arXiv subjects

Long Zhao

Publications and source records attributed to Long Zhao.

79 records · Page 5Linked to original sources

arXiv2019

Cartoonish sketch-based face editing in videos using identity deformation transfer

We address the problem of using hand-drawn sketches to create exaggerated deformations to faces in videos, such as enlarging the shape or modifying the position of eyes or mouth. This task is formulated as a 3D face model reconstruction and deformation problem. We first recover the facial identity and expressions from the video by fitting a face morphable model for each frame. At the same time, user's editing intention is recognized from input sketches as a set of facial modifications. Then a novel identity deformation algorithm is proposed to transfer these facial deformations from 2D space to the 3D facial identity directly while preserving the facial expressions. After an optional stage for further refining the 3D face model, these changes are propagated to the whole video with the modified identity. Both the user study and experimental results demonstrate that our sketching framework can help users effectively edit facial identities in videos, while high consistency and fidelity are ensured at the same time.

cs.CV↗

arXiv2018

Learning to Forecast and Refine Residual Motion for Image-to-Video Generation

We consider the problem of image-to-video translation, where an input image is translated into an output video containing motions of a single object. Recent methods for such problems typically train transformation networks to generate future frames conditioned on the structure sequence. Parallel work has shown that short high-quality motions can be generated by spatiotemporal generative networks that leverage temporal knowledge from the training data. We combine the benefits of both approaches and propose a two-stage generation framework where videos are generated from structures and then refined by temporal signals. To model motions more efficiently, we train networks to learn residual motion between the current and future frames, which avoids learning motion-irrelevant details. We conduct extensive experiments on two image-to-video translation tasks: facial expression retargeting and human pose forecasting. Superior results over the state-of-the-art methods on both tasks demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2018

CR-GAN: Learning Complete Representations for Multi-view Generation

Generating multi-view images from a single-view input is an essential yet challenging problem. It has broad applications in vision, graphics, and robotics. Our study indicates that the widely-used generative adversarial network (GAN) may learn "incomplete" representations due to the single-pathway framework: an encoder-decoder network followed by a discriminator network. We propose CR-GAN to address this problem. In addition to the single reconstruction path, we introduce a generation sideway to maintain the completeness of the learned embedding space. The two learning pathways collaborate and compete in a parameter-sharing manner, yielding considerably improved generalization ability to "unseen" dataset. More importantly, the two-pathway framework makes it possible to combine both labeled and unlabeled data for self-supervised learning, which further enriches the embedding space for realistic generations. The experimental results prove that CR-GAN significantly outperforms state-of-the-art methods, especially when generating from "unseen" inputs in wild conditions.

cs.CV↗

arXiv2017

Complexity/Action duality of shock wave geometry in a massive gravity theory

On the holographic complexity dual to the bulk action, we investigate the action growth for a shock wave geometry in a massive gravity theory within the Wheeler-De Witt (WDW) patch at the late time limit. For a global shock wave, the graviton mass does not affect the action growth in the bulk, i.e. the complexity on the boundary, showing that the action growth (complexity) is the same for both the Einstein gravity and the massive gravity. Nevertheless, for a local shock wave that depends on transverse coordinates, the action growth (complexity) is proportional to the butterfly velocity for the two gravity theories, but the butterfly velocity of the massive gravity theory is smaller than that of the Einstein gravity theory, indicating that the action growth (complexity) of the massive gravity is depressed by the graviton mass. In addition, we extend the black hole thermodynamics of the massive gravity and obtain the right Smarr formula.

hep-th↗

arXiv2017

A Two-Stage Allocation Scheme for Delay-Sensitive Services in Dense Vehicular Networks

Driven by the rapid development of wireless communication system, more and more vehicular services can be efficiently supported via vehicle-to-everything (V2X) communications. In order to allocate radio resource with the reasonable implementation complexity in dense urban intersection, a two-stage allocation algorithm is proposed in this paper, whose main objective is to minimize delay and ensure reliability. In particular, as for the first stage, the allocation policy is based on traffic density information (TDI), which is different from utilizing channel state information (CSI) and queue state information (QSI) in the second stage. Moreover, in order to reflect the influence of TDI on delay, a macroscopic vehicular mobility model is employed in this paper. Simulation results show that the proposed algorithm can acquire an asymptotically optimal performance with the acceptable complexity.

cs.IT↗

arXiv2017

Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning

Weakly-supervised object detection (WOD) is a challenging problems in computer vision. The key problem is to simultaneously infer the exact object locations in the training images and train the object detectors, given only the training images with weak image-level labels. Intuitively, by simulating the selective attention mechanism of human visual system, saliency detection technique can select attractive objects in scenes and thus is a potential way to provide useful priors for WOD. However, the way to adopt saliency detection in WOD is not trivial since the detected saliency region might be possibly highly ambiguous in complex cases. To this end, this paper first comprehensively analyzes the challenges in applying saliency detection to WOD. Then, we make one of the earliest efforts to bridge saliency detection to WOD via the self-paced curriculum learning, which can guide the learning procedure to gradually achieve faithful knowledge of multi-class objects from easy to hard. The experimental results demonstrate that the proposed approach can successfully bridge saliency detection and WOD tasks and achieve the state-of-the-art object detection results under the weak supervision.

cs.CV↗

arXiv2015

Reliable and Efficient Autonomous Driving: the Need for Heterogeneous Vehicular Networks

Autonomous driving technology has been regarded as a promising solution to reduce road accidents and traffic congestion, as well as to optimize the usage of fuel and lane. Reliable and high efficient Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communications are essential to let commercial autonomous driving vehicles be on the road before 2020. The current paper firstly presents the concept of Heterogeneous Vehicular NETworks (HetVNETs) for autonomous driving, in which an improved protocol stack is proposed to satisfy the communication requirements of not only safety but also non-safety services. We then consider and study in detail several typical scenarios for autonomous driving. In order to tackle the potential challenges raised by the autonomous driving vehicles in HetVNETs, new techniques from transmission to networking are proposed as potential solutions.

cs.NI↗