Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation
University of Chinese Academy of Sciences（中国科学院大学）；The Institute of Microelectronics, Tsinghua University（清华大学微电子研究所）；Chinese Academy of Sciences Artificial Intelligence Research（中国科学院人工智能研究院）
This paper proposes a novel model for video generation and especially makes the attempt to deal with the problem of video generation from text descriptions, i.e., synthesizing realistic videos conditioned on given texts. Existing video generation methods cannot be easily adapted to handle this task well, due to the frame discontinuity issue and their text-free generation schemes. To address these problems, we propose a recurrent deconvolutional generative adversarial network (RD-GAN), which includes a recurrent deconvolutional network (RDN) as the generator and a 3D convolutional neural network (3D-CNN) as the discriminator. The RDN is a deconvolutional version of conventional recurrent neural network, which can well model the long-range temporal dependency of generated video frames and make good use of conditional information. The proposed model can be jointly trained by pushing the RDN to generate realistic videos so that the 3D-CNN cannot distinguish them from real ones. We apply the proposed RD-GAN to a series of tasks including conventional video generation, conditional video generation, video prediction and video classification, and demonstrate its effectiveness by achieving well performance.
Sun Yat-Sen University（中山大学）；National University of Singapore（新加坡国立大学）；Nanjing University of Science and Technology（南京理工大学）
We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures. The pipeline of this architecture consists of three parts. Through the first part, we encode an input face image to resolution-preserved deconvolutional feature maps via a deep network with stacked convolutional and deconvolutional layers. Then, in the second part, we estimate the initial coordinates of the facial key points by an additional convolutional layer on top of these deconvolutional feature …
University of Trento（特伦托大学）；EPFL（洛桑联邦理工学院）；Inria（法国国家信息与自动化研究所）；Grenoble-Alpes University（格勒诺布尔阿尔卑斯大学）；Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会）
Each smile is unique: one person surely smiles in different ways (e.g., closing/opening the eyes or mouth). Given one input image of a neutral face, can we generate multiple smile videos with distinctive characteristics? To tackle this one-to-many video generation problem, we propose a novel deep learning architecture named Conditional Multi-Mode Network (CMM-Net). To better encode the dynamics of facial expressions, CMM-Net explicitly exploits facial landmarks for generating smile sequences. Specifically, a variational auto-encoder is used to learn a facial landmark embedding. This single emb…
CRCV, University of Central Florida（中佛罗里达大学计算机视觉研究中心）；National University of Singapore（新加坡国立大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
We focus on the problem of novel-view human action synthesis. Given an action video, the goal is to generate the same action from an unseen viewpoint. Naturally, novel view video synthesis is more challenging than image synthesis. It requires the synthesis of a sequence of realistic frames with temporal coherency. Besides, transferring the different actions to a novel target view requires awareness of action category and viewpoint change simultaneously. To address these challenges, we propose a novel framework named Pose-guided Action Separable Generative Adversarial Net (PAS-GAN), which utili…
ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking
Huazhong University of Science and Technology（华中科技大学）；Jiangxi University of Water Resources and Electric Power（江西水利电力大学）；Zhongnan University of Economics and Law（中南财经政法大学）
Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction
Beijing Institute of Technology（北京理工大学）；China Mobile (Suzhou) Software Technology Co., Ltd.（中国移动（苏州）软件技术有限公司）；Anhui University（安徽大学）；Beijing Normal University（北京师范大学）
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；University of Trento（特伦托大学）
Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a single image, performing a series of motions exemplified by an auxiliary (driving) video. Our GAN-based architecture, DwNet, leverages dense intermediate pose-guided representation and refinement process to warp the required subject appearance, in the form of the texture, from a source image into a desired pose. Temporal consistency is maintained by further …
Recent deep learning based salient object detection methods which utilize both saliency and boundary features have achieved remarkable performance. However, most of them ignore the complementarity between saliency features and boundary features, thus get worse predictions in scenes with low contrast between foreground and background. To address this issue, we propose a novel Recurrent Two-Stream Guided Refinement Network (RTGRNet) that consists of iterating Two-Stream Guided Refinement Modules (TGRMs). TGRM consists of a Guide Block and two feature streams: saliency and boundary, the Guide Blo…
Peking University（北京大学）；National University of Singapore（新加坡国立大学）；Snapchat Inc.（Snapchat公司）
In this work, we consider the image super-resolution (SR) problem. The main challenge of image SR is to recover high-frequency details of a low-resolution (LR) image that are important for human perception. To address this essentially ill-posed problem, we introduce a Deep Edge Guided REcurrent rEsidual~(DEGREE) network to progressively recover the high-frequency details. Different from most of existing methods that aim at predicting high-resolution (HR) images directly, DEGREE investigates an alternative route to recover the difference between a pair of LR and HR images by recurrent residual …
Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR)（德国航空航天中心（DLR）遥感技术研究所（IMF））；Signal Processing in Earth Observation (SiPEO), Technical University of Munich (TUM)（慕尼黑工业大学（TUM）地球观测信号处理（SiPEO））
Semantic segmentation in high resolution remote sensing images is a fundamental and challenging task. Convolutional neural networks (CNNs), such as fully convolutional network (FCN) and SegNet, have shown outstanding performance in many segmentation tasks. One key pillar of these successes is mining useful information from features in convolutional layers for producing high resolution segmentation maps. For example, FCN nonlinearly combines high-level features extracted from last convolutional layers; whereas SegNet utilizes a deconvolutional network which takes as input only coarse, high-leve…
Understanding the world around us and making decisions about the future is a critical component to human intelligence. As autonomous systems continue to develop, their ability to reason about the future will be the key to their success. Semantic anticipation is a relatively under-explored area for which autonomous vehicles could take advantage of (e.g., forecasting pedestrian trajectories). Motivated by the need for real-time prediction in autonomous systems, we propose to decompose the challenging semantic forecasting task into two subtasks: current frame segmentation and future optical flow …
This paper aims at task-oriented action prediction, i.e., predicting a sequence of actions towards accomplishing a specific task under a certain scene, which is a new problem in computer vision research. The main challenges lie in how to model task-specific knowledge and integrate it in the learning procedure. In this work, we propose to train a recurrent long-short term memory (LSTM) network for handling this problem, i.e., taking a scene image (including pre-located objects) and the specified task as input and recurrently predicting action sequences. However, training such a network usually …
Shanghai Jiao Tong University（上海交通大学）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属瑞金医院）；Rutgers University（罗格斯大学）
Pancreas segmentation in medical imaging data is of great significance for clinical pancreas diagnostics and treatment. However, the large population variations in the pancreas shape and volume cause enormous segmentation difficulties, even for state-of-the-art algorithms utilizing fully-convolutional neural networks (FCNs). Specifically, pancreas segmentation suffers from the loss of spatial information in 2D methods, and the high computational cost of 3D methods. To alleviate these problems, we propose a probabilistic-map-guided bi-directional recurrent UNet (PBR-UNet) architecture, which fu…
University of Manitoba（曼尼托巴大学）；Huawei Technologies（华为技术有限公司）
We consider the problem of sentence specified dynamic video thumbnail generation. Given an input video and a user query sentence, the goal is to generate a video thumbnail that not only provides the preview of the video content, but also semantically corresponds to the sentence. In this paper, we propose a sentence guided temporal modulation (SGTM) mechanism that utilizes the sentence embedding to modulate the normalized temporal activations of the video thumbnail generation network. Unlike the existing state-of-the-art method that uses recurrent architectures, we propose a non-recurrent frame…
Brain segmentation based on multi-atlas guided 3D fully convolutional network ensembles
School of Electronics and Information Technology, Sun Yat-sen University（中山大学电子与信息工程学院）；Department of Electrical and Electronic Engineering, Southern University of Science and Technology（南方科技大学电子与电气工程学院）
A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements. Due to these factors, it has become the norm for modern graphics-heavy websites to transmit low-resolution, low-bytecount image previews (thumbnails) as part of the initial page load process to improve apparent page responsiveness. Increasing thumbnail compression beyond the capabilities of existing codecs is therefore a current research focus, as any byte savings will significantly enhance the experience of mobile device users. Toward thi…
ETH Zurich（苏黎世联邦理工学院）；Meta Inc.（Meta公司）；University of Wurzburg（维尔茨堡大学）
Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the video frame by frame in a recurrent way, which would result in different merits and drawbacks. Typically, the former has the advantage of temporal information fusion. However, it suffers from large model size and intensive memory consumption; the latter has a relatively small model size as it shares parameters across frames; however, it lacks long-range depende…
Northwestern Polytechnical University（西北工业大学）；National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（国家空天地海一体化大数据应用技术国家工程实验室）；The University of Adelaide（阿德莱德大学）；MinSheng FinTech Corp. Ltd.（民生金融科技股份有限公司）
Reading irregular scene text of arbitrary shape in natural images is still a challenging problem, despite the progress made recently. Many existing approaches incorporate sophisticated network structures to handle various shapes, use extra annotations for stronger supervision, or employ hard-to-train recurrent neural networks for sequence modeling. In this work, we propose a simple yet strong approach for scene text recognition. With no need to convert input images to sequence representations, we directly connect two-dimensional CNN features to an attention-based sequence decoder which guided …
School of Biomedical Engineering and Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与成像科学学院）；Department of Women and Children’s Health, School of Life Course Sciences, King’s College London（伦敦国王学院生命历程科学学院妇幼健康系）
Accurately estimating and correcting the motion artifacts are crucial for 3D image reconstruction of the abdominal and in-utero magnetic resonance imaging (MRI). The state-of-art methods are based on slice-to-volume registration (SVR) where multiple 2D image stacks are acquired in three orthogonal orientations. In this work, we present a novel reconstruction pipeline that only needs one orientation of 2D MRI scans and can reconstruct the full high-resolution image without masking or registration steps. The framework consists of two main stages: the respiratory motion estimation using a self-su…
Yale University（耶鲁大学）；Yale School of Medicine（耶鲁大学医学院）
Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain. We propose to model heterogeneous patterns of functional network differences using a demographic-guided attention (DGA) mechanism for recurrent neural network models for prediction from functional magnetic resonance imaging (fMRI) time-series data. The context computed from the DGA head is used to help focus on the appropriate functional networks based on individual demographic information. We demonstrate improved classification on 3 subsets…
Peking University（北京大学）；Shanghai Jiao Tong University（上海交通大学）；Carnegie Mellon University（卡内基梅隆大学）；Beijing Changcheng Aviation Measurement and Control Institute（北京长城航空测控技术研究所）
We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks. Different from current monocular visual odometry methods, our approach is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we propose a dual-branch recurrent network to learn the rotation and translation separately by leveraging current Convolutional Neural Network (CNN) for feature representation and Recurrent Neural Network (RNN) for image sequence reasoning. To enhance the ability of fe…
University of Pittsburgh（匹兹堡大学）；U.S. Geological Survey（美国地质调查局）；University of Minnesota（明尼苏达大学）
This paper proposes a physics-guided machine learning approach that combines advanced machine learning models and physics-based models to improve the prediction of water flow and temperature in river networks. We first build a recurrent graph network model to capture the interactions among multiple segments in the river network. Then we present a pre-training technique which transfers knowledge from physics-based models to initialize the machine learning model and learn the physics of streamflow and thermodynamics. We also propose a new loss function that balances the performance over differen…
Samsung Electronics (China) R&D Center（三星电子（中国）研发中心）；Samsung Electronics, South Korea（三星电子（韩国））
Flow-guided synthesis provides a common framework for frame interpolation, where optical flow is estimated to guide the synthesis of intermediate frames between consecutive inputs. In this paper, we present UPR-Net, a novel Unified Pyramid Recurrent Network for frame interpolation. Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis. At each pyramid level, it leverages estimated bi-directional flow to generate forward-warped representations for frame synthesis; across pyramid levels, it en…
The University of Auckland（奥克兰大学）；Purdue University（普渡大学）；The Australian National University（澳大利亚国立大学）
To make the best use of the underlying structure of faces, the collective information through face datasets and the intermediate estimates during the upsampling process, here we introduce a fully convolutional multi-stage neural network for 4$\times$ super-resolution for face images. We implicitly impose facial component-wise attention maps using a segmentation network to allow our network to focus on face-inherent patterns. Each stage of our network is composed of a stem layer, a residual backbone, and spatial upsampling layers. We recurrently apply stages to reconstruct an intermediate image…
Existing image-text matching approaches typically infer the similarity of an image-text pair by capturing and aggregating the affinities between the text and each independent object of the image. However, they ignore the connections between the objects that are semantically related. These objects may collectively determine whether the image corresponds to a text or not. To address this problem, we propose a Dual Path Recurrent Neural Network (DP-RNN) which processes images and sentences symmetrically by recurrent neural networks (RNN). In particular, given an input image-text pair, our model r…
Low-light images challenge both human perceptions and computer vision algorithms. It is crucial to make algorithms robust to enlighten low-light images for computational photography and computer vision applications such as real-time detection and segmentation. This paper proposes a semantic-guided zero-shot low-light enhancement network (SGZ) which is trained in the absence of paired images, unpaired datasets, and segmentation annotation. Firstly, we design an enhancement factor extraction network using depthwise separable convolution for an efficient estimate of the pixel-wise light deficienc…
Youtube-8M dataset enhances the development of large-scale video recognition technology as ImageNet dataset has encouraged image classification, recognition and detection of artificial intelligence fields. For this large video dataset, it is a challenging task to classify a huge amount of multi-labels. By change of perspective, we propose a novel method by regarding labels as words. In details, we describe online learning approaches to multi-label video classification that are guided by deep recurrent neural networks for video to sentence translator. We designed the translator based on LSTMs a…
Predicting depth from a monocular video sequence is an important task for autonomous driving. Although it has advanced considerably in the past few years, recent methods based on convolutional neural networks (CNNs) discard temporal coherence in the video sequence and estimate depth independently for each frame, which often leads to undesired inconsistent results over time. To address this problem, we propose to memorize temporal consistency in the video sequence, and leverage it for the task of depth prediction. To this end, we introduce a two-stream CNN with a flow-guided memory module, wher…
Fully convolutional networks (FCN) has significantly improved the performance of many pixel-labeling tasks, such as semantic segmentation and depth estimation. However, it still remains non-trivial to thoroughly utilize the multi-level convolutional feature maps and boundary information for salient object detection. In this paper, we propose a novel FCN framework to integrate multi-level convolutional features recurrently with the guidance of object boundary information. First, a deep convolutional network is used to extract multi-level feature maps and separately aggregate them into multiple …
The University of Tokyo（东京大学）；HKUST Guangzhou（香港科技大学（广州））；Huawei（华为）；HKUST（香港科技大学）
Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the information from clear regions in adjacent frames for current frame deblurring. To realize this process, our idea is to detect the pixel-wise blur level of each frame and combine it with video deblurring. To this end, we propose a novel framework that utilizes the motion magnitude prior (MMP) as guidance for efficient deep video deblurring. Specifically, as th…
Detecting dangerous traffic agents in videos captured by vehicle-mounted dashboard cameras (dashcams) is essential to facilitate safe navigation in a complex environment. Accident-related videos are just a minor portion of the driving video big data, and the transient pre-accident processes are highly dynamic and complex. Besides, risky and non-risky traffic agents can be similar in their appearance. These make risky object localization in the driving video particularly challenging. To this end, this paper proposes an attention-guided multistream feature fusion network (AM-Net) to localize dan…
A recurrent structure is a popular framework choice for the task of video super-resolution. The state-of-the-art method BasicVSR adopts bidirectional propagation with feature alignment to effectively exploit information from the entire input video. In this study, we redesign BasicVSR by proposing second-order grid propagation and flow-guided deformable alignment. We show that by empowering the recurrent framework with the enhanced propagation and alignment, one can exploit spatiotemporal information across misaligned video frames more effectively. The new components lead to an improved perform…
Nanjing University of Science and Technology（南京理工大学）；Communication University of China（中国传媒大学）
How to effectively explore the colors of reference exemplars and propagate them to colorize each frame is vital for exemplar-based video colorization. In this paper, we present an effective BiSTNet to explore colors of reference exemplars and utilize them to help video colorization by a bidirectional temporal feature fusion with the guidance of semantic image prior. We first establish the semantic correspondence between each frame and the reference exemplars in deep feature space to explore color information from reference exemplars. Then, to better propagate the colors of reference exemplars …
Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention (FGSW-MSA). For each $query$ element on the blurry reference frame, FGSW-MSA enjoys the guidance of the estimated optical flow to globally sample spatially …
University of Amsterdam（阿姆斯特丹大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
When speakers describe an image, they tend to look at objects before mentioning them. In this paper, we investigate such sequential cross-modal alignment by modelling the image description generation process computationally. We take as our starting point a state-of-the-art image captioning system and develop several model variants that exploit information from human gaze patterns recorded during language production. In particular, we propose the first approach to image description generation where visual processing is modelled $\textit{sequentially}$. Our experiments and analyses confirm that …
Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）
Image-guided adaptive lung radiotherapy requires accurate tumor and organs segmentation from during treatment cone-beam CT (CBCT) images. Thoracic CBCTs are hard to segment because of low soft-tissue contrast, imaging artifacts, respiratory motion, and large treatment induced intra-thoracic anatomic changes. Hence, we developed a novel Patient-specific Anatomic Context and Shape prior or PACS-aware 3D recurrent registration-segmentation network for longitudinal thoracic CBCT segmentation. Segmentation and registration networks were concurrently trained in an end-to-end framework and implemente…
We address the problem of Visual Question Answering (VQA), which requires joint image and language understanding to answer a question about a given photograph. Recent approaches have applied deep image captioning methods based on convolutional-recurrent networks to this problem, but have failed to model spatial inference. To remedy this, we propose a model we call the Spatial Memory Network and apply it to the VQA task. Memory networks are recurrent neural networks with an explicit attention mechanism that selects certain parts of the information stored in memory. Our Spatial Memory Network st…
Shanghai Jiao Tong University（上海交通大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Ruijin Hospital affiliated to Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属瑞金医院）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Mayo Clinic in Arizona（亚利桑那州妙佑医疗国际）；ShanghaiTech University（上海科技大学）
Interventional magnetic resonance imaging (i-MRI) for surgical guidance could help visualize the interventional process such as deep brain stimulation (DBS), improving the surgery performance and patient outcome. Different from retrospective reconstruction in conventional dynamic imaging, i-MRI for DBS has to acquire and reconstruct the interventional images sequentially online. Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling. By using an initializer and C…
To drive safely in complex traffic environments, autonomous vehicles need to make an accurate prediction of the future trajectories of nearby heterogeneous traffic agents (i.e., vehicles, pedestrians, bicyclists, etc). Due to the interactive nature, human drivers are accustomed to infer what the future situations will become if they are going to execute different maneuvers. To fully exploit the impacts of interactions, this paper proposes a ego-planning guided multi-graph convolutional network (EPG-MGCN) to predict the trajectories of heterogeneous agents using both historical trajectory infor…
Yale University（耶鲁大学）；IBM Almaden Research Center（IBM阿尔马登研究中心）；New York University（纽约大学）
Pulmonary Embolism (PE) is a life-threatening disorder associated with high mortality and morbidity. Prompt diagnosis and immediate initiation of therapeutic action is important. We explored a deep learning model to detect PE on volumetric contrast-enhanced chest CT scans using a 2-stage training strategy. First, a residual convolutional neural network (ResNet) was trained using annotated 2D images. In addition to the classification loss, an attention loss was added during training to help the network focus attention on PE. Next, a recurrent network was used to scan sequentially through the fe…
