arXiv subjects

Zhuang Li

Publications and source records attributed to Zhuang Li.

88 records · Page 5Linked to original sources

arXiv2022

Real-time End-to-End Video Text Spotter with Contrastive Representation Learning

Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models long-range dependencies and learning temporal information across multiple frames. 3) A simple, lightweight architecture is designed for effective and accurate performance, including GPU-parallel detection post-processing, CTC-based recognition head with Masked RoI. Extensive experiments show the superiority of our method. Especially, CoText achieves an video text spotting IDF1 of 72.0% at 41.0 FPS on ICDAR2015video, with 10.5% and 32.0 FPS improvement the previous best method. The code can be found at github.com/weijiawu/CoText.

cs.CV↗

arXiv2022

The Third Place Solution for CVPR2022 AVA Accessibility Vision and Autonomy Challenge

The goal of AVA challenge is to provide vision-based benchmarks and methods relevant to accessibility. In this paper, we introduce the technical details of our submission to the CVPR2022 AVA Challenge. Firstly, we conducted some experiments to help employ proper model and data augmentation strategy for this task. Secondly, an effective training strategy was applied to improve the performance. Thirdly, we integrated the results from two different segmentation frameworks to improve the performance further. Experimental results demonstrate that our approach can achieve a competitive result on the AVA test set. Finally, our approach achieves 63.008\%AP@0.50:0.95 on the test set of CVPR2022 AVA Challenge.

cs.CV↗

arXiv2022

The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge--Track 3: Referring Video Object Segmentation

The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames. Due to the requirement of understanding cross-modal semantics within individual instances, this task is more challenging than the traditional semi-supervised video object segmentation where the ground truth object masks in the first frame are given. With the great achievement of Transformer in object detection and object segmentation, RVOS has been made remarkable progress where ReferFormer achieved the state-of-the-art performance. In this work, based on the strong baseline framework--ReferFormer, we propose several tricks to boost further, including cyclical learning rates, semi-supervised approach, and test-time augmentation inference. The improved ReferFormer ranks 2nd place on CVPR2022 Referring Youtube-VOS Challenge.

cs.CV↗

arXiv2022

Explanation of electron and muon $g-2$ anomalies in AMSB

We propose to jointly explain the electron/muon $g-2$ anomalies in the framework of anomaly mediated SUSY breaking (AMSB) scenario. Two Yukawa deflected AMSB models are proposed and discussed in depth: one with lepton-specific interactions and the other one with messenger-matter interactions. Both models are found to be able to jointly explain the anomalies at $2 σ$ level by naturally realizing the preferred parameter space with $μM_1,μM_2<0$ and very heavy left-handed smuon.

hep-ph↗

arXiv2022

Explaining The Muon $g-2$ Anomaly and New CDF II W-Boson Mass in the Framework of (Extra)Ordinary Gauge Mediation

The SUSY contributions $Δa_μ$ to muon $g-2$ anomaly can not even reach $3σ$ in ordinary gauge mediated SUSY breaking (GMSB) scenarios because of the strong correlations between the colored sparticle masses and the uncolored EW sparticle masses. An interesting extension to GMSB is the (Extra)Ordinary Gauge Mediation (EOGM), which can relax the correlations between squarks and sleptons with non-universal choices for $N_{eff,3}$ and $N_{eff,2}$. We find that EOGM scenarios with $N_{eff,3}\ll N_{eff,2}$ can explain the muon $g-2$ anomaly within $3σ$ range, however can not explain the new W-boson mass by CDF II. We also propose to extend EOGM with additional adjoint $Σ_8$ and $Σ_3$ messengers at a high scale of order $1.0\times 10^{14}$ GeV, which can shift the gauge coupling unification scale to the string scale. Such EOGM extension scenarios with adjoint messengers could spoil the unwanted gaugino mass ratios and give large SUSY contributions to $Δa_μ$ for $N_{eff,3}\ll N_{eff,2}$, which can explain the muon $g-2$ anomaly up to $1σ$. Besides, because of the large messenger scale of order $1.0\times 10^{14}$ GeV, such scenarios will in general lead to large $|A_t|$ at the EW scale, which can accommodate the 125 GeV Higgs easily and possibly lead to smaller EWFT as well as BGFT. We discuss the possibility to explain the new CDF II W-boson mass in the GMSB-type framework. We find that SUSY contributions can marginally account for the new W-boson mass in the region with sleptons and wino both being light.

hep-ph↗

arXiv2021

A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer

Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four features for BOVText. Firstly, we provide 2,000+ videos with more than 1,750,000+ frames, 25 times larger than the existing largest dataset with incidental text in videos. Secondly, our dataset covers 30+ open categories with a wide selection of various scenarios, e.g., Life Vlog, Driving, Movie, etc. Thirdly, abundant text types annotation (i.e., title, caption or scene text) are provided for the different representational meanings in video. Fourthly, the BOVText provides bilingual text annotation to promote multiple cultures live and communication. Besides, we propose an end-to-end video text spotting framework with Transformer, termed TransVTSpotter, which solves the multi-orient text spotting in video with a simple, but efficient attention-based query-key mechanism. It applies object features from the previous frame as a tracking query for the current frame and introduces a rotation angle prediction to fit the multiorient text instance. On ICDAR2015(video), TransVTSpotter achieves the state-of-the-art performance with 44.1% MOTA, 9 fps. The dataset and code of TransVTSpotter can be found at github:com=weijiawu=BOVText and github:com=weijiawu=TransVTSpotter, respectively.

cs.CV↗

arXiv2021

Gluino-SUGRA scenarios in light of FNAL muon g-2 anomaly

Gluino-SUGRA ($\tilde{g}$SUGRA), which is an economical extension of the predictive mSUGRA, adopts much heavier gluino mass parameter than other gauginos mass parameters and universal scalar mass parameter at the unification scale. It can elegantly reconcile the experimental results on the Higgs boson mass, the muon $g-2$, the null results in search for supersymmetry at the LHC and the results from B-physics. In this work, we propose several new ways to generate large gaugino hierarchy (i.e. $M_3\gg M_1,M_2$) for $\tilde{g}$SUGRA model building and then discuss in detail the implications of the new muon $g-2$ results with the updated LHC constraints on such $\tilde{g}$SUGRA scenarios. We obtain the following observations: (i) For the most interesting $M_1=M_2$ case at the GUT scale with a viable bino-like dark matter, the $\tilde{g}$SUGRA can explain the muon $g-2$ anomaly at $1σ$ level and be consistent with the updated LHC constraints for $6\leq M_3/M_1 \leq 9$ at the GUT scale; (ii) For $M_1:M_2=5:1$ at the GUT scale with wino-like dark matter, the $\tilde{g}$SUGRA model can explain the muon $g-2$ anomaly at $2σ$ level and be consistent with the updated LHC constraints for $3\leq M_3/M_1 \leq 3.2$ at the GUT scale; (iii) For $M_1:M_2=3:2$ at the GUT scale with mixed bino-wino dark matter, the $\tilde{g}$SUGRA model can explain the muon $g-2$ anomaly at $1σ$ level and be consistent with the updated LHC constraints for $6.9\leq M_3/M_1 \leq 7.5$ at the GUT scale. Although the choice of heavy gluino will always increase the FT involved, some of the $1σ/2σ$ survived points of $Δa_μ^{combine}$ can still allow low EWFT of order several hundreds and be fairly natural. Constraints from (dimension-five operator induced) proton decay are also discussed.

hep-ph↗

arXiv2021

Asymmetric Correntropy for Robust Adaptive Filtering

In recent years, correntropy has been seccessfully applied to robust adaptive filtering to eliminate adverse effects of impulsive noises or outliers. Correntropy is generally defined as the expectation of a Gaussian kernel between two random variables. This definition is reasonable when the error between the two random variables is symmetrically distributed around zero. For the case of asymmetric error distribution, the symmetric Gaussian kernel is however inappropriate and cannot adapt to the error distribution well. To address this problem, in this brief we propose a new variant of correntropy, named asymmetric correntropy, which uses an asymmetric Gaussian model as the kernel function. In addition, a robust adaptive filtering algorithm based on asymmetric correntropy is developed and its steady-state convergence performance is analyzed. Simulations are provided to confirm the theoretical results and good performance of the proposed algorithm.

eess.SP↗

arXiv2021

Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers

This paper investigates continual learning for semantic parsing. In this setting, a neural semantic parser learns tasks sequentially without accessing full training data from previous tasks. Direct application of the SOTA continual learning algorithms to this problem fails to achieve comparable performance with re-training models with all seen tasks because they have not considered the special properties of structured outputs yielded by semantic parsers. Therefore, we propose TotalRecall, a continual learning method designed for neural semantic parsers from two aspects: i) a sampling method for memory replay that diversifies logical form templates and balances distributions of parse actions in a memory; ii) a two-stage training method that significantly improves generalization capability of the parsers across tasks. We conduct extensive experiments to study the research problems involved in continual semantic parsing and demonstrate that a neural semantic parser trained with TotalRecall achieves superior performance than the one trained directly with the SOTA continual learning algorithms and achieve a 3-6 times speedup compared to re-training from scratch. Code and datasets are available at: https://github.com/zhuang-li/cl_nsp.

cs.CL↗

arXiv2021

AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation

Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the effective solutions to overcome such difficulties. In our work, we propose AugNet, a new deep learning training paradigm to learn image features from a collection of unlabeled pictures. We develop a method to construct the similarities between pictures as distance metrics in the embedding space by leveraging the inter-correlation between augmented versions of samples. Our experiments demonstrate that the method is able to represent the image in low dimensional space and performs competitively in downstream tasks such as image classification and image similarity comparison. Specifically, we achieved over 60% and 27% accuracy on the STL10 and CIFAR100 datasets with unsupervised clustering, respectively. Moreover, unlike many deep-learning-based image retrieval algorithms, our approach does not require access to external annotated datasets to train the feature extractor, but still shows comparable or even better feature representation ability and easy-to-use characteristics. In our evaluations, the method outperforms all the state-of-the-art image retrieval algorithms on some out-of-domain image datasets. The code for the model implementation is available at https://github.com/chenmingxiang110/AugNet.

cs.CV↗

arXiv2021

On Robustness of Neural Semantic Parsers

Semantic parsing maps natural language (NL) utterances into logical forms (LFs), which underpins many advanced NLP problems. Semantic parsers gain performance boosts with deep neural networks, but inherit vulnerabilities against adversarial examples. In this paper, we provide the empirical study on the robustness of semantic parsers in the presence of adversarial attacks. Formally, adversaries of semantic parsing are considered to be the perturbed utterance-LF pairs, whose utterances have exactly the same meanings as the original ones. A scalable methodology is proposed to construct robustness test sets based on existing benchmark corpora. Our results answered five research questions in measuring the sate-of-the-art parsers' performance on robustness test sets, and evaluating the effect of data augmentation.

cs.CL↗

arXiv2021

Few-Shot Semantic Parsing for New Predicates

In this work, we investigate the problems of semantic parsing in a few-shot learning setting. In this setting, we are provided with utterance-logical form pairs per new predicate. The state-of-the-art neural semantic parsers achieve less than 25% accuracy on benchmark datasets when k= 1. To tackle this problem, we proposed to i) apply a designated meta-learning method to train the model; ii) regularize attention scores with alignment statistics; iii) apply a smoothing technique in pre-training. As a result, our method consistently outperforms all the baselines in both one and two-shot settings.

cs.CL↗

arXiv2020

Context Dependent Semantic Parsing: A Survey

Semantic parsing is the task of translating natural language utterances into machine-readable meaning representations. Currently, most semantic parsing methods are not able to utilize contextual information (e.g. dialogue and comments history), which has a great potential to boost semantic parsing performance. To address this issue, context dependent semantic parsing has recently drawn a lot of attention. In this survey, we investigate progress on the methods for the context dependent semantic parsing, together with the current datasets and tasks. We then point out open problems and challenges for future research in this area. The collected resources for this topic are available at:https://github.com/zhuang-li/Contextual-Semantic-Parsing-Paper-List.

cs.CL↗

arXiv2020

Type-II neutrino seesaw mechanism extension of NMSSM from SUSY breaking mechanisms

We propose to accommodate economically the type-II neutrino seesaw mechanism in (G)NMSSM from GMSB and AMSB, respectively. The heavy triplets within neutrino seesaw mechanism are identified to be the messengers. Therefore, the $μ$-problem, the neutrino mass generation, LFV as well the soft SUSY breaking parameters can be economically combined in a non-trivial way. General features of such extensions are discussed. The type-II neutrino seesaw-specific interactions can give additional Yukawa deflection contributions to the soft SUSY breaking parameters of NMSSM, which are indispensable to realize successful EWSB and accommodate the 125 GeV Higgs. Relevant numerical results, including the constraints of dark matter and possible LFV processes $l_i\rightarrow l_j γ$ etc, are also given. We find that our economical type-II neutrino seesaw mechanism extension of NMSSM from AMSB or GMSB can lead to realistic low energy NMSSM spectrum, both admitting the 125 GeV Higgs as the lightest CP-even scalar. The possibility of the 125 GeV Higgs being the next-to-lightest CP-even scalar in GMSB-type scenario is ruled out by the constraints from EWSB, collider and precision measurements. The possibility of the 125 GeV Higgs being the next-to-lightest CP-even scalar in AMSB-type scenario is ruled out by dark matter direct detection experiments. Possible constraints from LFV processes $l_i\rightarrow l_j γ$ can give an upper bound for the messenger scale.

hep-ph↗

arXiv2020

Explaining The XENON1T Excess With Light Goldstini Dark Matter

In the scenario with a multiplicity of sectors which independently break supersymmetry, multiplicity of goldstini are predicted. We propose a new interpretation of the electron recoil excess at 2-7 keV observed in the XENON1T experiment with very long-lived goldstini DM elastically scattering off the electrons. The goldstini DM can be boosted by the late-decay of the other nearly degenerate (long-lived) goldstini DM, with their tiny mass difference being converted into kinetic energy of the lighter goldstini DM and neutrinos. We show that viable parameter space can be found which can explain the excess of electron recoil events around 2-3 keV recently reported by the XENON1T experiment.

hep-ph↗

arXiv2019

Minimal Yukawa deflection of AMSB from the Kahler potential

We propose a minimal Yukawa deflection scenario of AMSB from the Kahler potential through the Higgs-messenger mixing. Salient features of this scenario are discussed and realistic MSSM spectrum can be obtained. Such a scenario, which are very predictive, can solve the tachyonic slepton problem with less messenger species. Numerical results indicate that the LOSPs predicted by this scenario can not be good DM candidates. So it is desirable to extend this scenario with a Peccei-Quinn sector to solve the strong CP problem and at the same time provide new DM candidates. We propose a way to obtain a light axino mass in SUSY KSVZ axion model with Yukawa deflected anomaly mediation SUSY breaking mechanism. The axino can possibly be the LSP and act as a good DM candidate.

hep-ph↗