arXiv subjects

Liang Zheng

Publications and source records attributed to Liang Zheng.

At least 109 records · Page 6Linked to original sources

arXiv2023

Multiview Detection with Cardboard Human Modeling

Multiview detection uses multiple calibrated cameras with overlapping fields of views to locate occluded pedestrians. In this field, existing methods typically adopt a ``human modeling - aggregation'' strategy. To find robust pedestrian representations, some intuitively incorporate 2D perception results from each frame, while others use entire frame features projected to the ground plane. However, the former does not consider the human appearance and leads to many ambiguities, and the latter suffers from projection errors due to the lack of accurate height of the human torso and head. In this paper, we propose a new pedestrian representation scheme based on human point clouds modeling. Specifically, using ray tracing for holistic human depth estimation, we model pedestrians as upright, thin cardboard point clouds on the ground. Then, we aggregate the point clouds of the pedestrian cardboard across multiple views for a final decision. Compared with existing representations, the proposed method explicitly leverages human appearance and reduces projection errors significantly by relatively accurate height estimation. On four standard evaluation benchmarks, the proposed method achieves very competitive results. Our code and data will be released at https://github.com/ZichengDuan/MvCHM.

cs.CV↗

arXiv2022

Revisiting the centrality definition and observable centrality dependence of relativistic heavy-ion collisions in PACIAE model

We improve the centrality definition in impact parameter in PACIAE model responding the fact reported by the ALICE, ATLAS, and CMS collaborations that the maximum impact parameter in heavy ion collisions should be extended to 20 $fm$. Meanwhile the PACIAE program is updated to a new version of PACIAE 2.2.2 with convenience of studying the elementary nuclear collisions, proton-nucleus collisions, and the nucleus-nucleus collisions in one unified program version. The new impact parameter definition together with the optical Glauber model calculated impact parameter bin, $N_{part}$, and $N_{coll}$ in proton-nucleus and nucleus-nucleus collisions at relativistic energies are consistent with the improved MC-Glauber model ones within the error bar. The charged-particle pseudorapidity and the transverse momentum distributions in Pb-Pb collisions at $\sqrt{s_{\rm NN}}=5.02$ TeV simulated by PACIAE 2.2.2 well reproduce the ALICE experimental data.

nucl-th↗

arXiv2022

High-Fidelity Guided Image Synthesis with Latent Diffusion Models

Controllable image synthesis with user scribbles has gained huge public interest with the recent advent of text-conditioned latent diffusion models. The user scribbles control the color composition while the text prompt provides control over the overall image semantics. However, we note that prior works in this direction suffer from an intrinsic domain shift problem, wherein the generated outputs often lack details and resemble simplistic representations of the target domain. In this paper, we propose a novel guided image synthesis framework, which addresses this problem by modeling the output image as the solution of a constrained optimization problem. We show that while computing an exact solution to the optimization is infeasible, an approximation of the same can be achieved while just requiring a single pass of the reverse diffusion process. Additionally, we show that by simply defining a cross-attention based correspondence between the input text tokens and the user stroke-painting, the user is also able to control the semantics of different painted regions without requiring any conditional training or finetuning. Human user study results show that the proposed approach outperforms the previous state-of-the-art by over 85.32% on the overall user satisfaction scores. Project page for our paper is available at https://1jsingh.github.io/gradop.

cs.CV↗

arXiv2022

On-demand storage of photonic qubits at telecom wavelengths

Quantum memories at telecom wavelengths are crucial for the construction of large-scale quantum networks based on existing fiber networks. On-demand storage of telecom photonic qubits is a fundamental request for such networking applications but yet to be demonstrated. Here we demonstrate the storage and on-demand retrieval of telecom photonic qubits using a laser-written waveguide fabricated in an $^{167}$Er$^{3+}$:Y$_2$SiO$_5$ crystal. Both ends of the waveguide memory are directly connected with fiber arrays with a fiber-to-fiber efficiency of 51%. Storage fidelity of 98.3(1)% can be obtained for time-bin qubits encoded with single-photon-level coherent pulses, which is far beyond the maximal fidelity that can be achieved with a classical measure and prepare strategy. This device features high reliability, easy scalability and can be directly integrated into fiber networks, which could play an essential role in fiber-based quantum networks.

quant-ph↗

arXiv2022

Studying strange hadron productions via two-particle correlations in high energy proton-proton collisions

Strange hadron production in pp collisions at $\sqrt{s}= 7$ TeV is studied with PYTHIA 8 and EPOS event generators via the two-particle correlation method. After pairing charged particles as trigger particles with associated strange hadrons $(\mathrm{K}^{0}_{S}$ and $(Λ/\overlineΛ)$ , the strange baryon to meson per trigger yield ratios ${Y_{Δφ}^{\mathrm{h}-(Λ+\overlineΛ)}}$/$/{2Y_{Δφ}^{\mathrm{h}-\mathrm{K}^{0}_{S}}}$ dependent on transverse momentum ($p_{T})$ are investigated within the near- and away-side jet region as well as the underlying event (UE) region. The modified string fragmentation effects of color reconnection and string shoving mechanisms implemented in PYTHIA 8 and the final state evolution effects built in EPOS are compared in this study. It is found that $p_{T}$ dependence of the $Λ/\mathrm{K}^{0}_{S}$ per trigger yield ratio in UE is similar to that in the inclusive measurements while the in-jet result is smaller. We also show that the $Λ/\mathrm{K}^{0}_{S}$ ratio at both near- and away-side jet region in the intermediate $p_{T}$ region decreases significantly with trigger $p_{T}$, which suggests the hard process effects might contribute to the strange baryon to meson enhancement at intermediate $p_{T}$. The much higher $Λ/\mathrm{K}^{0}_{S}$ ratio in UE and the striking difference between the near and away side of the in-jet results with low trigger $p_{T}$ predicted by the EPOS model indicate that the soft process effects induced by the final state evolution further increase the strange baryon production and can be still effective in a higher $p_{T}$ region compared to the string fragmentation type models.

hep-ph↗

arXiv2022

Generalizable Re-Identification from Videos with Cycle Association

In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos. Compared with 1) the popular unsupervised re-ID setting where the training and test sets are typically under the same domain, and 2) the popular domain generalization (DG) re-ID setting where the training samples are labeled, our novel scenario combines their key challenges: the training samples are unlabeled, and collected form various domains which do no align with the test domain. In other words, we aim to learn a representation in an unsupervised manner and directly use the learned representation for re-ID in novel domains. To fulfill this goal, we make two main contributions: First, we propose Cycle Association (CycAs), a scalable self-supervised learning method for re-ID with low training complexity; and second, we construct a large-scale unlabeled re-ID dataset named LMP-video, tailored for the proposed method. Specifically, CycAs learns re-ID features by enforcing cycle consistency of instance association between temporally successive video frame pairs, and the training cost is merely linear to the data size, making large-scale training possible. On the other hand, the LMP-video dataset is extremely large, containing 50 million unlabeled person images cropped from over 10K Youtube videos, therefore is sufficient to serve as fertile soil for self-supervised learning. Trained on LMP-video, we show that CycAs learns good generalization towards novel domains. The achieved results sometimes even outperform supervised domain generalizable models. Remarkably, CycAs achieves 82.2% Rank-1 on Market-1501 and 49.0% Rank-1 on MSMT17 with zero human annotation, surpassing state-of-the-art supervised DG re-ID methods. Moreover, we also demonstrate the superiority of CycAs under the canonical unsupervised re-ID and the pretrain-and-finetune scenarios.

cs.CV↗

arXiv2022

Linear scaling of lepton charge asymmetry in $W^\pm$ production in ultra-relativistic nuclear collisions

The lepton charge asymmetry in $W^\pm$ production in the nuclear collisions at $\sqrt{s_{\rm NN}}=5.02$ TeV is investigated with a parton and hadron cascade model PACIAE. Recently published ALICE and the ATLAS data of lepton charge asymmetry are well reproduced. An interesting linear scaling behavior is observed in the lepton charge asymmetry as a function of the collision system valence quark number asymmetry among the different size of nuclear collision systems at $\sqrt{s_{\rm NN}}=5.02$ TeV. This linear scaling behavior may serve as an additional constraint on the PDF (nPDF) extractions.

hep-ph↗

arXiv2022

How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?

This paper does not contain technical novelty but introduces our key discoveries in a data generation protocol, a database and insights. We aim to address the lack of large-scale datasets in micro-expression (MiE) recognition due to the prohibitive cost of data collection, which renders large-scale training less feasible. To this end, we develop a protocol to automatically synthesize large scale MiE training data that allow us to train improved recognition models for real-world test data. Specifically, we discover three types of Action Units (AUs) that can constitute trainable MiEs. These AUs come from real-world MiEs, early frames of macro-expression videos, and the relationship between AUs and expression categories defined by human expert knowledge. With these AUs, our protocol then employs large numbers of face images of various identities and an off-the-shelf face generator for MiE synthesis, yielding the MiE-X dataset. MiE recognition models are trained or pre-trained on MiE-X and evaluated on real-world test sets, where very competitive accuracy is obtained. Experimental results not only validate the effectiveness of the discovered AUs and MiE-X dataset but also reveal some interesting properties of MiEs: they generalize across faces, are close to early-stage macro-expressions, and can be manually defined.

cs.CV↗

arXiv2022

Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing

Controllable image synthesis with user scribbles is a topic of keen interest in the computer vision community. In this paper, for the first time we study the problem of photorealistic image synthesis from incomplete and primitive human paintings. In particular, we propose a novel approach paint2pix, which learns to predict (and adapt) "what a user wants to draw" from rudimentary brushstroke inputs, by learning a mapping from the manifold of incomplete human paintings to their realistic renderings. When used in conjunction with recent works in autonomous painting agents, we show that paint2pix can be used for progressive image synthesis from scratch. During this process, paint2pix allows a novice user to progressively synthesize the desired image output, while requiring just few coarse user scribbles to accurately steer the trajectory of the synthesis process. Furthermore, we find that our approach also forms a surprisingly convenient approach for real image editing, and allows the user to perform a diverse range of custom fine-grained edits through the addition of only a few well-placed brushstrokes. Supplemental video and demo are available at https://1jsingh.github.io/paint2pix

cs.CV↗

arXiv2022

Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation needs rich and robust supervision on unlabeled data. Consistency learning enforces the same pixel to have similar features in different augmented views, which is a robust signal but neglects relationships with other pixels. In comparison, contrastive learning considers rich pairwise relationships, but it can be a conundrum to assign binary positive-negative supervision signals for pixel pairs. In this paper, we take the best of both worlds and propose multi-view correlation consistency (MVCC) learning: it considers rich pairwise relationships in self-correlation matrices and matches them across views to provide robust supervision. Together with this correlation consistency loss, we propose a view-coherent data augmentation strategy that guarantees pixel-pixel correspondence between different views. In a series of semi-supervised settings on two datasets, we report competitive accuracy compared with the state-of-the-art methods. Notably, on Cityscapes, we achieve 76.8% mIoU with 1/8 labeled data, just 0.6% shy from the fully supervised oracle.

cs.CV↗

arXiv2022

Learning to Structure an Image with Few Colors and Beyond

Color and structure are the two pillars that combine to give an image its meaning. Interested in critical structures for neural network recognition, we isolate the influence of colors by limiting the color space to just a few bits, and find structures that enable network recognition under such constraints. To this end, we propose a color quantization network, ColorCNN, which learns to structure an image in limited color spaces by minimizing the classification loss. Building upon the architecture and insights of ColorCNN, we introduce ColorCNN+, which supports multiple color space size configurations, and addresses the previous issues of poor recognition accuracy and undesirable visual fidelity under large color spaces. Via a novel imitation learning approach, ColorCNN+ learns to cluster colors like traditional color quantization methods. This reduces overfitting and helps both visual fidelity and recognition accuracy under large color spaces. Experiments verify that ColorCNN+ achieves very competitive results under most circumstances, preserving both key structures for network recognition and visual fidelity with accurate colors. We further discuss differences between key structures and accurate colors, and their specific contributions to network recognition. For potential applications, we show that ColorCNNs can be used as image compression methods for network recognition.

cs.CV↗

arXiv2022

On the Strong Correlation Between Model Invariance and Generalization

Generalization and invariance are two essential properties of any machine learning model. Generalization captures a model's ability to classify unseen data while invariance measures consistency of model predictions on transformations of the data. Existing research suggests a positive relationship: a model generalizing well should be invariant to certain visual factors. Building on this qualitative implication we make two contributions. First, we introduce effective invariance (EI), a simple and reasonable measure of model invariance which does not rely on image labels. Given predictions on a test image and its transformed version, EI measures how well the predictions agree and with what level of confidence. Second, using invariance scores computed by EI, we perform large-scale quantitative correlation studies between generalization and invariance, focusing on rotation and grayscale transformations. From a model-centric view, we observe generalization and invariance of different models exhibit a strong linear relationship, on both in-distribution and out-of-distribution datasets. From a dataset-centric view, we find a certain model's accuracy and invariance linearly correlated on different test sets. Apart from these major findings, other minor but interesting insights are also discussed.

cs.LG↗

arXiv2022

A transport model study of multiparticle cumulants in $p+p$ collisions at 13 TeV

Flow-like signals including the ridge structure observed in small collision systems that are similar to those in large collision systems have led to questions about the onset of collectivity in nuclear collisions. In this study, we use the string melting version of a multi-phase transport (AMPT) model with or without the sub-nucleon geometry for the proton to study multiparticle cumulants in $p+p$ collisions at 13 TeV. Both versions of the model produce negative $c_{2}\{4 \}$ values at high multiplicities. In addition, the dependence of $c_{2}\{4 \}$ on the parton cross section is non-monotonous, where only a range of parton cross section values leads to negative $c_{2} \{4 \}$. Furthermore, the AMPT model with sub-nucleon geometry better describes the multiplicity dependence of $c_{2} \{4 \}$, demonstrating the importance of incorporating the sub-nucleon geometry in studies of small collision systems.

nucl-th↗

arXiv2022

The 6th AI City Challenge

The 6th edition of the AI City Challenge specifically focuses on problems in two domains where there is tremendous unlocked potential at the intersection of computer vision and artificial intelligence: Intelligent Traffic Systems (ITS), and brick and mortar retail businesses. The four challenge tracks of the 2022 AI City Challenge received participation requests from 254 teams across 27 countries. Track 1 addressed city-scale multi-target multi-camera (MTMC) vehicle tracking. Track 2 addressed natural-language-based vehicle track retrieval. Track 3 was a brand new track for naturalistic driving analysis, where the data were captured by several cameras mounted inside the vehicle focusing on driver safety, and the task was to classify driver actions. Track 4 was another new track aiming to achieve retail store automated checkout using only a single view camera. We released two leader boards for submissions based on different methods, including a public leader board for the contest, where no use of external data is allowed, and a general leader board for all submitted results. The top performance of participating teams established strong baselines and even outperformed the state-of-the-art in the proposed challenge tracks.

cs.CV↗

arXiv2022

BeAGLE: Benchmark $e$A Generator for LEptoproduction in high energy lepton-nucleus collisions

The upcoming Electron-Ion Collider (EIC) will address several outstanding puzzles in modern nuclear physics. Topics such as the partonic structure of nucleons and nuclei, the origin of their mass and spin, among others, can be understood via the study of high energy electron-proton ($ep$) and electron-nucleus ($e$A) collisions. Achieving the scientific goals of the EIC will require a novel electron-hadron collider and detectors capable to perform high-precision measurements, but also dedicated tools to model and interpret the data. To aid in the latter, we present a general-purpose $e$A Monte Carlo (MC) generator - BeAGLE. In this paper, we provide a general description of the models integrated into BeAGLE, applications of BeAGLE in $e$A physics, implications for detector requirements at the EIC, and the tuning of the parameters in BeAGLE based on available experimental data. Specifically, we focus on a selection of model and data comparisons in particle production in both $ep$ and $e$A collisions, where baseline particle distributions provide essential information to characterize the event. In addition, we investigate the collision geometry determination in $e$A collisions, which could be used as an experimental tool for varying the nuclear density.

physics.comp-ph↗

arXiv2022

Strange particle production in jets and underlying events in pp collisions at $\sqrt{s}~=~7$ TeV with PYTHIA8 generator

Strange hadron production in pp collisions at $\sqrt{s}~=~7$ TeV is studied in jets and underlying events using the PYTHIA8 event generator. Matching strange hadrons to the jet area and the underlying event area is expected to help us disentangle the strange particles produced in hard and soft processes. The yield and the relative production of strange hadrons dependent on the event multiplicity are investigated with the color reconnection and color rope mechanisms implemented in the PYTHIA8 framework. It is found that the inclusive strange hadron productions can be reasonably described by the color reconnection and color rope combined effects. A significant multiplicity dependent enhancement of the strange baryon production in the jet area is observed induced by the modified string fragmentation mechanisms, indicating the strange baryon enhancement persists in both the hard and the soft process. Multi-strange baryons are found to be more collimated with the jet axis than other strange hadrons in the string fragmentation picture with the jet shape analysis technique. Future experimental examination of these jet related strange hadron productions will provide more insight to the origin of strangeness enhancement in small systems.

hep-ph↗

arXiv2022

Centrality dependence and isospin effect on $\Wpm$ and $\Zn$ productions in nucleus-nucleus collisions at $\sNN=5.02$~TeV

In this paper, the centrality dependent $\Zn$ and $\Wpm$ production and the isospin effect in $\Wpm$ production are investigated with a parton and hadron cascade model PACIAE in Pb--Pb collisions at $\sNN=5.02$~TeV. ALICE data of $\Zn$ production in Pb--Pb collisions at $\sNN=5.02$~TeV are found to be reproduced fairly well. The prediction on $\Wpm$ production in the same collision system is given as well. An interesting isospin effect is observed in exploring the charge asymmetry between $\Wp$ and $\Wm$ as a function of the asymmetry between number of valence $u$- and $d$-quarks varied from small to large collision systems at center-of-mass energy 5.02 TeV. The results serve as a important benchmarks for understanding the initial conditions of heavy-ion collisions.

hep-ph↗

arXiv2021

Intelli-Paint: Towards Developing Human-like Painting Agents

The generation of well-designed artwork is often quite time-consuming and assumes a high degree of proficiency on part of the human painter. In order to facilitate the human painting process, substantial research efforts have been made on teaching machines how to "paint like a human", and then using the trained agent as a painting assistant tool for human users. However, current research in this direction is often reliant on a progressive grid-based division strategy wherein the agent divides the overall image into successively finer grids, and then proceeds to paint each of them in parallel. This inevitably leads to artificial painting sequences which are not easily intelligible to human users. To address this, we propose a novel painting approach which learns to generate output canvases while exhibiting a more human-like painting style. The proposed painting pipeline Intelli-Paint consists of 1) a progressive layering strategy which allows the agent to first paint a natural background scene representation before adding in each of the foreground objects in a progressive fashion. 2) We also introduce a novel sequential brushstroke guidance strategy which helps the painting agent to shift its attention between different image regions in a semantic-aware manner. 3) Finally, we propose a brushstroke regularization strategy which allows for ~60-80% reduction in the total number of required brushstrokes without any perceivable differences in the quality of the generated canvases. Through both quantitative and qualitative results, we show that the resulting agents not only show enhanced efficiency in output canvas generation but also exhibit a more natural-looking painting style which would better assist human users express their ideas through digital artwork.

cs.CV↗