Search

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.

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., Comment: Accepted at ECCV 2024. The dataset and code can be accessed at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/WebRPG

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.

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., Comment: This paper is received by https://ieee-metacom.org

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., Comment: CVPR 2024 Workshop -- AI for Streaming (AIS) Video Quality Assessment Challenge

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., Comment: 9 pages, 5 figures, accepted to be published in MNRAS Letter

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, Comment: CVPR 2024

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., Comment: arXiv admin note: substantial text overlap with arXiv:2303.03730

In this article we exhibit new explicit families of congruences for the overpartition function, making effective the existence results given previously by Treneer. We give infinite families of congruences modulo $m$ for $m = 5, 7, 11$, and finite families for $m = 13, 17, 19$., Comment: Added an author, improved results

The primary focus of this paper is overpartitions, a type of partition that plays a significant role in $q$-series theory. In 2006, Treneer discovered an explicit infinite family of congruences of overpartitions modulo $5$. In our research, we have identified explicit infinite families of congruences of overpartitions modulo $3,7,11$. This work reveals the connection between overpartitions and half-integral modular forms.

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}., Comment: Accepted by ICCV2023

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)., Comment: ICCV 2023

The main result of the paper is the Fibonacci-like property of the partition function. The partition function $p(n)$ has a property: $p(n) \leq p(n-1) + p(n-2)$. Our result shows that if we impose certain restrictions on the partition, then the inequality becomes an equality. Furthermore, we extend this result to cases with a greater number of summands., Comment: First draft

The main result of the paper is the existence of an infinitely many families of Ramanujan-type congruences for $b_4(n)$ and $b_6(n)$ modulo primes $m \geq 2$ and $m \geq 5$, respectively. We provide new examples of congruences for $b_4(n)$ and $b_6(n)$. Moreover, we find two infinite explicit infinite families of congruences for $b_4(n)$ modulo $3$., Comment: 13 pages. v2: Append results for b_4(n) modulo 2, b_6(n) modulo 5. v3: We find two explicit infinite families of b_4(n) modulo 3. See Theorem 1.2

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.

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.

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, Comment: CVPR 2023 Highlight