Search

Recent years have witnessed the emergence of many new mobile apps and user-centered systems that interact with users by offering choices with rewards. These applications have been promising to address challenging societal problems such as congestion in transportation and behavior changes for healthier lifestyles. Considerable research efforts have been devoted to model the user behaviors in these new applications. However, as real-world user data is often prone to data corruptions, the success of these models hinges on a robust learning method. Building on the recently proposed Latent Decision Threshold model, this article shows that, among the existing robust learning frameworks, the L0-norm-based framework can outperform other state-of-the-art methods in terms of prediction accuracy and model estimation. And based on the L0-norm framework, we further develop a user screening algorithm to identify potential bad actors. [ABSTRACT FROM AUTHOR]

Objective Artificial intelligence (AI) detects heart disease from images of electrocardiograms (ECGs). However, traditional supervised learning is limited by the need for large amounts of labeled data. We report the development of Biometric Contrastive Learning (BCL), a self-supervised pretraining approach for label-efficient deep learning on ECG images. Materials and Methods Using pairs of ECGs from 78 288 individuals from Yale (2000-2015), we trained a convolutional neural network to identify temporally separated ECG pairs that varied in layouts from the same patient. We fine-tuned BCL-pretrained models to detect atrial fibrillation (AF), gender, and LVEF < 40%, using ECGs from 2015 to 2021. We externally tested the models in cohorts from Germany and the United States. We compared BCL with ImageNet initialization and general-purpose self-supervised contrastive learning for images (simCLR). Results While with 100% labeled training data, BCL performed similarly to other approaches for detecting AF/Gender/LVEF < 40% with an AUROC of 0.98/0.90/0.90 in the held-out test sets, it consistently outperformed other methods with smaller proportions of labeled data, reaching equivalent performance at 50% of data. With 0.1% data, BCL achieved AUROC of 0.88/0.79/0.75, compared with 0.51/0.52/0.60 (ImageNet) and 0.61/0.53/0.49 (simCLR). In external validation, BCL outperformed other methods even at 100% labeled training data, with an AUROC of 0.88/0.88 for Gender and LVEF < 40% compared with 0.83/0.83 (ImageNet) and 0.84/0.83 (simCLR). Discussion and Conclusion A pretraining strategy that leverages biometric signatures of different ECGs from the same patient enhances the efficiency of developing AI models for ECG images. This represents a major advance in detecting disorders from ECG images with limited labeled data. [ABSTRACT FROM AUTHOR]

Background and Aims Early diagnosis of aortic stenosis (AS) is critical to prevent morbidity and mortality but requires skilled examination with Doppler imaging. This study reports the development and validation of a novel deep learning model that relies on two-dimensional (2D) parasternal long axis videos from transthoracic echocardiography without Doppler imaging to identify severe AS, suitable for point-of-care ultrasonography. Methods and results In a training set of 5257 studies (17 570 videos) from 2016 to 2020 [Yale-New Haven Hospital (YNHH), Connecticut], an ensemble of three-dimensional convolutional neural networks was developed to detect severe AS, leveraging self-supervised contrastive pretraining for label-efficient model development. This deep learning model was validated in a temporally distinct set of 2040 consecutive studies from 2021 from YNHH as well as two geographically distinct cohorts of 4226 and 3072 studies, from California and other hospitals in New England, respectively. The deep learning model achieved an area under the receiver operating characteristic curve (AUROC) of 0.978 (95% CI: 0.966, 0.988) for detecting severe AS in the temporally distinct test set, maintaining its diagnostic performance in geographically distinct cohorts [0.952 AUROC (95% CI: 0.941, 0.963) in California and 0.942 AUROC (95% CI: 0.909, 0.966) in New England]. The model was interpretable with saliency maps identifying the aortic valve, mitral annulus, and left atrium as the predictive regions. Among non-severe AS cases, predicted probabilities were associated with worse quantitative metrics of AS suggesting an association with various stages of AS severity. Conclusion This study developed and externally validated an automated approach for severe AS detection using single-view 2D echocardiography, with potential utility for point-of-care screening. [ABSTRACT FROM AUTHOR]

Aims: This metabolomic study aimed to evaluate the role of N‐acetylneuraminic acid (Neu5Ac) in the neurological deficits of normal pressure hydrocephalus (NPH) and its potential therapeutic effect. Methods: We analyzed the metabolic profiles of NPH using cerebrospinal fluid with multivariate and univariate statistical analyses in a set of 42 NPH patients and 38 controls. We further correlated the levels of differential metabolites with severity‐related clinical parameters, including the normal pressure hydrocephalus grading scale (NPHGS). We then established kaolin‐induced hydrocephalus in mice and treated them using N‐acetylmannosamine (ManNAc), a precursor of Neu5Ac. We examined brain Neu5Ac, astrocyte polarization, demyelination, and neurobehavioral outcomes to explore its therapeutic effect. Results: Three metabolites were significantly altered in NPH patients. Only decreased Neu5Ac levels were correlated with NPHGS scores. Decreased brain Neu5Ac levels have been observed in hydrocephalic mice. Increasing brain Neu5Ac by ManNAc suppressed the activation of astrocytes and promoted their transition from A1 to A2 polarization. ManNAc also attenuated the periventricular white matter demyelination and improved neurobehavioral outcomes in hydrocephalic mice. Conclusion: Increasing brain Neu5Ac improved the neurological outcomes associated with the regulation of astrocyte polarization and the suppression of demyelination in hydrocephalic mice, which may be a potential therapeutic strategy for NPH. [ABSTRACT FROM AUTHOR]

Dynamic artistic text style transfer aims to migrate the style in terms of both the appearance and motion patterns from a reference style video to the target text to create artistic text animation. Recent researches have improved the usability of transfer models by introducing texture control. However, it remains an important open challenge to investigate the control of the stylistic degree with respect to shape deformation. In this paper, we explore a new problem of dynamic artistic text style transfer with glyph stylistic degree control. The key idea is to build multi-scale glyph-style shape mappings through a novel bidirectional shape matching framework. Following this idea, we first introduce a scale-ware Shape-Matching GAN to learn such mappings to simultaneously model the style shape features at multiple scales and transfer them onto the target glyph. Furthermore, an advanced Shape-Matching GAN++ is proposed to animate a static text image based on the reference style video. Our Shape-Matching GAN++ characterizes the short-term consistency of motion patterns via shape matchings within consecutive frames, which are propagated to achieve effective long-term consistency. Experiments show that the proposed method outperforms previous state-of-the-arts both qualitatively and quantitatively, and generate high-quality and controllable artistic text. [ABSTRACT FROM AUTHOR]

Low-light images captured in the real world are inevitably corrupted by sensor noise. Such noise is spatially variant and highly dependent on the underlying pixel intensity, deviating from the oversimplified assumptions in conventional denoising. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework. For the real low-light noise removal part, we customize a self-supervised denoising model that can easily be adapted without referring to clean ground-truth images. For the light enhancement part, we also improve the design of a state-of-the-art backbone. The two parts are then joint formulated into one principled plug-and-play optimization. Our approach is compared against state-of-the-art low-light enhancement methods both qualitatively and quantitatively. Besides standard benchmarks, we further collect and test on a new realistic low-light mobile photography dataset (RLMP), whose mobile-captured photos display heavier realistic noise than those taken by high-quality cameras. CERL consistently produces the most visually pleasing and artifact-free results across all experiments. Our RLMP dataset and codes are available at: https://github.com/VITA-Group/CERL. [ABSTRACT FROM AUTHOR]

In this Special Section of the IEEE Transactions on Circuits and Systems for Video Technology, it is our honor to present emerging advanced machine learning and data analytics algorithms aiming at catalyzing synergies among image/video processing, text/speech understanding, and multimodal learning in biomedical informatics. Our goals are to 1) introduce novel data-driven models to accelerate knowledge discovery in biomedicine through the seamless integration of medical data collected from imaging systems, laboratory and wearable devices, as well as other related medical devices; 2) promote the development of new multi-modal learning systems to enhance the healthcare quality and patient safety; and 3) promote new applications in biomedical informatics that can leverage or benefits from the integration of multi-modal data and machine learning. [ABSTRACT FROM AUTHOR]

We investigate privacy-preserving, video-based action recognition in deep learning, a problem with growing importance in smart camera applications. A novel adversarial training framework is formulated to learn an anonymization transform for input videos such that the trade-off between target utility task performance and the associated privacy budgets is explicitly optimized on the anonymized videos. Notably, the privacy budget, often defined and measured in task-driven contexts, cannot be reliably indicated using any single model performance because strong protection of privacy should sustain against any malicious model that tries to steal private information. To tackle this problem, we propose two new optimization strategies of model restarting and model ensemble to achieve stronger universal privacy protection against any attacker models. Extensive experiments have been carried out and analyzed. On the other hand, given few public datasets available with both utility and privacy labels, the data-driven (supervised) learning cannot exert its full power on this task. We first discuss an innovative heuristic of cross-dataset training and evaluation, enabling the use of multiple single-task datasets (one with target task labels and the other with privacy labels) in our problem. To further address this dataset challenge, we have constructed a new dataset, termed PA-HMDB51, with both target task labels (action) and selected privacy attributes (skin color, face, gender, nudity, and relationship) annotated on a per-frame basis. This first-of-its-kind video dataset and evaluation protocol can greatly facilitate visual privacy research and open up other opportunities. Our codes, models, and the PA-HMDB51 dataset are available at: https://github.com/VITA-Group/PA-HMDB51 [ABSTRACT FROM AUTHOR]

What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressing need for the development of algorithms that are designed for the joint problem of improving visual appearance and recognition, which will be an enabling factor for the deployment of visual recognition tools in many real-world scenarios. To address this, we introduce the UG $^2$ 2 dataset as a large-scale benchmark composed of video imagery captured under challenging conditions, and two enhancement tasks designed to test algorithmic impact on visual quality and automatic object recognition. Furthermore, we propose a set of metrics to evaluate the joint improvement of such tasks as well as individual algorithmic advances, including a novel psychophysics-based evaluation regime for human assessment and a realistic set of quantitative measures for object recognition performance. We introduce six new algorithms for image restoration or enhancement, which were created as part of the IARPA sponsored UG $^2$ 2 Challenge workshop held at CVPR 2018. Under the proposed evaluation regime, we present an in-depth analysis of these algorithms and a host of deep learning-based and classic baseline approaches. From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area. [ABSTRACT FROM AUTHOR]

Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendously growing demand for bringing DNN-powered intelligence into mobile platforms. While the potential of deploying DNNs on resource-constrained platforms has been demonstrated by DNN compression techniques, the current practice suffers from two limitations: 1) merely stand-alone compression schemes are investigated even though each compression technique only suit for certain types of DNN layers; and 2) mostly compression techniques are optimized for DNNs’ inference accuracy, without explicitly considering other application-driven system performance (e.g., latency and energy cost) and the varying resource availability across platforms (e.g., storage and processing capability). To this end, we propose AdaDeep, a usage-driven, automated DNN compression framework for systematically exploring the desired trade-off between performance and resource constraints, from a holistic system level. Specifically, in a layer-wise manner, AdaDeep automatically selects the most suitable combination of compression techniques and the corresponding compression hyperparameters for a given DNN. Thorough evaluations on six datasets and across twelve devices demonstrate that ${\sf AdaDeep}$ AdaDeep can achieve up to $18.6\times$ 18. 6 × latency reduction, $9.8\times$ 9. 8 × energy-efficiency improvement, and $37.3\times$ 37. 3 × storage reduction in DNNs while incurring negligible accuracy loss. Furthermore, ${\sf AdaDeep}$ AdaDeep also uncovers multiple novel combinations of compression techniques. [ABSTRACT FROM AUTHOR]

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a self-regularized perceptual loss fusion, and the attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. Our codes and pre-trained models are available at: https://github.com/VITA-Group/EnlightenGAN. [ABSTRACT FROM AUTHOR]

Classification is a critical, widely employed type of hyperspectral image (HSI) processing. Recently, deep learning models have been attracting more attention within the hyperspectral remote-sensing community due to their improved classification performance. Among them, recurrent neural networks (RNNs), which were initially used to handle sequential data, have been applied to HSI classification with promising results. The key point for such RNN-based models in a classification context is the extraction of a sequential feature for each individual pixel in a HSI. One popular strategy is to first extract similar pixels compared with a target pixel from the HSI, and then use those similar pixels to encode its sequential feature. However, the computational cost is tremendous, especially if such similarity-calculation search is done on the whole image. In this article, inspired by our previous work regarding similarity measurement-based sequential feature construction, a faster sequential feature extraction framework for long short-term memory (LSTM)-based HSI classification is proposed, where object-based segmentation method is employed for the purpose of imposing spatial constraints and computational acceleration. Within the proposed framework, both the local segment containing the target pixel and nonlocal segments are considered. For a target pixel, similar segments are selected first based on segment-based features, and then similar pixels from selected segments are extracted to construct a sequential feature. During pixel-wise similarity measurement, both spectral and spatial information are considered in such computation. Experimental results on three benchmark HSI data sets illustrate that the proposed methods achieve promising classification performance with markedly lower computation-time cost. [ABSTRACT FROM AUTHOR]

Idiopathic normal pressure hydrocephalus (iNPH), the most common type of adult‐onset hydrocephalus, is a potentially reversible neuropsychiatric entity characterized by dilated ventricles, cognitive deficit, gait apraxia, and urinary incontinence. Despite its relatively typical imaging features and clinical symptoms, the pathogenesis and pathophysiology of iNPH remain unclear. In this review, we summarize current pathogenetic conceptions of iNPH and its pathophysiological features that lead to neurological deficits. The common consensus is that ventriculomegaly resulting from cerebrospinal fluid (CSF) dynamics could initiate a vicious cycle of neurological damages in iNPH. Pathophysiological factors including hypoperfusion, glymphatic impairment, disturbance of metabolism, astrogliosis, neuroinflammation, and blood‐brain barrier disruption jointly cause white matter and gray matter lesions, and eventually lead to various iNPH symptoms. Also, we review the current treatment options and discuss the prospective treatment strategies for iNPH. CSF diversion with ventriculoperitoneal or lumboperitonealshunts remains as the standard therapy, while its complications prompt attempts to refine shunt insertion and develop new therapeutic procedures. Recent progress on advanced biomaterials and improved understanding of pathogenesis offers new avenues to treat iNPH. [ABSTRACT FROM AUTHOR]

Existing enhancement methods are empirically expected to help the high-level end computer vision task: however, that is observed to not always be the case in practice. We focus on object or face detection in poor visibility enhancements caused by bad weathers (haze, rain) and low light conditions. To provide a more thorough examination and fair comparison, we introduce three benchmark sets collected in real-world hazy, rainy, and low-light conditions, respectively, with annotated objects/faces. We launched the UG2+ challenge Track 2 competition in IEEE CVPR 2019, aiming to evoke a comprehensive discussion and exploration about whether and how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios. To our best knowledge, this is the first and currently largest effort of its kind. Baseline results by cascading existing enhancement and detection models are reported, indicating the highly challenging nature of our new data as well as the large room for further technical innovations. Thanks to a large participation from the research community, we are able to analyze representative team solutions, striving to better identify the strengths and limitations of existing mindsets as well as the future directions. [ABSTRACT FROM AUTHOR]

Image denoising and high-level vision tasks are usually handled independently in the conventional practice of computer vision, and their connection is fragile. In this paper, we cope with the two jointly and explore the mutual influence between them with the focus on two questions, namely (1) how image denoising can help improving high-level vision tasks, and (2) how the semantic information from high-level vision tasks can be used to guide image denoising. First for image denoising we propose a convolutional neural network in which convolutions are conducted in various spatial resolutions via downsampling and upsampling operations in order to fuse and exploit contextual information on different scales. Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation. We experimentally show that on one hand, the proposed denoiser has the generality to overcome the performance degradation of different high-level vision tasks. On the other hand, with the guidance of high-level vision information, the denoising network produces more visually appealing results. Extensive experiments demonstrate the benefit of exploiting image semantics simultaneously for image denoising and high-level vision tasks via deep learning. The code is available online: https://github.com/Ding-Liu/DeepDenoising [ABSTRACT FROM AUTHOR]

Objectives: The aim of this study wasto investigate the efficacy of tacrolimus treatment in patients with refractory generalized myasthenia gravis (MG) and explore its impact on lymphocytic phenotypes and related cytokines mRNA expression. Methods: A total of 24 refractory generalized MG patients were enrolled. Before treatment and at 2, 6, and 12 months after tacrolimus treatment, the therapeutic effect was evaluated by the quantitative MG score of the Myasthenia Gravis Foundation of America (QMG), Manual Muscle Test (MMT), MG-specific Activities of Daily Living (MG-ADL), 15-item Myasthenia Gravis Quality-of-Life Scale (MG-QOL15), and changes of prednisone dosage. Also, we used the flow cytometer for the lymphocytic immunophenotyping and real-time PCR for the qualification of cytokine mRNA in peripheral blood mononuclear cells (PBMCs) at different time points during the treatment. Results: Significantly decreased QMG, MMT, MG-ADL, and MG-QOL15 were observed at all time points during the tacrolimus treatment. The dosage of prednisone also reduced at the end of the observation period with only 6 adverse events reported. The immunological impact of tacrolimus was revealed by reduced percentages of Tfh, Breg, CD19+BAFF-R+ B cells, and increased percentages of Treg cells as well as down-regulated expression of IL-2, IL-4, IL-10, and IL-13 mRNA levels in PBMCs during the treatment. Conclusion: Our study indicated the clinical efficacy of tacrolimus in patients with refractory generalized MG. The underlying immunoregulatory mechanism of tacrolimus may involve alterations in the phenotypes of peripheral blood lymphocytes and Th1/Th2-related cytokine expression of PBMCs. [ABSTRACT FROM AUTHOR]

State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things (IoT) applications. We propose a dual dynamic inference (DDI) framework that highlights the following aspects: 1) we integrate both input-dependent and resource-dependent dynamic inference mechanisms under a unified framework in order to fit the varying IoT resource requirements in practice. DDI is able to both constantly suppress unnecessary costs for easy samples, and to halt inference for all samples to meet hard resource constraints enforced; 2) we propose a flexible multi-grained learning to skip (MGL2S) approach for input-dependent inference which allows simultaneous layer-wise and channel-wise skipping; 3) we extend DDI to complex CNN backbones such as DenseNet and show that DDI can be applied towards optimizing any specific resource goals including inference latency and energy cost. Extensive experiments demonstrate the superior inference accuracy-resource trade-off achieved by DDI, as well as the flexibility to control such a trade-off as compared to existing peer methods. Specifically, DDI can achieve up to 4 times computational savings with the same or even higher accuracy as compared to existing competitive baselines. [ABSTRACT FROM AUTHOR]

The thresholded feature has recently emerged as an extremely efficient, yet rough empirical approximation, of the time-consuming sparse coding inference process. Such an approximation has not yet been rigorously examined, and standard dictionaries often lead to non-optimal performance when used for computing thresholded features. In this paper, we first present two theoretical recovery guarantees for the thresholded feature to exactly recover the nonzero support of the sparse code. Motivated by them, we then formulate the Dictionary Learning for Thresholded Features (DLTF) model, which learns an optimized dictionary for applying the thresholded feature. In particular, for the $(k, 2)$ norm involved, a novel proximal operator with log-linear time complexity $O(m\log m)$ is derived. We evaluate the performance of DLTF on a vast range of synthetic and real-data tasks, where DLTF demonstrates remarkable efficiency, effectiveness, and robustness in all experiments. In addition, we briefly discuss the potential link between DLTF and deep learning building blocks. [ABSTRACT FROM AUTHOR]

Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, the traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explore the potential of CSC in sparse-view CT reconstruction. By directly working on the whole image, without the necessity of dividing the image into overlapped patches in DL-based methods, the proposed methods can maintain more details and avoid artifacts caused by patch aggregation. With predetermined filters, an alternating scheme is developed to optimize the objective function. Extensive experiments with simulated and real CT data were performed to validate the effectiveness of the proposed methods. The qualitative and quantitative results demonstrate that the proposed methods achieve better performance than the several existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Motivation Drug discovery demands rapid quantification of compound–protein interaction (CPI). However, there is a lack of methods that can predict compound–protein affinity from sequences alone with high applicability, accuracy and interpretability. Results We present a seamless integration of domain knowledges and learning-based approaches. Under novel representations of structurally annotated protein sequences, a semi-supervised deep learning model that unifies recurrent and convolutional neural networks has been proposed to exploit both unlabeled and labeled data, for jointly encoding molecular representations and predicting affinities. Our representations and models outperform conventional options in achieving relative error in IC50 within 5-fold for test cases and 20-fold for protein classes not included for training. Performances for new protein classes with few labeled data are further improved by transfer learning. Furthermore, separate and joint attention mechanisms are developed and embedded to our model to add to its interpretability, as illustrated in case studies for predicting and explaining selective drug–target interactions. Lastly, alternative representations using protein sequences or compound graphs and a unified RNN/GCNN-CNN model using graph CNN (GCNN) are also explored to reveal algorithmic challenges ahead. Availability and implementation Data and source codes are available at https://github.com/Shen-Lab/DeepAffinity. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage. While deep neural networks have been extensively exploited in the techniques of low-quality image restoration and high-quality image recognition tasks, respectively, few studies have been done on the important problem of recognition from very low-quality images. This paper proposes a deep learning-based framework for improving the performance of image and video recognition models under adverse conditions, using robust adverse pre-training or its aggressive variant. The robust adverse pre-training algorithms leverage the power of pre-training and generalize the conventional unsupervised pre-training and data augmentation methods. We further develop a transfer learning approach to cope with real-world datasets of unknown adverse conditions. The proposed framework is comprehensively evaluated on a number of image and video recognition benchmarks, and obtains significant performance improvements under various single or mixed adverse conditions. Our visualization and analysis further add to the explainability of the results. [ABSTRACT FROM AUTHOR]

Minimum-cost flow algorithms have recently achieved state-of-the-art results in multi-object tracking. However, they rely on the whole image sequence as input. When deployed in real-time applications or in distributed settings, these algorithms first operate on short batches of frames and then stitch the results into full trajectories. This decoupled strategy is prone to errors because the batch-based tracking errors may propagate to the final trajectories and cannot be corrected by other batches. In this paper, we propose a greedy batch-based minimum-cost flow approach for tracking multiple objects. Unlike existing approaches that conduct batch-based tracking and stitching sequentially, we optimize consecutive batches jointly so that the tracking results on one batch may benefit the results on the other. Specifically, we apply a generalized minimum-cost flows (MCF) algorithm on each batch and generate a set of conflicting trajectories. These trajectories comprise the ones with high probabilities, but also those with low probabilities potentially missed by detectors and trackers. We then apply the generalized MCF again to obtain the optimal matching between trajectories from consecutive batches. Our proposed approach is simple, effective, and does not require training. We demonstrate the power of our approach on data sets of different scenarios. [ABSTRACT FROM PUBLISHER]