arXiv subjects

Xiao Sun

Publications and source records attributed to Xiao Sun.

136 records · Page 8Linked to original sources

arXiv2019

Explicit Spatiotemporal Joint Relation Learning for Tracking Human Pose

We present a method for human pose tracking that is based on learning spatiotemporal relationships among joints. Beyond generating the heatmap of a joint in a given frame, our system also learns to predict the offset of the joint from a neighboring joint in the frame. Additionally, it is trained to predict the displacement of the joint from its position in the previous frame, in a manner that can account for possibly changing joint appearance, unlike optical flow. These relational cues in the spatial domain and temporal domain are inferred in a robust manner by attending only to relevant areas in the video frames. By explicitly learning and exploiting these joint relationships, our system achieves state-of-the-art performance on standard benchmarks for various pose tracking tasks including 3D body pose tracking in RGB video, 3D hand pose tracking in depth sequences, and 3D hand gesture tracking in RGB video.

cs.CV↗

arXiv2019

Intermultiplet transitions and magnetic long-range order in Sm-based pyrochlores

We present bulk and neutron scattering measurements performed on the isotopically enriched $^{154}\mathrm{Sm_2Ti_2O_7}$ and $^{154}\mathrm{Sm_2Sn_2O_7}$ samples. Both compounds display sharp heat capacity anomalies, at 350 mK and 440 mK, respectively. Inelastic neutron scattering measurements are employed to determine the crystalline electric field (CEF) level scheme, which includes transitions between the ground-state and first excited $J$ multiplets of the $\mathrm{Sm}^{3+}$ ion. To further validate those results, the single-ion magnetic susceptibility of the compounds is calculated and compared with the experimental DC-susceptibility measured in low applied magnetic fields. It is demonstrated that the inclusion of intermultiplet transitions in the CEF analysis is fundamental to the understanding of the intermediate and, more importantly, low temperature magnetic behaviour of the Sm-based pyrochlores. Finally, the heat capacity anomaly is shown to correspond to the onset of an all-in-all-out long-range order in the stannate sample, while in the titanate a dipolar long-range order can be only indirectly inferred.

cond-mat.str-el↗

arXiv2018

Integral Human Pose Regression

State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as not differentiable and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time.

cs.CV↗

arXiv2018

An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge

For the ECCV 2018 PoseTrack Challenge, we present a 3D human pose estimation system based mainly on the integral human pose regression method. We show a comprehensive ablation study to examine the key performance factors of the proposed system. Our system obtains 47mm MPJPE on the CHALL_H80K test dataset, placing second in the ECCV2018 3D human pose estimation challenge. Code will be released to facilitate future work.

cs.CV↗

arXiv2018

A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation

Traditional neural language models tend to generate generic replies with poor logic and no emotion. In this paper, a syntactically constrained bidirectional-asynchronous approach for emotional conversation generation (E-SCBA) is proposed to address this issue. In our model, pre-generated emotion keywords and topic keywords are asynchronously introduced into the process of decoding. It is much different from most existing methods which generate replies from the first word to the last. Through experiments, the results indicate that our approach not only improves the diversity of replies, but gains a boost on both logic and emotion compared with baselines.

cs.CL↗

arXiv2018

Spin wave emission by spin-orbit torque antennas

We study the generation of propagating spin waves in Ta/CoFeB waveguides by spin-orbit torque antennas and compare them to conventional inductive antennas. The spin-orbit torque was generated by a transverse microwave current across the magnetic waveguide. The detected spin wave signals for an in-plane magnetization across the waveguide (Damon-Eshbach configuration) exhibited the expected phase rotation and amplitude decay upon propagation when the current spreading was taken into account. Wavevectors up to about 6 rad/$μ$m could be excited by the spin-orbit torque antennas despite the current spreading, presumably due to the non-uniformity of the microwave current. The relative magnitude of generated anti-damping spin-Hall and Oersted fields was calculated within an analytic model and it was found that they contribute approximately equally to the total effective field generated by the spin-orbit torque antenna. Due to the ellipticity of the precession in the ultrathin waveguide and the different orientation of the anti-damping spin-Hall and Oersted fields, the torque was however still dominated by the Oersted field. The prospects for obtaining a pure spin-orbit torque response are discussed, as are the energy efficiency and the scaling properties of spin-orbit torque antennas.

cond-mat.mes-hall↗

arXiv2017

Compositional Human Pose Regression

Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It significantly advances the state-of-the-art on Human3.6M and is competitive with state-of-the-art results on MPII.

cs.CV↗

arXiv2017

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

In this paper, we study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images with 2D pose or in the lab images with 3D pose. We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure. Our network augments a state-of-the-art 2D pose estimation sub-network with a 3D depth regression sub-network. Unlike previous two stage approaches that train the two sub-networks sequentially and separately, our training is end-to-end and fully exploits the correlation between the 2D pose and depth estimation sub-tasks. The deep features are better learnt through shared representations. In doing so, the 3D pose labels in controlled lab environments are transferred to in the wild images. In addition, we introduce a 3D geometric constraint to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels. Our method achieves competitive results on both 2D and 3D benchmarks.

cs.CV↗

arXiv2017

Cooperative Data Offload in Opportunistic Networks: From Mobile Devices to Infrastructure

Opportunistic mobile networks consisting of intermittently connected mobile devices have been exploited for various applications, such as computational offloading and mitigating cellular traffic load. In contrast to existing work, in this paper, we focus on cooperatively offloading data among mobile devices to maximally improve the probability of data delivery from a mobile device to intermittently connected infrastructure within a given time constraint, which is referred to as the \textit{cooperative offloading} problem. Unfortunately, the estimation of data delivery probability over an opportunistic path is difficult and cooperative offloading is NP-hard. To this end, we first propose a probabilistic framework that provides the estimation of such probability. Based on the proposed probabilistic framework, we design a heuristic algorithm to solve cooperative offloading at a low computation cost. Due to the lack of global information, a distributed algorithm is further proposed. The performance of the proposed approaches is evaluated based on both synthetic networks and real traces. Experimental results show that the probabilistic framework can accurately estimate the data delivery probability, cooperative offloading greatly improves the delivery probability, the heuristic algorithm approximates the optimum, and the performance of both the heuristic algorithm and distributed algorithm outperforms other approaches.

cs.NI↗

arXiv2016

Deep Kinematic Pose Regression

Learning articulated object pose is inherently difficult because the pose is high dimensional but has many structural constraints. Most existing work do not model such constraints and does not guarantee the geometric validity of their pose estimation, therefore requiring a post-processing to recover the correct geometry if desired, which is cumbersome and sub-optimal. In this work, we propose to directly embed a kinematic object model into the deep neutral network learning for general articulated object pose estimation. The kinematic function is defined on the appropriately parameterized object motion variables. It is differentiable and can be used in the gradient descent based optimization in network training. The prior knowledge on the object geometric model is fully exploited and the structure is guaranteed to be valid. We show convincing experiment results on a toy example and the 3D human pose estimation problem. For the latter we achieve state-of-the-art result on Human3.6M dataset.

cs.CV↗