arXiv subjects

Li Cheng

Publications and source records attributed to Li Cheng.

At least 55 records · Page 3Linked to original sources

arXiv2021

Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction

Predicting human motion from historical pose sequence is crucial for a machine to succeed in intelligent interactions with humans. One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results. Yet there is no effort that investigates across different pose representation schemes. We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. Moreover, recent approaches build upon off-the-shelf RNN units for motion prediction. These approaches process input pose sequence sequentially and inherently have difficulties in capturing long-term dependencies. In this paper, we propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction which simultaneously models local motion contexts and a global context. We further explore a geodesic loss and a forward kinematics loss for the motion prediction task, which have more geometric significance than the widely employed L2 loss. Interestingly, we applied our method to a range of articulate objects including human, fish, and mouse. Empirical results show that our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency, such as retaining natural human-like motions over 50 seconds predictions. Our codes are released.

cs.CV↗

arXiv2021

Action2video: Generating Videos of Human 3D Actions

We aim to tackle the interesting yet challenging problem of generating videos of diverse and natural human motions from prescribed action categories. The key issue lies in the ability to synthesize multiple distinct motion sequences that are realistic in their visual appearances. It is achieved in this paper by a two-step process that maintains internal 3D pose and shape representations, action2motion and motion2video. Action2motion stochastically generates plausible 3D pose sequences of a prescribed action category, which are processed and rendered by motion2video to form 2D videos. Specifically, the Lie algebraic theory is engaged in representing natural human motions following the physical law of human kinematics; a temporal variational auto-encoder (VAE) is developed that encourages diversity of output motions. Moreover, given an additional input image of a clothed human character, an entire pipeline is proposed to extract his/her 3D detailed shape, and to render in videos the plausible motions from different views. This is realized by improving existing methods to extract 3D human shapes and textures from single 2D images, rigging, animating, and rendering to form 2D videos of human motions. It also necessitates the curation and reannotation of 3D human motion datasets for training purpose. Thorough empirical experiments including ablation study, qualitative and quantitative evaluations manifest the applicability of our approach, and demonstrate its competitiveness in addressing related tasks, where components of our approach are compared favorably to the state-of-the-arts.

cs.CV↗

arXiv2021

Self-supervised 3D Human Mesh Recovery from Noisy Point Clouds

This paper presents a novel self-supervised approach to reconstruct human shape and pose from noisy point cloud data. Relying on large amount of dataset with ground-truth annotations, recent learning-based approaches predict correspondences for every vertice on the point cloud; Chamfer distance is usually used to minimize the distance between a deformed template model and the input point cloud. However, Chamfer distance is quite sensitive to noise and outliers, thus could be unreliable to assign correspondences. To address these issues, we model the probability distribution of the input point cloud as generated from a parametric human model under a Gaussian Mixture Model. Instead of explicitly aligning correspondences, we treat the process of correspondence search as an implicit probabilistic association by updating the posterior probability of the template model given the input. A novel self-supervised loss is further derived which penalizes the discrepancy between the deformed template and the input point cloud conditioned on the posterior probability. Our approach is very flexible, which works with both complete point cloud and incomplete ones including even a single depth image as input. Compared to previous self-supervised methods, our method shows the capability to deal with substantial noise and outliers. Extensive experiments conducted on various public synthetic datasets as well as a very noisy real dataset (i.e. CMU Panoptic) demonstrate the superior performance of our approach over the state-of-the-art methods.

cs.CV↗

arXiv2021

3D Pose Estimation and Future Motion Prediction from 2D Images

This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences. Based on Lie algebra pose representation, a novel self-projection mechanism is proposed that naturally preserves human motion kinematics. This is further facilitated by a sequence-to-sequence multi-task architecture based on an encoder-decoder topology, which enables us to tap into the common ground shared by both tasks. Finally, a global refinement module is proposed to boost the performance of our framework. The effectiveness of our approach, called PoseMoNet, is demonstrated by ablation tests and empirical evaluations on Human3.6M and HumanEva-I benchmark, where competitive performance is obtained comparing to the state-of-the-arts.

cs.CV↗

arXiv2021

The RETA Benchmark for Retinal Vascular Tree Analysis

Topological and geometrical analysis of retinal blood vessel is a cost-effective way for early detection of many common diseases. Meanwhile, automated vessel segmentation and vascular tree analysis are still lacking in terms of generalization capability. In this work, we construct a novel benchmark RETA with 81 labeled vessel masks aiming to facilitate retinal vessel analysis. A semi-automated coarse-to-fine workflow is proposed to annotating vessel pixels. During dataset construction, we strived to control inter-annotator variability and intra-annotator variability by performing multi-stage annotation and label disambiguation on self-developed dedicated software. In addition to binary vessel masks, we obtained vessel annotations containing artery/vein masks, vascular skeletons, bifurcations, trees and abnormalities during vessel labelling. Both subjective and objective quality validation of labeled vessel masks have demonstrated significant improved quality over other publicly datasets. The annotation software is also made publicly available for vessel annotation visualization. Users could develop vessel segmentation algorithms or evaluate vessel segmentation performance with our dataset. Moreover, our dataset might be a good research source for cross-modality tubular structure segmentation.

eess.IV↗

arXiv2021

CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a particularly challenging barrier, as it demands sufficient prior experience, enormous effort, intuition, and perhaps some good luck. Meanwhile, neural architecture search has gaining grounds in practical applications as a promising method in tackling the issue of automated search of feasible network structures. In this work, we propose a novel cell-level differentiable architecture search mechanism with early stopping to automate the network design of the tracking module, aiming to adapt backbone features to the objective of Siamese tracking networks during offline training. Besides, the proposed early stopping strategy avoids over-fitting and performance collapse problems leading to generalization improvement. The proposed approach is simple, efficient, and with no need to stack a series of modules to construct a network. Our approach is easy to be incorporated into existing trackers, which is empirically validated using different differentiable architecture search-based methods and tracking objectives. Extensive experimental evaluations demonstrate the superior performance of our approach over five commonly-used benchmarks.

cs.CV↗

arXiv2021

The interaction between phosphorene oxide and the villin headpiece

Phosphorene, a novel member of the two-dimensional nanomaterial family, has been demonstrated a great potential in biomedical applications, such as photothermal therapy, drug delivery and antibacterial. However, phosphorene is unstable and easily oxidized in an aerobic environment. In this paper, using the larger-scale molecular dynamics simulations, we investigated the disruption of phosphorene oxide (PO) to the structure of a model protein, villin headpiece subdomain (HP35). It shows that the disruption of PO nanosheets to protein structure enhances with the increase of the oxidation concentration of PO, but the oxidation mode has almost no effect on the PO-HP35 interaction. At low oxidation concentration, PO is good biocompatibility to HP35. Oxygen atoms filled into the groove region in puckered surface of phosphorene enhances the dispersion interaction between phosphorene and HP35. Thus, oxidation enhances the destructive effect of phosphorene on the structure of HP35. These findings might shed light on understanding the biological toxicity of PO nanosheets and would be helpful for the future potential biomedical applications of PO nanosheets, such as nanodrugs and antibacterial agents.

cond-mat.soft↗

arXiv2021

Understanding the flat band in 1T-TaS2 using a rotated basis

Electronic flat bands serve as a unique platform to achieve strongly-correlated phases. The emergence of a flat band around the Fermi level in 1T-TaS$_2$ in accompany with the development of a $\sqrt{13}\times\sqrt{13}$ charge density wave (CDW) superlattice has long been noticed experimentally, but a transparent theoretical understanding remains elusive. We show that without CDW, the primary feature of the $1\times1$ bands can be fitted by a simple trigonometric function, and physically understood by choosing a rotated $\tilde{t}_{2g}$ basis with the principle axes aligning to the tilted TaS$_6$ octahedron. Using this basis, we trace the band evolution in the $\sqrt{13}\times\sqrt{13}$ superlattice by progressively including different CDW effects. We point out that CDW strongly rehybridizes the three $\tilde{t}_{2g}$ orbitals, which leads to the formation of a well-localized molecular orbital and spawns the flat band.

cond-mat.mtrl-sci↗

arXiv2021

Automated Generation of Accurate \& Fluent Medical X-ray Reports

Our paper focuses on automating the generation of medical reports from chest X-ray image inputs, a critical yet time-consuming task for radiologists. Unlike existing medical re-port generation efforts that tend to produce human-readable reports, we aim to generate medical reports that are both fluent and clinically accurate. This is achieved by our fully differentiable and end-to-end paradigm containing three complementary modules: taking the chest X-ray images and clinical his-tory document of patients as inputs, our classification module produces an internal check-list of disease-related topics, referred to as enriched disease embedding; the embedding representation is then passed to our transformer-based generator, giving rise to the medical reports; meanwhile, our generator also pro-duces the weighted embedding representation, which is fed to our interpreter to ensure consistency with respect to disease-related topics.Our approach achieved promising results on commonly-used metrics concerning language fluency and clinical accuracy. Moreover, noticeable performance gains are consistently ob-served when additional input information is available, such as the clinical document and extra scans of different views.

cs.CL↗

arXiv2021

EventHPE: Event-based 3D Human Pose and Shape Estimation

Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: rather than capturing static body postures, the event signals are best at capturing local motions. This leads us to propose a two-stage deep learning approach, called EventHPE. The first-stage, FlowNet, is trained by unsupervised learning to infer optical flow from events. Both events and optical flow are closely related to human body dynamics, which are fed as input to the ShapeNet in the second stage, to estimate 3D human shapes. To mitigate the discrepancy between image-based flow (optical flow) and shape-based flow (vertices movement of human body shape), a novel flow coherence loss is introduced by exploiting the fact that both flows are originated from the identical human motion. An in-house event-based 3D human dataset is curated that comes with 3D pose and shape annotations, which is by far the largest one to our knowledge. Empirical evaluations on DHP19 dataset and our in-house dataset demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2021

Bidirectional elastic diode with frequency-preserved nonreciprocity

The study of nonreciprocal wave propagation is of great interests for both fundamental research and engineering applications. Here we demonstrate theoretically and experimentally a bidirectional, nonreciprocal, and high-quality diode that can rectify elastic waves in both forward and backward directions in an elastic metamaterial designed to exhibit enhanced nonlinearity of resonances. This diode can preserve or vary frequency, rectify low-frequency long wave with small system size, offer high-quality insulation, can be modulated by amplitude, and break reciprocity of both the total energy and fundamental wave. We report three mechanisms to break reciprocity: the amplitude-dependent bandgap combining interface reflection, chaotic response combining linear bandgap, amplitude-dependent attenuation rate in damping diode. The bidirectional diode paves ways for mutually controlling information/energy transport between two sources, which can be used as new wave insulators.

physics.app-ph↗

arXiv2021

Deep Learning for Visual Tracking: A Comprehensive Survey

Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale benchmark datasets have been established, on which considerable methods have been developed and demonstrated with significant progress in recent years -- predominantly by recent deep learning (DL)-based methods. This survey aims to systematically investigate the current DL-based visual tracking methods, benchmark datasets, and evaluation metrics. It also extensively evaluates and analyzes the leading visual tracking methods. First, the fundamental characteristics, primary motivations, and contributions of DL-based methods are summarized from nine key aspects of: network architecture, network exploitation, network training for visual tracking, network objective, network output, exploitation of correlation filter advantages, aerial-view tracking, long-term tracking, and online tracking. Second, popular visual tracking benchmarks and their respective properties are compared, and their evaluation metrics are summarized. Third, the state-of-the-art DL-based methods are comprehensively examined on a set of well-established benchmarks of OTB2013, OTB2015, VOT2018, LaSOT, UAV123, UAVDT, and VisDrone2019. Finally, by conducting critical analyses of these state-of-the-art trackers quantitatively and qualitatively, their pros and cons under various common scenarios are investigated. It may serve as a gentle use guide for practitioners to weigh when and under what conditions to choose which method(s). It also facilitates a discussion on ongoing issues and sheds light on promising research directions.

cs.CV↗

arXiv2020

Achromatic metasurfaces with inversely customized dispersion for ultra-broadband acoustic beam engineering

Metasurfaces, the ultrathin media with extraordinary wavefront modulation ability, have shown versatile potential in manipulating waves. However, existing acoustic metasurfaces are limited by their narrow-band frequency-dependent capability, which severely hinders their real-world applications that usually require customized dispersion. To address this bottlenecking challenge, we report ultra-broadband achromatic metasurfaces that are capable of delivering arbitrary and frequency-independent wave properties by bottom-up topology optimization. We successively demonstrate three ultra-broadband functionalities, including acoustic beam steering, focusing and levitation, featuring record-breaking relative bandwidths of 93.3%, 120% and 118.9%, respectively. All metasurface elements show novel asymmetric geometries containing multiple scatters, curved air channels and local cavities. Moreover, we reveal that the inversely designed metasurfaces can support integrated internal resonances, bi-anisotropy and multiple scattering, which collectively form the mechanism underpinning the ultra-broadband customized dispersion. Our study opens new horizons for ultra-broadband high-efficiency achromatic functional devices on demand, with promising extension to the optical and elastic achromatic metamaterials.

cond-mat.mtrl-sci↗

arXiv2020

Reconstruct high-resolution multi-focal plane images from a single 2D wide field image

High-resolution 3D medical images are important for analysis and diagnosis, but axial scanning to acquire them is very time-consuming. In this paper, we propose a fast end-to-end multi-focal plane imaging network (MFPINet) to reconstruct high-resolution multi-focal plane images from a single 2D low-resolution wild filed image without relying on scanning. To acquire realistic MFP images fast, the proposed MFPINet adopts generative adversarial network framework and the strategies of post-sampling and refocusing all focal planes at one time. We conduct a series experiments on cytology microscopy images and demonstrate that MFPINet performs well on both axial refocusing and horizontal super resolution. Furthermore, MFPINet is approximately 24 times faster than current refocusing methods for reconstructing the same volume images. The proposed method has the potential to greatly increase the speed of high-resolution 3D imaging and expand the application of low-resolution wide-field images.

eess.IV↗

arXiv2020

COMET: Context-Aware IoU-Guided Network for Small Object Tracking

We consider the problem of tracking an unknown small target from aerial videos of medium to high altitudes. This is a challenging problem, which is even more pronounced in unavoidable scenarios of drastic camera motion and high density. To address this problem, we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-stream network and an offline reference proposal generation strategy. The proposed network fully exploits target-related information by multi-scale feature learning and attention modules. The proposed strategy introduces an efficient sampling strategy to generalize the network on the target and its parts without imposing extra computational complexity during online tracking. These strategies contribute considerably in handling significant occlusions and viewpoint changes. Empirically, COMET outperforms the state-of-the-arts in a range of aerial view datasets that focusing on tracking small objects. Specifically, COMET outperforms the celebrated ATOM tracker by an average margin of 6.2% (and 7%) in precision (and success) score on challenging benchmarks of UAVDT, VisDrone-2019, and Small-90.

cs.CV↗

arXiv2020

Action2Motion: Conditioned Generation of 3D Human Motions

Action recognition is a relatively established task, where givenan input sequence of human motion, the goal is to predict its ac-tion category. This paper, on the other hand, considers a relativelynew problem, which could be thought of as an inverse of actionrecognition: given a prescribed action type, we aim to generateplausible human motion sequences in 3D. Importantly, the set ofgenerated motions are expected to maintain itsdiversityto be ableto explore the entire action-conditioned motion space; meanwhile,each sampled sequence faithfully resembles anaturalhuman bodyarticulation dynamics. Motivated by these objectives, we followthe physics law of human kinematics by adopting the Lie Algebratheory to represent thenaturalhuman motions; we also propose atemporal Variational Auto-Encoder (VAE) that encourages adiversesampling of the motion space. A new 3D human motion dataset, HumanAct12, is also constructed. Empirical experiments overthree distinct human motion datasets (including ours) demonstratethe effectiveness of our approach.

cs.CV↗

arXiv2020

Polarization Human Shape and Pose Dataset

Polarization images are known to be able to capture polarized reflected lights that preserve rich geometric cues of an object, which has motivated its recent applications in reconstructing detailed surface normal of the objects of interest. Meanwhile, inspired by the recent breakthroughs in human shape estimation from a single color image, we attempt to investigate the new question of whether the geometric cues from polarization camera could be leveraged in estimating detailed human body shapes. This has led to the curation of Polarization Human Shape and Pose Dataset (PHSPD), our home-grown polarization image dataset of various human shapes and poses.

cs.CV↗

arXiv2020

3D Human Shape Reconstruction from a Polarization Image

This paper tackles the problem of estimating 3D body shape of clothed humans from single polarized 2D images, i.e. polarization images. Polarization images are known to be able to capture polarized reflected lights that preserve rich geometric cues of an object, which has motivated its recent applications in reconstructing surface normal of the objects of interest. Inspired by the recent advances in human shape estimation from single color images, in this paper, we attempt at estimating human body shapes by leveraging the geometric cues from single polarization images. A dedicated two-stage deep learning approach, SfP, is proposed: given a polarization image, stage one aims at inferring the fined-detailed body surface normal; stage two gears to reconstruct the 3D body shape of clothing details. Empirical evaluations on a synthetic dataset (SURREAL) as well as a real-world dataset (PHSPD) demonstrate the qualitative and quantitative performance of our approach in estimating human poses and shapes. This indicates polarization camera is a promising alternative to the more conventional color or depth imaging for human shape estimation. Further, normal maps inferred from polarization imaging play a significant role in accurately recovering the body shapes of clothed people.

cs.CV↗