arXiv subjects

Qi Zheng

Publications and source records attributed to Qi Zheng.

At least 73 records · Page 4Linked to original sources

arXiv2024

AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results

This paper reviews the AIS 2024 Video Quality Assessment (VQA) Challenge, focused on User-Generated Content (UGC). The aim of this challenge is to gather deep learning-based methods capable of estimating the perceptual quality of UGC videos. The user-generated videos from the YouTube UGC Dataset include diverse content (sports, games, lyrics, anime, etc.), quality and resolutions. The proposed methods must process 30 FHD frames under 1 second. In the challenge, a total of 102 participants registered, and 15 submitted code and models. The performance of the top-5 submissions is reviewed and provided here as a survey of diverse deep models for efficient video quality assessment of user-generated content.

cs.CV↗

arXiv2024

SDSS J222428.53+261423.2: unique emission lines properties unveil a sub-kiloparsec dual AGN candidate

In this paper, we presented a detailed analysis of the Sloan Digital Sky Survey optical spectrum of a new sub-kpc scale dual AGN candidate SDSS J222428.53+261423.2 (=SDSS J2224). The target is one of the few AGNs with all the optical narrow emission lines characterized by double-peaked profiles and with peak separations in velocity units of about 930 km/s. If the double-peaked narrow emission lines (DPNELs) are due to a dual AGN in \obj, the estimated physical separation between the two cores is about 500 pc. Meanwhile, three alternative explanations are also discussed in this paper, however, we can not find solid evidence to completely rule them out. Our results support the presence of a sub-kpc dual AGN with DPNELs in all lines, indicating a key episode of galaxy merging evolution at sub-kpc scale.

astro-ph.GA↗

arXiv2024

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding

Recently, leveraging large language models (LLMs) or multimodal large language models (MLLMs) for document understanding has been proven very promising. However, previous works that employ LLMs/MLLMs for document understanding have not fully explored and utilized the document layout information, which is vital for precise document understanding. In this paper, we propose LayoutLLM, an LLM/MLLM based method for document understanding. The core of LayoutLLM is a layout instruction tuning strategy, which is specially designed to enhance the comprehension and utilization of document layouts. The proposed layout instruction tuning strategy consists of two components: Layout-aware Pre-training and Layout-aware Supervised Fine-tuning. To capture the characteristics of document layout in Layout-aware Pre-training, three groups of pre-training tasks, corresponding to document-level, region-level and segment-level information, are introduced. Furthermore, a novel module called layout chain-of-thought (LayoutCoT) is devised to enable LayoutLLM to focus on regions relevant to the question and generate accurate answers. LayoutCoT is effective for boosting the performance of document understanding. Meanwhile, it brings a certain degree of interpretability, which could facilitate manual inspection and correction. Experiments on standard benchmarks show that the proposed LayoutLLM significantly outperforms existing methods that adopt open-source 7B LLMs/MLLMs for document understanding. The training data of the LayoutLLM is publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/LayoutLLM

cs.CV↗

arXiv2024

LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-training

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes or learning to directly generate the corresponding markup sequences from the table images. However, existing approaches either count on additional heuristic rules to recover the table structures, or face challenges in capturing long-range dependencies within tables, resulting in increased complexity. In this paper, we propose an alternative paradigm. We model TSR as a logical location regression problem and propose a new TSR framework called LORE, standing for LOgical location REgression network, which for the first time regresses logical location as well as spatial location of table cells in a unified network. Our proposed LORE is conceptually simpler, easier to train, and more accurate than other paradigms of TSR. Moreover, inspired by the persuasive success of pre-trained models on a number of computer vision and natural language processing tasks, we propose two pre-training tasks to enrich the spatial and logical representations at the feature level of LORE, resulting in an upgraded version called LORE++. The incorporation of pre-training in LORE++ has proven to enjoy significant advantages, leading to a substantial enhancement in terms of accuracy, generalization, and few-shot capability compared to its predecessor. Experiments on standard benchmarks against methods of previous paradigms demonstrate the superiority of LORE++, which highlights the potential and promising prospect of the logical location regression paradigm for TSR.

cs.CV↗

arXiv2023

Atomically-precise engineering of spin-orbit polarons in a kagome magnetic Weyl semimetal

Atomically-precise engineering of defects in topological quantum materials, which is essential for constructing new artificial quantum materials with exotic properties and appealing for practical quantum applications, remains challenging due to the hindrances in modifying complex lattice with atomic precision. Here, we report the atomically-precise engineering of the vacancy-localized spin-orbital polarons (SOP) in a kagome magnetic Weyl semimetal Co3Sn2S2, using scanning tunneling microscope. We achieve the step-by-step repairing of the selected vacancies, which results in the formation of artificial sulfur vacancy with elaborate geometry. We find that that the bound states localized around the vacancies experience a symmetry-dependent energy shift towards Fermi level with increasing vacancy size. Strikingly, as vacancy size increases, the localized magnetic moments of SOPs are tunable and ultimately extended to the negative magnetic moments resulting from spin-orbit coupling in the kagome flat band. These findings establish a new platform for engineering atomic quantum states in topological quantum materials, offering potential for kagome-lattice-based spintronics and quantum technologies.

cond-mat.mes-hall↗

arXiv2023

Vision Grid Transformer for Document Layout Analysis

Document pre-trained models and grid-based models have proven to be very effective on various tasks in Document AI. However, for the document layout analysis (DLA) task, existing document pre-trained models, even those pre-trained in a multi-modal fashion, usually rely on either textual features or visual features. Grid-based models for DLA are multi-modality but largely neglect the effect of pre-training. To fully leverage multi-modal information and exploit pre-training techniques to learn better representation for DLA, in this paper, we present VGT, a two-stream Vision Grid Transformer, in which Grid Transformer (GiT) is proposed and pre-trained for 2D token-level and segment-level semantic understanding. Furthermore, a new dataset named D$^4$LA, which is so far the most diverse and detailed manually-annotated benchmark for document layout analysis, is curated and released. Experiment results have illustrated that the proposed VGT model achieves new state-of-the-art results on DLA tasks, e.g. PubLayNet ($95.7\%$$\rightarrow$$96.2\%$), DocBank ($79.6\%$$\rightarrow$$84.1\%$), and D$^4$LA ($67.7\%$$\rightarrow$$68.8\%$). The code and models as well as the D$^4$LA dataset will be made publicly available ~\url{https://github.com/AlibabaResearch/AdvancedLiterateMachinery}.

cs.CV↗

arXiv2023

LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition

The diversity in length constitutes a significant characteristic of text. Due to the long-tail distribution of text lengths, most existing methods for scene text recognition (STR) only work well on short or seen-length text, lacking the capability of recognizing longer text or performing length extrapolation. This is a crucial issue, since the lengths of the text to be recognized are usually not given in advance in real-world applications, but it has not been adequately investigated in previous works. Therefore, we propose in this paper a method called Length-Insensitive Scene TExt Recognizer (LISTER), which remedies the limitation regarding the robustness to various text lengths. Specifically, a Neighbor Decoder is proposed to obtain accurate character attention maps with the assistance of a novel neighbor matrix regardless of the text lengths. Besides, a Feature Enhancement Module is devised to model the long-range dependency with low computation cost, which is able to perform iterations with the neighbor decoder to enhance the feature map progressively. To the best of our knowledge, we are the first to achieve effective length-insensitive scene text recognition. Extensive experiments demonstrate that the proposed LISTER algorithm exhibits obvious superiority on long text recognition and the ability for length extrapolation, while comparing favourably with the previous state-of-the-art methods on standard benchmarks for STR (mainly short text).

cs.CV↗

arXiv2023

Discovery and construction of surface kagome electronic states induced by p-d electronic hybridization

Kagome-lattice materials possess attractive properties for quantum computing applications, but their synthesis remains challenging. Herein, we show surface kagome electronic states (SKESs) on a Sn-terminated triangular Co3Sn2S2 surface, which are imprinted by vertical p-d electronic hybridization between the surface Sn (subsurface S) atoms and the buried Co kagome lattice network in the Co3Sn layer under the surface. Owing to the subsequent lateral hybridization of the Sn and S atoms in a corner-sharing manner, the kagome symmetry and topological electronic properties of the Co3Sn layer is proximate to the Sn surface. The SKESs and both hybridizations were verified via qPlus non-contact atomic force microscopy (nc-AFM) and density functional theory calculations. The construction of SKESs with tunable properties can be achieved by the atomic substitution of surface Sn (subsurface S) with other group III-V elements (Se or Te), which was demonstrated theoretically. This work exhibits the powerful capacity of nc-AFM in characterizing localized topological states and reveals the strategy for synthesis of large-area transition-metal-based kagome lattice materials using conventional surface deposition techniques.

cond-mat.mtrl-sci↗

arXiv2023

GeoLayoutLM: Geometric Pre-training for Visual Information Extraction

Visual information extraction (VIE) plays an important role in Document Intelligence. Generally, it is divided into two tasks: semantic entity recognition (SER) and relation extraction (RE). Recently, pre-trained models for documents have achieved substantial progress in VIE, particularly in SER. However, most of the existing models learn the geometric representation in an implicit way, which has been found insufficient for the RE task since geometric information is especially crucial for RE. Moreover, we reveal another factor that limits the performance of RE lies in the objective gap between the pre-training phase and the fine-tuning phase for RE. To tackle these issues, we propose in this paper a multi-modal framework, named GeoLayoutLM, for VIE. GeoLayoutLM explicitly models the geometric relations in pre-training, which we call geometric pre-training. Geometric pre-training is achieved by three specially designed geometry-related pre-training tasks. Additionally, novel relation heads, which are pre-trained by the geometric pre-training tasks and fine-tuned for RE, are elaborately designed to enrich and enhance the feature representation. According to extensive experiments on standard VIE benchmarks, GeoLayoutLM achieves highly competitive scores in the SER task and significantly outperforms the previous state-of-the-arts for RE (\eg, the F1 score of RE on FUNSD is boosted from 80.35\% to 89.45\%). The code and models are publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/GeoLayoutLM

cs.CV↗

arXiv2023

LORE: Logical Location Regression Network for Table Structure Recognition

cs.CV↗

arXiv2023

Twisted bilayer zigzag-graphene nanoribbon junctions with tunable edge states

Stacking two-dimensional layered materials such as graphene and transitional metal dichalcogenides with nonzero interlayer twist angles has recently become attractive because of the emergence of novel physical properties. Stacking of one-dimensional nanomaterials offers the lateral stacking offset as an additional parameter for modulating the resulting material properties. Here, we report that the edge states of twisted bilayer zigzag graphene nanoribbons (TBZGNRs) can be tuned with both the twist angle and the stacking offset. Strong edge state variations in the stacking region are first revealed by density functional theory (DFT) calculations. We construct and characterize twisted bilayer zigzag graphene nanoribbon (TBZGNR) systems on a Au(111) surface using scanning tunneling microscopy. A detailed analysis of three prototypical orthogonal TBZGNR junctions exhibiting different stacking offsets by means of scanning tunneling spectroscopy reveals emergent near-zero-energy states. From a comparison with DFT calculations, we conclude that the emergent edge states originate from the formation of flat bands whose energy and spin degeneracy are highly tunable with the stacking offset. Our work highlights fundamental differences between 2D and 1D twistronics and spurs further investigation of twisted one-dimensional systems.

cond-mat.mes-hall↗

arXiv2022

Velocity offset between emission and absorption lines might be an effective indicator of dual core system

This paper presents a detection of significant velocity offset between emission and absorption lines for a dual core system in SDSS~J155708.82+273518.74 (= SDSS~J1557). The photometric image of SDSS~J1557 exhibits clear two cores with a projected separation of $\sim$2.2 arcseconds (4.9 kpc) determined by GALFIT. Based on the applications of the commonly accepted pPXF code with 636 theoretical SSP templates, the host galaxy contribution can be well determined. Then, the emission line features of SDSS~J1557 can be well measured after subtraction of host starlight. It is found that the velocity offset of emission lines with respect to absorption lines reaches $458 \pm 13$ km/s. According to the Baldwin-Phillips-Terlevich (BPT) diagram, SDSS J1557 is a composite galaxy. In addition, SDSS J1557 can well fit the $M_{\rm BH}-σ_{\ast}$ relation of bulges and the galaxy merger would not change this relation. Two reasonable models (say, AGN-driven outflow vs. dual core system) have been discussed to explain this velocity offset. The model of AGN-driven outflow fails to interpret the systematic redshift of emission lines and similar velocity offsets for various emission lines in SDSS~J1557. A significant velocity offset between emission and absorption lines might be an effective indicator of dual core system.

astro-ph.GA↗

arXiv2022

Tailoring interfacial nanostructures at graphene/transition metal dichalcogenide heterostructures

Integration of two-dimensional (2D) van der Waals (vdWs) materials with non-2D materials to realize mixed-dimensional heterostructures has potential for creating functional devices beyond the reach of existing materials and has long been a pursuit of the material science community. Here we report the patterning of monolayer/bilayer transition metal dichalcogenide (TMD) nanostructures with nanometer-precision, tunable sizes and sites at interfaces of graphene/TMD heterostructures. Our experiments demonstrate that the TMD nanostructures can be created at selected positions of the interface using scanning tunneling microscope lithography and, more importantly, the sizes of the interfacial TMD nanostructures can be tuned with nanoscale precise by merging adjacent TMD nanostructures or by further tailoring. A structural phase transition from hexagonal phase in bulk TMD to monoclinic phase in the interfacial nanostructures is explicitly observed, which locally introduce well-defined electrostatic potentials on graphene. These results not only enable the creation of high-quality patterned p-n junctions in vdWs heterostructures, but also provide a new route to realize custom-designed mixed-dimensional heterostructures.

cond-mat.mtrl-sci↗

arXiv2022

Experimental evidence for electron-electron interaction and spin-charge separation in graphene quantum dots

Graphene quantum dots (GQDs) can exhibit a range of spectacular phenomena such as the Klein-tunneling-induced quasibound states1-6 and Berry-phase-tuned energy spectra7-15. According to previous studies, all these interesting quantum phenomena seem to be well understood in the free electron picture1-15. However, electronic motion in the GQDs is reduced to quantized orbits by quantum confinement, which implies that the kinetic energy may be comparable to or even smaller than the Coulomb energy of the quasiparticles, possibly resulting in exotic correlated phases in the GQDs. Here we present a scanning tunneling microscopy and spectroscopy study of gate-tunable GQDs in graphene/WSe2 heterostructure devices and report for the first time the observation of electron-electron interaction and correlation-induced spin-charge separation in the GQDs. Gating allows us to precise characterize effects of the electron-electron interaction on the energy spectra of the GQDs. By measuring density of states as a function of energy and position, we explicitly uncover two density waves with different velocities in the GQDs, attributing to spin-charge separation in real space.

cond-mat.mes-hall↗

arXiv2022

Cross-Modal Contrastive Learning for Robust Reasoning in VQA

Multi-modal reasoning in visual question answering (VQA) has witnessed rapid progress recently. However, most reasoning models heavily rely on shortcuts learned from training data, which prevents their usage in challenging real-world scenarios. In this paper, we propose a simple but effective cross-modal contrastive learning strategy to get rid of the shortcut reasoning caused by imbalanced annotations and improve the overall performance. Different from existing contrastive learning with complex negative categories on coarse (Image, Question, Answer) triplet level, we leverage the correspondences between the language and image modalities to perform finer-grained cross-modal contrastive learning. We treat each Question-Answer (QA) pair as a whole, and differentiate between images that conform with it and those against it. To alleviate the issue of sampling bias, we further build connected graphs among images. For each positive pair, we regard the images from different graphs as negative samples and deduct the version of multi-positive contrastive learning. To our best knowledge, it is the first paper that reveals a general contrastive learning strategy without delicate hand-craft rules can contribute to robust VQA reasoning. Experiments on several mainstream VQA datasets demonstrate our superiority compared to the state of the arts. Code is available at \url{https://github.com/qizhust/cmcl_vqa_pl}.

cs.CV↗

arXiv2022

Interweaving Polar Charge Orders in a Layered Metallic Super-atomic Crystal

Electronic properties of super-atomic crystals have not been sufficiently explored due to the versatility of their building units; moreover, their inter-unit couplings are even poorly understood. Here, we present a joint experiment-theory investigation of a rational-designed layered super-atomic crystal of Au6Te12Se8 cubes, stacked by non-covalent inter-cube quasi-bonds. We found a sequential-emerged anisotropic triple-cube charge-density-wave (tc-CDW) and polarized metallic states below 120 K, as revealed via scanning tunneling microscopy/spectroscopy, angle-resolved photoemission spectroscopy, transport measurement, Raman spectra, and density functional theory. The polarized states are locked in an anti-parallel configuration, which is required for maintaining the inversion symmetry of the center-cube in the tc-CDW. The anti-polar metallic states are thus interweaved by the charge-density-wave and the polarized metallic states, and primarily ascribed to electronic effects via theoretical calculations. This work not only demonstrates a microscopic picture of the interweaved CDW and polarized charge orders in the super-atomic crystal of ATS, but also sheds light on expanding the existing category of quantum materials to non-covalent solids.

cond-mat.mtrl-sci↗

arXiv2022

Coexistence of Reconstructed and Unreconstructed Structures in Structural Transition Regime of Twisted Bilayer Graphene

In twisted bilayer graphene (TBG), a twist-angle-dependent competition between interlayer stacking energy and intralayer elastic energy results in flat rigid layers at large twist angles and lattice reconstruction at small twist angles. Despite enormous scientific interest and effort in the TBG, however, an experimental study of evolution from the rigid lattice to the reconstructed lattice as a function of twist angle is still missing. Here we present a scanning tunneling microscopy and spectroscopy study to reveal the twist-angle-dependent lattice reconstruction in the TBG. Our experiment demonstrates that there is a transition regime between the rigid regime and the relaxed regime and, unexpectedly, the reconstructed and unreconstructed structures coexist in the transition regime. The coexistence of the two distinct structures in this regime may arise from subtle balance between the interlayer stacking energy and intralayer elastic energy in the TBG with intermediate moiré sizes.

cond-mat.mes-hall↗

arXiv2022

Stabilizing sample-wide Kekulé orders in graphene/transition metal dichalcogenide heterostructures

Kekulé phases are Peierls-like lattice distortions in graphene that are predicted to host novel electronic states beyond graphene (1-8). Although the Kekulé phases are realized in graphene through introducing electron-electron interactions at high magnetic fields (9-11) or adatom superlattices (12-15), it is still an extremely challenge to obtain large-area graphene Kekulé phases in experiment. Here we demonstrate that sample-wide Kekulé distortions in graphene can be stabilized by using transition metal dichalcogenides (TMDs) as substrates and the induced Kekulé orders are quite robust in the whole graphene/TMDs heterostructures with different twist angles. The commensurate structures of the heterostructures provide periodic scattering centers that break the translational symmetry of graphene and couple electrons of the two valleys in graphene, which tips the graphene toward global Kekulé density wave phases. Unexpectedly, three distinct Kekulé bond textures stabilized at various energies are directly imaged in every graphene/TMDs heterostructure. Our results reveal an unexpected sensitivity of electronic properties in graphene to the supporting substrates and provide an attractive route toward designing novel phases in graphene/TMDs heterostructures.

cond-mat.mtrl-sci↗