlet allocation (LDA). Finally, we conduct offline change point discovery on our sentiment time series data using the Pruned Exact Linear Time (PELT) search algorithm. Experimental results on a large corpus of Twitter data reveal multiple insights regarding demographic sentiment towards face masks that agree with existing surveys. Furthermore, we find two key policy-shift events contributed to statistically significant changes in sentiment for both Republicans and Democrats.

cs.CY↗

arXiv2020

Content-based Analysis of the Cultural Differences between TikTok and Douyin

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

cs.CV↗

arXiv2020

Measuring Female Representation and Impact in Films over Time

Women have always been underrepresented in movies and not until recently has the representation of women in movies improved. To investigate the improvement of female representation and its relationship with a movie's success, we propose a new measure, the female cast ratio, and compare it to the commonly used Bechdel test result. We employ generalized linear regression with $L_1$ penalty and a Random Forest model to identify the predictors that influence female representation, and evaluate the relationship between female representation and a movie's success in three aspects: revenue/budget ratio, rating, and popularity. Three important findings in our study have highlighted the difficulties women in the film industry face both upstream and downstream. First, female filmmakers, especially female screenplay writers, are instrumental for movies to have better female representation, but the percentage of female filmmakers has been very low. Second, movies that have the potential to tell insightful stories about women are often provided with lower budgets, and this usually causes the films to in turn receive more criticism. Finally, the demand for better female representation from moviegoers has also not been strong enough to compel the film industry to change, as movies that have poor female representation can still be very popular and successful in the box office.

cs.CY↗

arXiv2020

Weakly Supervised Body Part Segmentation with Pose based Part Priors

Human body part segmentation refers to the task of predicting the semantic segmentation mask for each body part. Fully supervised body part segmentation methods achieve good performances but require an enormous amount of effort to annotate part masks for training. In contrast to high annotation costs needed for a limited number of part mask annotations, a large number of weak labels such as poses and full body masks already exist and contain relevant information. Motivated by the possibility of using existing weak labels, we propose the first weakly supervised body part segmentation framework. The core idea is first converting the sparse weak labels such as keypoints to the initial estimate of body part masks, and then iteratively refine the part mask predictions. We name the initial part masks estimated from poses the "part priors." With sufficient extra weak labels, our weakly supervised framework achieves a comparable performance (62.0% mIoU) to the fully supervised method (63.6% mIoU) on the Pascal-Person-Part dataset. Furthermore, in the extended semi-supervised setting, the proposed framework outperforms the state-of-art methods. Moreover, we extend our proposed framework to other keypoint-supervised part segmentation tasks such as face parsing.

cs.CV↗

arXiv2020

Pose-based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation

Inspired by the human ability to infer emotions from body language, we propose an automated framework for body language based emotion recognition starting from regular RGB videos. In collaboration with psychologists, we further extend the framework for psychiatric symptom prediction. Because a specific application domain of the proposed framework may only supply a limited amount of data, the framework is designed to work on a small training set and possess a good transferability. The proposed system in the first stage generates sequences of body language predictions based on human poses estimated from input videos. In the second stage, the predicted sequences are fed into a temporal network for emotion interpretation and psychiatric symptom prediction. We first validate the accuracy and transferability of the proposed body language recognition method on several public action recognition datasets. We then evaluate the framework on a proposed URMC dataset, which consists of conversations between a standardized patient and a behavioral health professional, along with expert annotations of body language, emotions, and potential psychiatric symptoms. The proposed framework outperforms other methods on the URMC dataset.

cs.CV↗

arXiv2020

Predicting Parkinson's Disease with Multimodal Irregularly Collected Longitudinal Smartphone Data

Parkinsons Disease is a neurological disorder and prevalent in elderly people. Traditional ways to diagnose the disease rely on in-person subjective clinical evaluations on the quality of a set of activity tests. The high-resolution longitudinal activity data collected by smartphone applications nowadays make it possible to conduct remote and convenient health assessment. However, out-of-lab tests often suffer from poor quality controls as well as irregularly collected observations, leading to noisy test results. To address these issues, we propose a novel time-series based approach to predicting Parkinson's Disease with raw activity test data collected by smartphones in the wild. The proposed method first synchronizes discrete activity tests into multimodal features at unified time points. Next, it distills and enriches local and global representations from noisy data across modalities and temporal observations by two attention modules. With the proposed mechanisms, our model is capable of handling noisy observations and at the same time extracting refined temporal features for improved prediction performance. Quantitative and qualitative results on a large public dataset demonstrate the effectiveness of the proposed approach.

cs.LG↗

arXiv2020

In the Eyes of the Beholder: Analyzing Social Media Use of Neutral and Controversial Terms for COVID-19

During the COVID-19 pandemic, "Chinese Virus" emerged as a controversial term for coronavirus. To some, it may seem like a neutral term referring to the physical origin of the virus. To many others, however, the term is in fact attaching ethnicity to the virus. While both arguments appear reasonable, quantitative analysis of the term's real-world usage is lacking to shed light on the issues behind the controversy. In this paper, we attempt to fill this gap. To model the substantive difference of tweets with controversial terms and those with non-controversial terms, we apply topic modeling and LIWC-based sentiment analysis. To test whether "Chinese Virus" and "COVID-19" are interchangeable, we formulate it as a classification task, mask out these terms, and classify them using the state-of-the-art transformer models. Our experiments consistently show that the term "Chinese Virus" is associated with different substantive topics and sentiment compared with "COVID-19" and that the two terms are easily distinguishable by looking at their context.

cs.SI↗

arXiv2020

How Political is the Spread of COVID-19 in the United States? An Analysis using Transportation and Weather Data

We investigate the difference in the spread of COVID-19 between the states won by Donald Trump (Red) and the states won by Hillary Clinton (Blue) in the 2016 presidential election, by mining transportation patterns of US residents from March 2020 to July 2020. To ensure a fair comparison, we first use a K-means clustering method to group the 50 states into five clusters according to their population, area and population density. We then characterize daily transportation patterns of the residents of different states using the mean percentage of residents traveling and the number of trips per person. For each state, we study the correlations between travel patterns and infection rate for a 2-month period before and after the official states reopening dates. We observe that during the lock-down, Red and Blue states both displayed strong positive correlations between their travel patterns and infection rates. However, after states reopened we find that Red states had higher travel-infection correlations than Blue states in all five state clusters. We find that the residents of both Red and Blue states displayed similar travel patterns during the period post the reopening of states, leading us to conclude that, on average, the residents in Red states might be mobilizing less safely than the residents in Blue states. Furthermore, we use temperature data to attempt to explain the difference in the way residents travel and practice safety measures.

cs.SI↗

arXiv2020

Region Comparison Network for Interpretable Few-shot Image Classification

While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming. Few-shot image classification has thus been proposed to effectively use only a limited number of labeled examples to train models for new classes. Recent works based on transferable metric learning methods have achieved promising classification performance through learning the similarity between the features of samples from the query and support sets. However, rare of them explicitly considers the model interpretability, which can actually be revealed during the training phase. For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets. Moreover, we also present a visualization strategy named Region Activation Mapping (RAM) to intuitively explain what our method has learned by visualizing intermediate variables in our network. We also present a new way to generalize the interpretability from the level of tasks to categories, which can also be viewed as a method to find the prototypical parts for supporting the final decision of our RCN. Extensive experiments on four benchmark datasets clearly show the effectiveness of our method over existing baselines.

cs.CV↗

arXiv2020

Dynamic Context-guided Capsule Network for Multimodal Machine Translation

Multimodal machine translation (MMT), which mainly focuses on enhancing text-only translation with visual features, has attracted considerable attention from both computer vision and natural language processing communities. Most current MMT models resort to attention mechanism, global context modeling or multimodal joint representation learning to utilize visual features. However, the attention mechanism lacks sufficient semantic interactions between modalities while the other two provide fixed visual context, which is unsuitable for modeling the observed variability when generating translation. To address the above issues, in this paper, we propose a novel Dynamic Context-guided Capsule Network (DCCN) for MMT. Specifically, at each timestep of decoding, we first employ the conventional source-target attention to produce a timestep-specific source-side context vector. Next, DCCN takes this vector as input and uses it to guide the iterative extraction of related visual features via a context-guided dynamic routing mechanism. Particularly, we represent the input image with global and regional visual features, we introduce two parallel DCCNs to model multimodal context vectors with visual features at different granularities. Finally, we obtain two multimodal context vectors, which are fused and incorporated into the decoder for the prediction of the target word. Experimental results on the Multi30K dataset of English-to-German and English-to-French translation demonstrate the superiority of DCCN. Our code is available on https://github.com/DeepLearnXMU/MM-DCCN.

cs.CL↗

arXiv2020

Learning to Localize Actions from Moments

With the knowledge of action moments (i.e., trimmed video clips that each contains an action instance), humans could routinely localize an action temporally in an untrimmed video. Nevertheless, most practical methods still require all training videos to be labeled with temporal annotations (action category and temporal boundary) and develop the models in a fully-supervised manner, despite expensive labeling efforts and inapplicable to new categories. In this paper, we introduce a new design of transfer learning type to learn action localization for a large set of action categories, but only on action moments from the categories of interest and temporal annotations of untrimmed videos from a small set of action classes. Specifically, we present Action Herald Networks (AherNet) that integrate such design into an one-stage action localization framework. Technically, a weight transfer function is uniquely devised to build the transformation between classification of action moments or foreground video segments and action localization in synthetic contextual moments or untrimmed videos. The context of each moment is learnt through the adversarial mechanism to differentiate the generated features from those of background in untrimmed videos. Extensive experiments are conducted on the learning both across the splits of ActivityNet v1.3 and from THUMOS14 to ActivityNet v1.3. Our AherNet demonstrates the superiority even comparing to most fully-supervised action localization methods. More remarkably, we train AherNet to localize actions from 600 categories on the leverage of action moments in Kinetics-600 and temporal annotations from 200 classes in ActivityNet v1.3. Source code and data are available at \url{https://github.com/FuchenUSTC/AherNet}.

cs.CV↗

arXiv2020

A Smartphone-based System for Real-time Early Childhood Caries Diagnosis

Early childhood caries (ECC) is the most common, yet preventable chronic disease in children under the age of 6. Treatments on severe ECC are extremely expensive and unaffordable for socioeconomically disadvantaged families. The identification of ECC in an early stage usually requires expertise in the field, and hence is often ignored by parents. Therefore, early prevention strategies and easy-to-adopt diagnosis techniques are desired. In this study, we propose a multistage deep learning-based system for cavity detection. We create a dataset containing RGB oral images labeled manually by dental practitioners. We then investigate the effectiveness of different deep learning models on the dataset. Furthermore, we integrate the deep learning system into an easy-to-use mobile application that can diagnose ECC from an early stage and provide real-time results to untrained users.

cs.CV↗