arXiv subjects

Bing Li

Publications and source records attributed to Bing Li.

At least 343 records · Page 19Linked to original sources

arXiv2022

EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching

Current metrics for video captioning are mostly based on the text-level comparison between reference and candidate captions. However, they have some insuperable drawbacks, e.g., they cannot handle videos without references, and they may result in biased evaluation due to the one-to-many nature of video-to-text and the neglect of visual relevance. From the human evaluator's viewpoint, a high-quality caption should be consistent with the provided video, but not necessarily be similar to the reference in literal or semantics. Inspired by human evaluation, we propose EMScore (Embedding Matching-based score), a novel reference-free metric for video captioning, which directly measures similarity between video and candidate captions. Benefit from the recent development of large-scale pre-training models, we exploit a well pre-trained vision-language model to extract visual and linguistic embeddings for computing EMScore. Specifically, EMScore combines matching scores of both coarse-grained (video and caption) and fine-grained (frames and words) levels, which takes the overall understanding and detailed characteristics of the video into account. Furthermore, considering the potential information gain, EMScore can be flexibly extended to the conditions where human-labeled references are available. Last but not least, we collect VATEX-EVAL and ActivityNet-FOIl datasets to systematically evaluate the existing metrics. VATEX-EVAL experiments demonstrate that EMScore has higher human correlation and lower reference dependency. ActivityNet-FOIL experiment verifies that EMScore can effectively identify "hallucinating" captions. The datasets will be released to facilitate the development of video captioning metrics. The code is available at: https://github.com/ShiYaya/emscore.

cs.CV↗

arXiv2022

Nonlinear function-on-function regression by RKHS

We propose a nonlinear function-on-function regression model where both the covariate and the response are random functions. The nonlinear regression is carried out in two steps: we first construct Hilbert spaces to accommodate the functional covariate and the functional response, and then build a second-layer Hilbert space for the covariate to capture nonlinearity. The second-layer space is assumed to be a reproducing kernel Hilbert space, which is generated by a positive definite kernel determined by the inner product of the first-layer Hilbert space for $X$--this structure is known as the nested Hilbert spaces. We develop estimation procedures to implement the proposed method, which allows the functional data to be observed at different time points for different subjects. Furthermore, we establish the convergence rate of our estimator as well as the weak convergence of the predicted response in the Hilbert space. Numerical studies including both simulations and a data application are conducted to investigate the performance of our estimator in finite sample.

stat.ME↗

arXiv2022

Novel Valence Transition in Elemental Metal Europium around 80 GPa

Valence transition could induce structural, insulator-metal, nonmagnetic-magnetic and superconducting transitions in rare-earth metals and compounds, while the underlying physics remains unclear due to the complex interaction of localized 4f electrons as well as their coupling with itinerant electrons. The valence transition in the elemental metal europium (Eu) still has remained as a matter of debate. Using resonant x-ray emission scattering and x-ray diffraction, we pressurize the states of 4f electrons in Eu and study its valence and structure transitions up to 160 GPa. We provide compelling evidence for a valence transition around 80 GPa, which coincides with a structural transition from a monoclinic (C2/c) to an orthorhombic phase (Pnma). We show that the valence transition occurs when the pressure-dependent energy gap between 4f and 5d electrons approaches the Coulomb interaction. Our discovery is critical for understanding the electrodynamics of Eu, including magnetism and high-pressure superconductivity.

cond-mat.str-el↗

arXiv2022

Low temperature competing magnetic energy scales in the topological ferrimagnet TbMn6Sn6

TbMn6Sn6 is a metallic ferrimagnet displaying signatures of both topological electrons and topological magnons arising from ferromagnetism and spin-orbit coupling within its Mn kagome layers. Inelastic neutron scattering measurements find strong ferromagnetic (FM) interactions within the Mn kagome layer and reveal a magnetic bandwidth of ~230 meV. The low-energy magnetic excitations are characterized by strong FM Mn-Mn and antiferromagnetic (AFM) Mn-Tb interlayer magnetic couplings. We observe weaker, competing long-range FM and AFM Mn-Mn interlayer interactions similar to those driving helical magnetism in the YMn6Sn6 system. Combined with density-functional theory calculations, we find that competing Mn-Mn interlayer magnetic interactions occur in all RMn6Sn6 compounds with R= Y, Gd-Lu, resulting in magnetic instabilities and tunability when Mn-R interactions are weak. In the case of TbMn6Sn6, strong AFM Mn-Tb coupling ensures a highly stable three-dimensional ferrimagnetic network.

cond-mat.str-el↗

arXiv2022

FGNET-RH: Fine-Grained Named Entity Typing via Refinement in Hyperbolic Space

Fine-Grained Named Entity Typing (FG-NET) aims at classifying the entity mentions into a wide range of entity types (usually hundreds) depending upon the context. While distant supervision is the most common way to acquire supervised training data, it brings in label noise, as it assigns type labels to the entity mentions irrespective of mentions context. In attempts to deal with the label noise, leading research on the FG-NET assumes that the fine-grained entity typing data possesses a euclidean nature, which restraints the ability of the existing models in combating the label noise. Given the fact that the fine-grained type hierarchy exhibits a hierarchical structure, it makes hyperbolic space a natural choice to model the FG-NET data. In this research, we propose FGNET-RH, a novel framework that benefits from the hyperbolic geometry in combination with the graph structures to perform entity typing in a performance-enhanced fashion. FGNET-RH initially uses LSTM networks to encode the mention in relation with its context, later it forms a graph to distill/refine the mention encodings in the hyperbolic space. Finally, the refined mention encoding is used for entity typing. Experimentation using different benchmark datasets shows that FGNET-RH improves the performance on FG-NET by up to 3.5-% in terms of strict accuracy.

cs.CL↗

arXiv2022

Hausdorff and box dimension of self-affine set in non-Archimedean field

In this paper we consider affine iterated function systems in locally compact non-Archimedean field $\mathbb{F}$. We establish the theory of singular value composition in $\mathbb{F}$ and compute box and Hausdorff dimension of self-affine set in $\mathbb{F}^n$, in generic sense, which is an analogy of Falconer's result for real case. The result has the advantage that no additional assumptions needed to be imposed on the norms of linear parts of affine transformation while such norms are strictly less than $\frac{1}{2}$ for real case, which benefits from the non-Archimedean metric on $\mathbb{F}$.

math.CA↗

arXiv2022

Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement

Compressed video action recognition has recently drawn growing attention, since it remarkably reduces the storage and computational cost via replacing raw videos by sparsely sampled RGB frames and compressed motion cues (e.g., motion vectors and residuals). However, this task severely suffers from the coarse and noisy dynamics and the insufficient fusion of the heterogeneous RGB and motion modalities. To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net). It follows the two-stream architecture, i.e. one for the RGB modality and the other for the motion modality. Particularly, the motion stream employs a multi-scale block embedded with a denoising module to enhance representation learning. The interaction between the two streams is then strengthened by introducing the Selective Motion Complement (SMC) and Cross-Modality Augment (CMA) modules, where SMC complements the RGB modality with spatio-temporally attentive local motion features and CMA further combines the two modalities with selective feature augmentation. Extensive experiments on the UCF-101, HMDB-51 and Kinetics-400 benchmarks demonstrate the effectiveness and efficiency of MEACI-Net.

cs.CV↗

arXiv2022

Simultaneous Estimation of Graphical Models by Neighborhood Selection

In many applications concerning statistical graphical models the data originate from several subpopulations that share similarities but have also significant differences. This raises the question of how to estimate several graphical models simultaneously. Compiling all the data together to estimate a single graph would ignore the differences among subpopulations. On the other hand, estimating a graph from each subpopulation separately does not make efficient use of the common structure in the data. We develop a new method for simultaneous estimation of multiple graphical models by estimating the topological neighborhoods of the involved variables under a sparse inducing penalty that takes into account the common structure in the subpopulations. Unlike the existing methods for joint graphical models, our method does not rely on spectral decomposition of large matrices, and is therefore more computationally attractive for estimating large networks. In addition, we develop the asymptotic properties of our method, demonstrate its the numerical complexity, and compare it with several existing methods by simulation. Finally, we apply our method to the estimation of genomic networks for a lung cancer dataset which consists of several subpopulations.

stat.ME↗

arXiv2022

Toward the smooth mesh climbing of a miniature robot using bioinspired soft and expandable claws

While most micro-robots face difficulty traveling on rugged and uneven terrain, beetles can walk smoothly on the complex substrate without slipping or getting stuck on the surface due to their stiffness-variable tarsi and expandable hooks on the tip of tarsi. In this study, we found that beetles actively bent and expanded their claws regularly to crawl freely on mesh surfaces. Inspired by the crawling mechanism of the beetles, we designed an 8-cm miniature climbing robot equipping artificial claws to open and bend in the same cyclic manner as natural beetles. The robot can climb freely with a controllable gait on the mesh surface, steep incline of the angle of 60°, and even transition surface. To our best knowledge, this is the first micro-scale robot that can climb both the mesh surface and cliffy incline.

cs.RO↗

arXiv2022

Narrowing the Gap: Improved Detector Training with Noisy Location Annotations

Deep learning methods require massive of annotated data for optimizing parameters. For example, datasets attached with accurate bounding box annotations are essential for modern object detection tasks. However, labeling with such pixel-wise accuracy is laborious and time-consuming, and elaborate labeling procedures are indispensable for reducing man-made noise, involving annotation review and acceptance testing. In this paper, we focus on the impact of noisy location annotations on the performance of object detection approaches and aim to, on the user side, reduce the adverse effect of the noise. First, noticeable performance degradation is experimentally observed for both one-stage and two-stage detectors when noise is introduced to the bounding box annotations. For instance, our synthesized noise results in performance decrease from 38.9% AP to 33.6% AP for FCOS detector on COCO test split, and 37.8%AP to 33.7%AP for Faster R-CNN. Second, a self-correction technique based on a Bayesian filter for prediction ensemble is proposed to better exploit the noisy location annotations following a Teacher-Student learning paradigm. Experiments for both synthesized and real-world scenarios consistently demonstrate the effectiveness of our approach, e.g., our method increases the degraded performance of the FCOS detector from 33.6% AP to 35.6% AP on COCO.

cs.CV↗

arXiv2022

Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning

Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They base the visual grounding on the features from pre-generated proposals or anchors, and fuse these features with the text embeddings to locate the target mentioned by the text. However, modeling the visual features from these predefined locations may fail to fully exploit the visual context and attribute information in the text query, which limits their performance. In this paper, we propose a transformer-based framework for accurate visual grounding by establishing text-conditioned discriminative features and performing multi-stage cross-modal reasoning. Specifically, we develop a visual-linguistic verification module to focus the visual features on regions relevant to the textual descriptions while suppressing the unrelated areas. A language-guided feature encoder is also devised to aggregate the visual contexts of the target object to improve the object's distinctiveness. To retrieve the target from the encoded visual features, we further propose a multi-stage cross-modal decoder to iteratively speculate on the correlations between the image and text for accurate target localization. Extensive experiments on five widely used datasets validate the efficacy of our proposed components and demonstrate state-of-the-art performance. Our code is public at https://github.com/yangli18/VLTVG.

cs.CV↗

arXiv2022

iPTF14hls in the circumstellar medium interaction model: A promising candidate for a pulsational pair-instability supernova

iPTF14hls is a luminous Type II supernova (SN) with a bumpy light curve that remains debated for its origin. It maintains roughly a constant effective temperature and luminosity since discovery for about 600 days, followed by a slow decay. On $\sim 1000$\ days post discovery the light curve transitions to a very steep decline. A spectrum taken during this steep decline phase shows clear signatures of shock interaction with dense circumstellar medium (CSM). Here we explore the possibility of iPTF14hls as an interaction-powered SN. The light curve of iPTF14hls can be fitted with wind-like CSMs. Analytic modeling indicates that iPTF14hls may have undertaken six episodes of mass loss during the last $\sim 200\mathrm{yr}$. Assuming that the 1954 eruption triggered the last mass-loss episode, the stellar-wind velocity is determined to be $40-70\mathrm{km}\mathrm{s}^{-1}$, depending on different models. Mass loss rates are in the range $% 0.4-3.3M_{\odot }\mathrm{yr}^{-1}$. The inferred total mass of ejecta and CSMs ($M_{\mathrm{ej}}+M_{\mathrm{CSMs}}\simeq 245M_{\odot }$) supports the idea that iPTF14hls may be a candidate for a (pulsational) pair-instability SN. Discovery and observations of more similar stellar explosions will help understand these peculiar SNe.

astro-ph.HE↗

arXiv2022

Rethinking the competition between detection and ReID in Multi-Object Tracking

Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS.

cs.CV↗

arXiv2022

Code Smells Detection via Modern Code Review: A Study of the OpenStack and Qt Communities

Code review that detects and locates defects and other quality issues plays an important role in software quality control. One type of issue that may impact the quality of software is code smells. Yet, little is known about the extent to which code smells are identified during modern code review. To investigate the concept behind code smells identified in modern code review and what actions reviewers suggest and developers take in response to the identified smells, we conducted a study of code smells in code reviews by analyzing reviews from four large open source projects from the OpenStack (Nova and Neutron) and Qt (Qt Base and Qt Creator) communities. We manually checked a total of 25,415 code review comments obtained by keywords search and random selection, and identified 1,539 smell-related reviews. Our analysis found that 1) code smells were not commonly identified in code reviews, 2) smells were usually caused by violation of coding conventions, 3) reviewers usually provided constructive feedback, including fixing (refactoring) recommendations to help developers remove smells, 4) developers generally followed those recommendations and actioned the changes, 5) once identified by reviewers, it usually takes developers less than one week to fix the smells, and 6) the main reason why developers chose to ignore the identified smells is not worth fixing the smell. Our results suggest that: 1) developers should closely follow coding conventions in their projects to avoid introducing code smells, 2) review-based detection of code smells is perceived to be a trustworthy approach by developers, mainly because reviews are context-sensitive (as reviewers are more aware of the context of the code given that they are part of the project's development team), and 3) program context needs to be fully considered in order to make a decision of whether to fix the identified code smell immediately.

cs.SE↗

arXiv2022

SubGraph Networks based Entity Alignment for Cross-lingual Knowledge Graph

Entity alignment is the task of finding entities representing the same real-world object in two knowledge graphs(KGs). Cross-lingual knowledge graph entity alignment aims to discover the cross-lingual links in the multi-language KGs, which is of great significance to the NLP applications and multi-language KGs fusion. In the task of aligning cross-language knowledge graphs, the structures of the two graphs are very similar, and the equivalent entities often have the same subgraph structure characteristics. The traditional GCN method neglects to obtain structural features through representative parts of the original graph and the use of adjacency matrix is not enough to effectively represent the structural features of the graph. In this paper, we introduce the subgraph network (SGN) method into the GCN-based cross-lingual KG entity alignment method. In the method, we extracted the first-order subgraphs of the KGs to expand the structural features of the original graph to enhance the representation ability of the entity embedding and improve the alignment accuracy. Experiments show that the proposed method outperforms the state-of-the-art GCN-based method.

cs.CL↗

arXiv2022

NAND-SPIN-Based Processing-in-MRAM Architecture for Convolutional Neural Network Acceleration

The performance and efficiency of running large-scale datasets on traditional computing systems exhibit critical bottlenecks due to the existing "power wall" and "memory wall" problems. To resolve those problems, processing-in-memory (PIM) architectures are developed to bring computation logic in or near memory to alleviate the bandwidth limitations during data transmission. NAND-like spintronics memory (NAND-SPIN) is one kind of promising magnetoresistive random-access memory (MRAM) with low write energy and high integration density, and it can be employed to perform efficient in-memory computation operations. In this work, we propose a NAND-SPIN-based PIM architecture for efficient convolutional neural network (CNN) acceleration. A straightforward data mapping scheme is exploited to improve the parallelism while reducing data movements. Benefiting from the excellent characteristics of NAND-SPIN and in-memory processing architecture, experimental results show that the proposed approach can achieve $\sim$2.6$\times$ speedup and $\sim$1.4$\times$ improvement in energy efficiency over state-of-the-art PIM solutions.

cs.AR↗

arXiv2022

Rational numbers in $\times b$-invariant sets

Let $b \geq 2$ be an integer and $S$ be a finite non-empty set of primes not containing divisors of $b$. For any non-dense set $A \subset [0,1)$ such that $A \cap \mathbb{Q}$ is invariant under $\times b$ operation, we prove the finiteness of rational numbers in $A$ whose denominators can only be divided by primes in $S$. A quantitative result on the largest prime divisors of the denominators of rational numbers in $A$ is also obtained.

math.NT↗

arXiv2022

Quasi-periodic oscillations of the X-ray burst from the magnetar SGR J1935+2154 and associated with the fast radio burst FRB 200428

The origin(s) and mechanism(s) of fast radio bursts (FRBs), which are short radio pulses from cosmological distances, have remained a major puzzle since their discovery. We report a strong Quasi-Periodic Oscillation(QPO) of 40 Hz in the X-ray burst from the magnetar SGR J1935+2154 and associated with FRB 200428, significantly detected with the Hard X-ray Modulation Telescope (Insight-HXMT) and also hinted by the Konus-Wind data. QPOs from magnetar bursts have only been rarely detected; our 3.4 sigma (p-value is 2.9e-4) detection of the QPO reported here reveals the strongest QPO signal observed from magnetars (except in some very rare giant flares), making this X-ray burst unique among magnetar bursts. The two X-ray spikes coinciding with the two FRB pulses are also among the peaks of the QPO. Our results suggest that at least some FRBs are related to strong oscillation processes of neutron stars. We also show that we may overestimate the significance of the QPO signal and underestimate the errors of QPO parameters if QPO exists only in a fraction of the time series of a X-ray burst which we use to calculate the Leahy-normalized periodogram.

astro-ph.HE↗