arXiv subjects

Qi Zheng

Publications and source records attributed to Qi Zheng.

At least 55 records · Page 3Linked to original sources

arXiv2025

Optical QPOs with dual periodicities 1103days and 243days in the blue quasar SDSS J100438.8+151056

This manuscript investigates the possible existence of a binary supermassive black holes (BSMBH) system in the blue quasar SDSS J100438.8+151056 (=SDSS J1004+1510) at z=0.219 based on the detection of robust optical QPOs. We determine QPOs using multiple analysis methods applied to the CSS-V, ZTFg/r band light curves, and additionally, combined with the characteristics of broad emission lines and explores potential mechanisms for the QPOs, including jet and disk precession models. Two distinct periodicities, $1103\pm260$days and $243\pm29$days, are identified in the ZTF g/r-band light curves with confidence level exceeding $5σ$, through four different techniques. Meanwhile, the $1103\pm260$days periodicity is also clearly detected in the CSS V-band light curve. The optical periodicities suggest a BSMBH system candidate in SDSS J1004+1510, with an estimated total virial BH mass of $(1.13\pm0.14)\times10^8 M_{\odot}$ and a space separation of $0.0053\pm0.0016$pc for the periodicity of $1103\pm260$days. The second periodicity of $243\pm29$days could be attributed to harmonic oscillations, considering $(1103\pm260)/(243\pm29)\sim4.54\pm0.47$ with large scatters. However, if the periodicity of $243\pm29$days was from an independent QPO, a triple BH system candidate on sub-pc scale could be probably expected, with space separations of $0.00036\pm0.00004$pc between a close BSMBH system and of $0.0053\pm0.0016$pc between the BSMBH system and the third BH, after considering similar BH mass of the third BH as the total mass of the central BSMBH. These findings strongly demonstrate that combined light curves from the different sky survey projects can lead to more reliable QPOs candidates to be detected, and also indicate higher quality light curves could be helpful to find probably potential QPOs with multiple periodicities leading to rare detections of candidates for sub-pc triple BH systems.

astro-ph.GA↗

arXiv2025

A Simple yet Effective Layout Token in Large Language Models for Document Understanding

Recent methods that integrate spatial layouts with text for document understanding in large language models (LLMs) have shown promising results. A commonly used method is to represent layout information as text tokens and interleave them with text content as inputs to the LLMs. However, such a method still demonstrates limitations, as it requires additional position IDs for tokens that are used to represent layout information. Due to the constraint on max position IDs, assigning them to layout information reduces those available for text content, reducing the capacity for the model to learn from the text during training, while also introducing a large number of potentially untrained position IDs during long-context inference, which can hinder performance on document understanding tasks. To address these issues, we propose LayTokenLLM, a simple yet effective method for document understanding. LayTokenLLM represents layout information as a single token per text segment and uses a specialized positional encoding scheme. It shares position IDs between text and layout tokens, eliminating the need for additional position IDs. This design maintains the model's capacity to learn from text while mitigating long-context issues during inference. Furthermore, a novel pre-training objective called Next Interleaved Text and Layout Token Prediction (NTLP) is devised to enhance cross-modality learning between text and layout tokens. Extensive experiments show that LayTokenLLM outperforms existing layout-integrated LLMs and MLLMs of similar scales on multi-page document understanding tasks, as well as most single-page tasks.

cs.CV↗

arXiv2025

ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data

Recently, large language models (LLMs) and multimodal large language models (MLLMs) have demonstrated promising results on document visual question answering (VQA) task, particularly after training on document instruction datasets. An effective evaluation method for document instruction data is crucial in constructing instruction data with high efficacy, which, in turn, facilitates the training of LLMs and MLLMs for document VQA. However, most existing evaluation methods for instruction data are limited to the textual content of the instructions themselves, thereby hindering the effective assessment of document instruction datasets and constraining their construction. In this paper, we propose ProcTag, a data-oriented method that assesses the efficacy of document instruction data. ProcTag innovatively performs tagging on the execution process of instructions rather than the instruction text itself. By leveraging the diversity and complexity of these tags to assess the efficacy of the given dataset, ProcTag enables selective sampling or filtering of document instructions. Furthermore, DocLayPrompt, a novel semi-structured layout-aware document prompting strategy, is proposed for effectively representing documents. Experiments demonstrate that sampling existing open-sourced and generated document VQA/instruction datasets with ProcTag significantly outperforms current methods for evaluating instruction data. Impressively, with ProcTag-based sampling in the generated document datasets, only 30.5\% of the document instructions are required to achieve 100\% efficacy compared to the complete dataset. The code is publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/ProcTag.

cs.CV↗

arXiv2025

End-to-End HOI Reconstruction Transformer with Graph-based Encoding

With the diversification of human-object interaction (HOI) applications and the success of capturing human meshes, HOI reconstruction has gained widespread attention. Existing mainstream HOI reconstruction methods often rely on explicitly modeling interactions between humans and objects. However, such a way leads to a natural conflict between 3D mesh reconstruction, which emphasizes global structure, and fine-grained contact reconstruction, which focuses on local details. To address the limitations of explicit modeling, we propose the End-to-End HOI Reconstruction Transformer with Graph-based Encoding (HOI-TG). It implicitly learns the interaction between humans and objects by leveraging self-attention mechanisms. Within the transformer architecture, we devise graph residual blocks to aggregate the topology among vertices of different spatial structures. This dual focus effectively balances global and local representations. Without bells and whistles, HOI-TG achieves state-of-the-art performance on BEHAVE and InterCap datasets. Particularly on the challenging InterCap dataset, our method improves the reconstruction results for human and object meshes by 8.9% and 8.6%, respectively.

cs.CV↗

arXiv2025

The orbital kinematics of kpc-scale dual-core systems with double-peaked narrow emission lines

In this manuscript, based on SDSS photometry and spectroscopy, a method is proposed to test the hypothesis that the orbital kinematics of kpc-scale dual-core systems can lead to double-peaked narrow emission lines (DPNELs), through analyzing a sample of seven kpc-scale dual-core systems by comparing the upper limits of their orbital velocities (calculated using total stellar mass and projected distance) with the velocity separation of DPNELs (peak separation). To determine accurate total stellar masses, GALFIT is applied to consider the effects of the overlapping components on the photometric images to obtain accurate magnitudes. Then, based on the correlation between absolute Petrosian magnitudes and total stellar masses, the individual masses of the galaxies are determined. Therefore, the maximum orbital velocities can be calculated by combining the projected distance. Meanwhile, the peak separation can be accurately measured after subtracting the pPXF determined host galaxy contributions. Finally, four objects exhibit peak separations almost consistent with their respective maximum orbital velocities under the assumption of a circular orbit, while the remaining three objects display peak separations larger than the maximum orbital velocities. A larger sample will be given later to further test whether DPNELs can arise from kpc-scale dual-core systems.

astro-ph.GA↗

arXiv2025

On type 1 active galactic nuclei with double-peaked [O~{\sc iii}]. I. data sample and basic results

Double-peaked narrow emission lines (DPNELs) might be evidence for the existence of kpc-scale dual AGNs. There are so far large samples of objects with DPNELs in narrow emission line galaxies. Here, a systematic search is made to build a sample of type 1 AGNs with double-peaked [O~{\sc~iii}] from Data Release 16 of the Sloan Digital Sky Survey (SDSS). Through visually inspecting and fitting [O~{\sc~iii}], fitting broad H$α$ emission lines, performing F-test for [O~{\sc~iii}] profiles, and checking broad H$β$ and [O~{\sc~iii}] emission lines, we select 62 type 1 AGNs with reliable double-peaked [O~{\sc~iii}] from 11557 QSOs with z < 0.3. After visually checking the 62 SDSS multi-color images, we find only seven objects with signs of merging. Four possible models for the double-peaked [O~{\sc~iii}] observed in our sample are discussed: the superposition model, AGN outflow model, dual AGN model, and rotating disk model. However, the current results can not provide any one explanation conclusively, and additional observational data are needed to provide the details of narrow line regions. But at least 22 objects with different velocity offsets between double-peaked [O~{\sc~iii}] and narrow H$α$ emission lines could be excluded as dual AGN candidates. The relative velocity offsets of the [O~{\sc~iii}] blue-shifted/red-shifted components are negative to their line flux ratios, which is consistent with dual AGN model. This work provides a new sample of 62 type 1 AGNs with double-peaked [O~{\sc~iii}] for further study.

astro-ph.GA↗

arXiv2025

A Robust and Efficient Visual-Inertial Initialization with Probabilistic Normal Epipolar Constraint

Accurate and robust initialization is essential for Visual-Inertial Odometry (VIO), as poor initialization can severely degrade pose accuracy. During initialization, it is crucial to estimate parameters such as accelerometer bias, gyroscope bias, initial velocity, gravity, etc. Most existing VIO initialization methods adopt Structure from Motion (SfM) to solve for gyroscope bias. However, SfM is not stable and efficient enough in fast-motion or degenerate scenes. To overcome these limitations, we extended the rotation-translation-decoupled framework by adding new uncertainty parameters and optimization modules. First, we adopt a gyroscope bias estimator that incorporates probabilistic normal epipolar constraints. Second, we fuse IMU and visual measurements to solve for velocity, gravity, and scale efficiently. Finally, we design an additional refinement module that effectively reduces gravity and scale errors. Extensive EuRoC dataset tests show that our method reduces gyroscope bias and rotation errors by 16\% and 4\% on average, and gravity error by 29\% on average. On the TUM dataset, our method reduces the gravity error and scale error by 14.2\% and 5.7\% on average respectively. The source code is available at https://github.com/MUCS714/DRT-PNEC.git

cs.RO↗

arXiv2025

An Atomic Skill Library Construction Method for Data-Efficient Embodied Manipulation

Embodied manipulation is a fundamental ability in the realm of embodied artificial intelligence. Although current embodied manipulation models show certain generalizations in specific settings, they struggle in new environments and tasks due to the complexity and diversity of real-world scenarios. The traditional end-to-end data collection and training manner leads to significant data demands. Decomposing end-to-end tasks into atomic skills helps reduce data requirements and improves the task success rate. However, existing methods are limited by predefined skill sets that cannot be dynamically updated. To address the issue, we introduce a three-wheeled data-driven method to build an atomic skill library. We divide tasks into subtasks using the Vision-Language-Planning (VLP). Then, atomic skill definitions are formed by abstracting the subtasks. Finally, an atomic skill library is constructed via data collection and Vision-Language-Action (VLA) fine-tuning. As the atomic skill library expands dynamically with the three-wheel update strategy, the range of tasks it can cover grows naturally. In this way, our method shifts focus from end-to-end tasks to atomic skills, significantly reducing data costs while maintaining high performance and enabling efficient adaptation to new tasks. Extensive experiments in real-world settings demonstrate the effectiveness and efficiency of our approach.

cs.RO↗

arXiv2024

M3-CVC: Controllable Video Compression with Multimodal Generative Models

Traditional and neural video codecs commonly encounter limitations in controllability and generality under ultra-low-bitrate coding scenarios. To overcome these challenges, we propose M3-CVC, a controllable video compression framework incorporating multimodal generative models. The framework utilizes a semantic-motion composite strategy for keyframe selection to retain critical information. For each keyframe and its corresponding video clip, a dialogue-based large multimodal model (LMM) approach extracts hierarchical spatiotemporal details, enabling both inter-frame and intra-frame representations for improved video fidelity while enhancing encoding interpretability. M3-CVC further employs a conditional diffusion-based, text-guided keyframe compression method, achieving high fidelity in frame reconstruction. During decoding, textual descriptions derived from LMMs guide the diffusion process to restore the original video's content accurately. Experimental results demonstrate that M3-CVC significantly outperforms the state-of-the-art VVC standard in ultra-low bitrate scenarios, particularly in preserving semantic and perceptual fidelity.

eess.IV↗

arXiv2024

ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting

Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to learn spatial-temporal representations. However, it encounters three key challenges: 1) the difficulty in selecting reliable negative pairs due to the homogeneity of variables, hindering contrastive learning methods; 2) overlooking spatial correlations across variables over time; 3) limitations of efficiency and scalability in existing self-supervised learning methods. To tackle these, we propose a lightweight representation-learning model ST-ReP, integrating current value reconstruction and future value prediction into the pre-training framework for spatial-temporal forecasting. And we design a new spatial-temporal encoder to model fine-grained relationships. Moreover, multi-time scale analysis is incorporated into the self-supervised loss to enhance predictive capability. Experimental results across diverse domains demonstrate that the proposed model surpasses pre-training-based baselines, showcasing its ability to learn compact and semantically enriched representations while exhibiting superior scalability.

cs.LG↗

arXiv2024

Video Quality Assessment: A Comprehensive Survey

Video quality assessment (VQA) is an important processing task, aiming at predicting the quality of videos in a manner highly consistent with human judgments of perceived quality. Traditional VQA models based on natural image and/or video statistics, which are inspired both by models of projected images of the real world and by dual models of the human visual system, deliver only limited prediction performances on real-world user-generated content (UGC), as exemplified in recent large-scale VQA databases containing large numbers of diverse video contents crawled from the web. Fortunately, recent advances in deep neural networks and Large Multimodality Models (LMMs) have enabled significant progress in solving this problem, yielding better results than prior handcrafted models. Numerous deep learning-based VQA models have been developed, with progress in this direction driven by the creation of content-diverse, large-scale human-labeled databases that supply ground truth psychometric video quality data. Here, we present a comprehensive survey of recent progress in the development of VQA algorithms and the benchmarking studies and databases that make them possible. We also analyze open research directions on study design and VQA algorithm architectures. Github link: https://github.com/taco-group/Video-Quality-Assessment-A-Comprehensive-Survey.

eess.IV↗

arXiv2024

Unicorn: Unified Neural Image Compression with One Number Reconstruction

Prevalent lossy image compression schemes can be divided into: 1) explicit image compression (EIC), including traditional standards and neural end-to-end algorithms; 2) implicit image compression (IIC) based on implicit neural representations (INR). The former is encountering impasses of either leveling off bitrate reduction at a cost of tremendous complexity while the latter suffers from excessive smoothing quality as well as lengthy decoder models. In this paper, we propose an innovative paradigm, which we dub \textbf{Unicorn} (\textbf{U}nified \textbf{N}eural \textbf{I}mage \textbf{C}ompression with \textbf{O}ne \textbf{N}number \textbf{R}econstruction). By conceptualizing the images as index-image pairs and learning the inherent distribution of pairs in a subtle neural network model, Unicorn can reconstruct a visually pleasing image from a randomly generated noise with only one index number. The neural model serves as the unified decoder of images while the noises and indexes corresponds to explicit representations. As a proof of concept, we propose an effective and efficient prototype of Unicorn based on latent diffusion models with tailored model designs. Quantitive and qualitative experimental results demonstrate that our prototype achieves significant bitrates reduction compared with EIC and IIC algorithms. More impressively, benefitting from the unified decoder, our compression ratio escalates as the quantity of images increases. We envision that more advanced model designs will endow Unicorn with greater potential in image compression. We will release our codes in \url{https://github.com/uniqzheng/Unicorn-Laduree}.

cs.CV↗

arXiv2024

Application of an ANN and LSTM-based Ensemble Model for Stock Market Prediction

Stock trading has always been a key economic indicator in modern society and a primary source of profit for financial giants such as investment banks, quantitative trading firms, and hedge funds. Discovering the underlying patterns within the seemingly volatile yet intrinsically structured economic activities has become a central focus of research for many companies. Our study leverages widely-used modern financial forecasting algorithms, including LSTM, ANN, CNN, and BiLSTM. We begin by comparing the predictive performance of these well-known algorithms on our stock market data, utilizing metrics such as R2, MAE, MSE, RMSE for detailed evaluation. Based on the performance of these models, we then aim to combine their strengths while mitigating their weaknesses, striving to construct a powerful hybrid model that overcomes the performance limitations of individual models.Through rigorous experimentation and exploration, we ultimately developed an LSTM+ANN model that breaks through prior performance bottlenecks, achieving promising and exciting results.

cs.CE↗

arXiv2024

Advanced Payment Security System:XGBoost, LightGBM and SMOTE Integrated

With the rise of various online and mobile payment systems, transaction fraud has become a significant threat to financial security. This study explores the application of advanced machine learning models, specifically based on XGBoost and LightGBM, for developing a more accurate and robust Payment Security Protection Model. To enhance data reliability, we meticulously processed the data sources and applied SMOTE (Synthetic Minority Over-sampling Technique) to address class imbalance and improve data representation. By selecting highly correlated features, we aimed to strengthen the training process and boost model performance. We conducted thorough performance evaluations of our proposed models, comparing them against traditional methods including Random Forest, Neural Network, and Logistic Regression. Using metrics such as Precision, Recall, and F1 Score, we rigorously assessed their effectiveness. Our detailed analyses and comparisons reveal that the combination of SMOTE with XGBoost and LightGBM offers a highly efficient and powerful mechanism for payment security protection. Moreover, the integration of XGBoost and LightGBM in a Local Ensemble model further demonstrated outstanding performance. After incorporating SMOTE, the new combined model achieved a significant improvement of nearly 6\% over traditional models and around 5\% over its sub-models, showcasing remarkable results.

cs.CR↗

arXiv2024

Enhanced Credit Score Prediction Using Ensemble Deep Learning Model

In contemporary economic society, credit scores are crucial for every participant. A robust credit evaluation system is essential for the profitability of core businesses such as credit cards, loans, and investments for commercial banks and the financial sector. This paper combines high-performance models like XGBoost and LightGBM, already widely used in modern banking systems, with the powerful TabNet model. We have developed a potent model capable of accurately determining credit score levels by integrating Random Forest, XGBoost, and TabNet, and through the stacking technique in ensemble modeling. This approach surpasses the limitations of single models and significantly advances the precise credit score prediction. In the following sections, we will explain the techniques we used and thoroughly validate our approach by comprehensively comparing a series of metrics such as Precision, Recall, F1, and AUC. By integrating Random Forest, XGBoost, and with the TabNet deep learning architecture, these models complement each other, demonstrating exceptionally strong overall performance.

cs.LG↗

arXiv2024

AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results

Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html.

eess.IV↗

arXiv2024

WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation

In the era of content creation revolution propelled by advancements in generative models, the field of web design remains unexplored despite its critical role in modern digital communication. The web design process is complex and often time-consuming, especially for those with limited expertise. In this paper, we introduce Web Rendering Parameters Generation (WebRPG), a new task that aims at automating the generation for visual presentation of web pages based on their HTML code. WebRPG would contribute to a faster web development workflow. Since there is no existing benchmark available, we develop a new dataset for WebRPG through an automated pipeline. Moreover, we present baseline models, utilizing VAE to manage numerous elements and rendering parameters, along with custom HTML embedding for capturing essential semantic and hierarchical information from HTML. Extensive experiments, including customized quantitative evaluations for this specific task, are conducted to evaluate the quality of the generated results.

cs.CV↗

arXiv2024

ESceme: Vision-and-Language Navigation with Episodic Scene Memory

Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes. Existing approaches have made enormous progress in navigation in new environments, such as beam search, pre-exploration, and dynamic or hierarchical history encoding. To balance generalization and efficiency, we resort to memorizing visited scenarios apart from the ongoing route while navigating. In this work, we introduce a mechanism of Episodic Scene memory (ESceme) for VLN that wakes an agent's memories of past visits when it enters the current scene. The episodic scene memory allows the agent to envision a bigger picture of the next prediction. This way, the agent learns to utilize dynamically updated information instead of merely adapting to the current observations. We provide a simple yet effective implementation of ESceme by enhancing the accessible views at each location and progressively completing the memory while navigating. We verify the superiority of ESceme on short-horizon (R2R), long-horizon (R4R), and vision-and-dialog (CVDN) VLN tasks. Our ESceme also wins first place on the CVDN leaderboard. Code is available: \url{https://github.com/qizhust/esceme}.

cs.CV↗