arXiv subjects

Liang He

Publications and source records attributed to Liang He.

At least 217 records · Page 12Linked to original sources

arXiv2023

MORE: A Multimodal Object-Entity Relation Extraction Dataset with a Benchmark Evaluation

Extracting relational facts from multimodal data is a crucial task in the field of multimedia and knowledge graphs that feeds into widespread real-world applications. The emphasis of recent studies centers on recognizing relational facts in which both entities are present in one modality and supplementary information is used from other modalities. However, such works disregard a substantial amount of multimodal relational facts that arise across different modalities, such as one entity seen in a text and another in an image. In this paper, we propose a new task, namely Multimodal Object-Entity Relation Extraction, which aims to extract "object-entity" relational facts from image and text data. To facilitate research on this task, we introduce MORE, a new dataset comprising 21 relation types and 20,264 multimodal relational facts annotated on 3,559 pairs of textual news titles and corresponding images. To show the challenges of Multimodal Object-Entity Relation Extraction, we evaluated recent state-of-the-art methods for multimodal relation extraction and conducted a comprehensive experimentation analysis on MORE. Our results demonstrate significant challenges for existing methods, underlining the need for further research on this task. Based on our experiments, we identify several promising directions for future research. The MORE dataset and code are available at https://github.com/NJUNLP/MORE.

cs.MM↗

arXiv2023

UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images

With the increasing prevalence of smartphones and websites, Image Aesthetic Assessment (IAA) has become increasingly crucial. While the significance of attributes in IAA is widely recognized, many attribute-based methods lack consideration for the selection and utilization of aesthetic attributes. Our initial step involves the acquisition of aesthetic attributes from both intra- and inter-perspectives. Within the intra-perspective, we extract the direct visual attributes of images, constituting the absolute attribute. In the inter-perspective, our focus lies in modeling the relative score relationships between images within the same sequence, forming the relative attribute. Then, to better utilize image attributes in aesthetic assessment, we propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images. For absolute attributes, we leverage multiple absolute-attribute perception modules and an absolute-attribute interacting network. The absolute-attribute perception modules are first pre-trained on several absolute-attribute learning tasks and then used to extract corresponding absolute attribute features. The absolute-attribute interacting network adaptively learns the weight of diverse absolute-attribute features, effectively integrating them with generic aesthetic features from various absolute-attribute perspectives and generating the aesthetic prediction. To model the relative attribute of images, we consider the relative ranking and relative distance relationships between images in a Relative-Relation Loss function, which boosts the robustness of the UMAAF. Furthermore, UMAAF achieves state-of-the-art performance on TAD66K and AVA datasets, and multiple experiments demonstrate the effectiveness of each module and the model's alignment with human preference.

cs.CV↗

arXiv2023

Reprogramming Self-supervised Learning-based Speech Representations for Speaker Anonymization

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker anonymization method based on recent End-to-End model reprogramming technology. To improve the anonymization performance, we first extract speaker representation from large SSL models as the speaker identifies. To hide the speaker's identity, we reprogram the speaker representation by adapting the speaker to a pseudo domain. Extensive experiments are carried out on the VoicePrivacy Challenge (VPC) 2022 datasets to demonstrate the effectiveness of our proposed parameter-efficient learning anonymization methods. Additionally, while achieving comparable performance with the VPC 2022 strong baseline 1.b, our approach consumes less computational resources during anonymization.

eess.AS↗

arXiv2023

GhostVec: A New Threat to Speaker Privacy of End-to-End Speech Recognition System

Speaker adaptation systems face privacy concerns, for such systems are trained on private datasets and often overfitting. This paper demonstrates that an attacker can extract speaker information by querying speaker-adapted speech recognition (ASR) systems. We focus on the speaker information of a transformer-based ASR and propose GhostVec, a simple and efficient attack method to extract the speaker information from an encoder-decoder-based ASR system without any external speaker verification system or natural human voice as a reference. To make our results quantitative, we pre-process GhostVec using singular value decomposition (SVD) and synthesize it into waveform. Experiment results show that the synthesized audio of GhostVec reaches 10.83\% EER and 0.47 minDCF with target speakers, which suggests the effectiveness of the proposed method. We hope the preliminary discovery in this study to catalyze future speech recognition research on privacy-preserving topics.

eess.AS↗

arXiv2023

Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction

ChatGPT has demonstrated impressive performance in various downstream tasks. However, in the Chinese Spelling Correction (CSC) task, we observe a discrepancy: while ChatGPT performs well under human evaluation, it scores poorly according to traditional metrics. We believe this inconsistency arises because the traditional metrics are not well-suited for evaluating generative models. Their overly strict length and phonics constraints may lead to underestimating ChatGPT's correction capabilities. To better evaluate generative models in the CSC task, this paper proposes a new evaluation metric: Eval-GCSC. By incorporating word-level and semantic similarity judgments, it relaxes the stringent length and phonics constraints. Experimental results show that Eval-GCSC closely aligns with human evaluations. Under this metric, ChatGPT's performance is comparable to traditional token-level classification models (TCM), demonstrating its potential as a CSC tool. The source code and scripts can be accessed at https://github.com/ktlKTL/Eval-GCSC.

cs.CL↗

arXiv2023

Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter

For performing regression tasks involved in various physics problems, enhancing the precision or equivalently reducing the uncertainty of regression results is undoubtedly one of the central goals. Here, somewhat surprisingly, we find that the unfavorable regression uncertainty in performing the regression tasks of inverse statistical problems actually contains hidden information concerning the phase transitions of the system under consideration. By utilizing this hidden information, we develop a new unsupervised machine learning approach for automated detection of phases of matter, dubbed learning from regression uncertainty. This is achieved by revealing an intrinsic connection between regression uncertainty and response properties of the system, thus making the outputs of this machine learning approach directly interpretable via conventional notions of physics. We demonstrate the approach by identifying the critical points of the ferromagnetic Ising model and the three-state clock model, and revealing the existence of the intermediate phase in the six-state and seven-state clock models. Comparing to the widely-used classification-based approaches developed so far, although successful, their recognized classes of patterns are essentially abstract, which hinders their straightforward relation to conventional notions of physics. These challenges persist even when one employs the state-of-the-art deep neural networks that excel at classification tasks. In contrast, with the core working horse being a neural network performing regression tasks, our new approach is not only practically more efficient, but also paves the way towards intriguing possibilities for unveiling new physics via machine learning in a physically interpretable manner.

cond-mat.stat-mech↗

arXiv2023

Reveal flocking phase transition of self-propelled active particles by machine learning regression uncertainty

We develop the neural network based "learning from regression uncertainty" approach for automated detection of phases of matter in nonequilibrium active systems. Taking the flocking phase transition of self-propelled active particles described by the Vicsek model for example, we find that after training a neural network for solving the inverse statistical problem, i.e., for performing the regression task of reconstructing the noise level from given samples of such a nonequilibrium many-body complex system's steady state configurations, the uncertainty of regression results obtained by the well-trained network can actually be utilized to reveal possible phase transitions in the system under study. The noise level dependence of regression uncertainty assumes a non-trivial M-shape, and its valley appears at the critical point of the flocking phase transition. By directly comparing this regression-based approach with the widely-used classification-based "learning by confusion" and "learning with blanking" approaches, we show that our approach has practical effectiveness, efficiency, good generality for various physical systems across interdisciplinary fields, and a greater possibility of being interpretable via conventional notions of physics. These approaches can complement each other to serve as a promising generic toolbox for investigating rich critical phenomena and providing data-driven evidence on the existence of various phase transitions, especially for those complex scenarios associated with first-order phase transitions or nonequilibrium active systems where traditional research methods in physics could face difficulties.

cond-mat.dis-nn↗

arXiv2023

3D Multiple Object Tracking on Autonomous Driving: A Literature Review

3D multi-object tracking (3D MOT) stands as a pivotal domain within autonomous driving, experiencing a surge in scholarly interest and commercial promise over recent years. Despite its paramount significance, 3D MOT confronts a myriad of formidable challenges, encompassing abrupt alterations in object appearances, pervasive occlusion, the presence of diminutive targets, data sparsity, missed detections, and the unpredictable initiation and termination of object motion trajectories. Countless methodologies have emerged to grapple with these issues, yet 3D MOT endures as a formidable problem that warrants further exploration. This paper undertakes a comprehensive examination, assessment, and synthesis of the research landscape in this domain, remaining attuned to the latest developments in 3D MOT while suggesting prospective avenues for future investigation. Our exploration commences with a systematic exposition of key facets of 3D MOT and its associated domains, including problem delineation, classification, methodological approaches, fundamental principles, and empirical investigations. Subsequently, we categorize these methodologies into distinct groups, dissecting each group meticulously with regard to its challenges, underlying rationale, progress, merits, and demerits. Furthermore, we present a concise recapitulation of experimental metrics and offer an overview of prevalent datasets, facilitating a quantitative comparison for a more intuitive assessment. Lastly, our deliberations culminate in a discussion of the prevailing research landscape, highlighting extant challenges and charting possible directions for 3D MOT research. We present a structured and lucid road-map to guide forthcoming endeavors in this field.

cs.CV↗

arXiv2023

DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding

Visually-situated languages such as charts and plots are omnipresent in real-world documents. These graphical depictions are human-readable and are often analyzed in visually-rich documents to address a variety of questions that necessitate complex reasoning and common-sense responses. Despite the growing number of datasets that aim to answer questions over charts, most only address this task in isolation, without considering the broader context of document-level question answering. Moreover, such datasets lack adequate common-sense reasoning information in their questions. In this work, we introduce a novel task named document-level chart question answering (DCQA). The goal of this task is to conduct document-level question answering, extracting charts or plots in the document via document layout analysis (DLA) first and subsequently performing chart question answering (CQA). The newly developed benchmark dataset comprises 50,010 synthetic documents integrating charts in a wide range of styles (6 styles in contrast to 3 for PlotQA and ChartQA) and includes 699,051 questions that demand a high degree of reasoning ability and common-sense understanding. Besides, we present the development of a potent question-answer generation engine that employs table data, a rich color set, and basic question templates to produce a vast array of reasoning question-answer pairs automatically. Based on DCQA, we devise an OCR-free transformer for document-level chart-oriented understanding, capable of DLA and answering complex reasoning and common-sense questions over charts in an OCR-free manner. Our DCQA dataset is expected to foster research on understanding visualizations in documents, especially for scenarios that require complex reasoning for charts in the visually-rich document. We implement and evaluate a set of baselines, and our proposed method achieves comparable results.

cs.AI↗

arXiv2023

FairMonitor: A Four-Stage Automatic Framework for Detecting Stereotypes and Biases in Large Language Models

Detecting stereotypes and biases in Large Language Models (LLMs) can enhance fairness and reduce adverse impacts on individuals or groups when these LLMs are applied. However, the majority of existing methods focus on measuring the model's preference towards sentences containing biases and stereotypes within datasets, which lacks interpretability and cannot detect implicit biases and stereotypes in the real world. To address this gap, this paper introduces a four-stage framework to directly evaluate stereotypes and biases in the generated content of LLMs, including direct inquiry testing, serial or adapted story testing, implicit association testing, and unknown situation testing. Additionally, the paper proposes multi-dimensional evaluation metrics and explainable zero-shot prompts for automated evaluation. Using the education sector as a case study, we constructed the Edu-FairMonitor based on the four-stage framework, which encompasses 12,632 open-ended questions covering nine sensitive factors and 26 educational scenarios. Experimental results reveal varying degrees of stereotypes and biases in five LLMs evaluated on Edu-FairMonitor. Moreover, the results of our proposed automated evaluation method have shown a high correlation with human annotations.

cs.CL↗

arXiv2023

Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering

Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features as input to the model results in the loss of fine-grained information within the evidence. Secondly, a gap exists between the feature extraction of evidence and the question, which hinders the model from effectively extracting critical features from the evidence based on the given question. We propose a two-stage framework for evidence retrieval and question-answering to alleviate these issues. First and foremost, we propose a progressive evidence refinement strategy for selecting crucial evidence. This strategy employs an iterative evidence retrieval approach to uncover the logical sequence among the evidence pieces. It incorporates two rounds of filtering to optimize the solution space, thus further ensuring temporal efficiency. Subsequently, we introduce a semi-supervised contrastive learning training strategy based on negative samples to expand the scope of the question domain, allowing for a more thorough exploration of latent knowledge within known samples. Finally, in order to mitigate the loss of fine-grained information, we devise a multi-turn retrieval and question-answering strategy to handle multimodal inputs. This strategy involves incorporating multimodal evidence directly into the model as part of the historical dialogue and question. Meanwhile, we leverage a cross-modal attention mechanism to capture the underlying connections between the evidence and the question, and the answer is generated through a decoding generation approach. We validate the model's effectiveness through extensive experiments, achieving outstanding performance on WebQA and MultimodelQA benchmark tests.

cs.AI↗

arXiv2023

Towards Better Chain-of-Thought Prompting Strategies: A Survey

Chain-of-Thought (CoT), a step-wise and coherent reasoning chain, shows its impressive strength when used as a prompting strategy for large language models (LLM). Recent years, the prominent effect of CoT prompting has attracted emerging research. However, there still lacks of a systematic summary about key factors of CoT prompting and comprehensive guide for prompts utilizing. For a deeper understanding about CoT prompting, we survey on a wide range of current research, presenting a systematic and comprehensive analysis on several factors that may influence the effect of CoT prompting, and introduce how to better apply it in different applications under these discussions. We further analyze the challenges and propose some future directions about CoT prompting. This survey could provide an overall reference on related research.

cs.CL↗

arXiv2023

UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model

Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs. In this work, we propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM). By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters and the training cost is much lower than previous work following domain-specific pretraining and finetuning paradigms. Concretely, UReader is jointly finetuned on a wide range of Visually-situated Language Understanding tasks via a unified instruction format. To enhance the visual text and semantic understanding, we further apply two auxiliary tasks with the same format, namely text reading and key points generation tasks. We design a shape-adaptive cropping module before the encoder-decoder architecture of MLLM to leverage the frozen low-resolution vision encoder for processing high-resolution images. Without downstream finetuning, our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks, across 5 domains: documents, tables, charts, natural images, and webpage screenshots. Codes and instruction-tuning datasets will be released.

cs.CV↗

arXiv2023

SPADA: A Toolbox of Designing Soft Pneumatic Actuators for Shape Matching based on Surrogate Modeling

Soft pneumatic actuators (SPAs) produce motions for soft robots with simple pressure input, however they require to be appropriately designed to fit the target application. Available design methods employ kinematic models and optimization to estimate the actuator response and the optimal design parameters, to achieve a target actuator's shape. Within SPAs, Bellow-SPAs excel in rapid prototyping and large deformation, yet their kinematic models often lack accuracy due to the geometry complexity and the material nonlinearity. Furthermore, existing shape-matching algorithms are not providing an end-to-end solution from the desired shape to the actuator. In addition, despite the availability of computational design pipelines, an accessible and user-friendly toolbox for direct application remains elusive. This paper addresses these challenges, offering an end-to-end shape-matching design framework for bellow-SPAs to streamline the design process, and the open-source toolbox SPADA (Soft Pneumatic Actuator Design frAmework) implementing the framework with a GUI for easy access. It provides a kinematic model grounded on a modular design to improve accuracy, Finite Element Method (FEM) simulations, and piecewise constant curvature (PCC) approximation. An Artificial Neural Network-trained surrogate model, based on FEM simulation data, is trained for fast computation in optimization. A shape-matching algorithm, merging 3D PCC segmentation and a surrogate model-based genetic algorithm, identifies optimal actuator design parameters for desired shapes. The toolbox, implementing the proposed design framework, has proven its end-to-end capability in designing actuators to precisely match 2D shapes with root-mean-square errors of 4.16, 2.70, and 2.51mm, and demonstrating its potential by designing a 3D deformable actuator.

cs.RO↗

arXiv2023

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Existing offboard 3D detectors always follow a modular pipeline design to take advantage of unlimited sequential point clouds. We have found that the full potential of offboard 3D detectors is not explored mainly due to two reasons: (1) the onboard multi-object tracker cannot generate sufficient complete object trajectories, and (2) the motion state of objects poses an inevitable challenge for the object-centric refining stage in leveraging the long-term temporal context representation. To tackle these problems, we propose a novel paradigm of offboard 3D object detection, named DetZero. Concretely, an offline tracker coupled with a multi-frame detector is proposed to focus on the completeness of generated object tracks. An attention-mechanism refining module is proposed to strengthen contextual information interaction across long-term sequential point clouds for object refining with decomposed regression methods. Extensive experiments on Waymo Open Dataset show our DetZero outperforms all state-of-the-art onboard and offboard 3D detection methods. Notably, DetZero ranks 1st place on Waymo 3D object detection leaderboard with 85.15 mAPH (L2) detection performance. Further experiments validate the application of taking the place of human labels with such high-quality results. Our empirical study leads to rethinking conventions and interesting findings that can guide future research on offboard 3D object detection.

cs.CV↗

arXiv2023

Graph Neural Network Backend for Speaker Recognition

Currently, most speaker recognition backends, such as cosine, linear discriminant analysis (LDA), or probabilistic linear discriminant analysis (PLDA), make decisions by calculating similarity or distance between enrollment and test embeddings which are already extracted from neural networks. However, for each embedding, the local structure of itself and its neighbor embeddings in the low-dimensional space is different, which may be helpful for the recognition but is often ignored. In order to take advantage of it, we propose a graph neural network (GNN) backend to mine latent relationships among embeddings for classification. We assume all the embeddings as nodes on a graph, and their edges are computed based on some similarity function, such as cosine, LDA+cosine, or LDA+PLDA. We study different graph settings and explore variants of GNN to find a better message passing and aggregation way to accomplish the recognition task. Experimental results on NIST SRE14 i-vector challenging, VoxCeleb1-O, VoxCeleb1-E, and VoxCeleb1-H datasets demonstrate that our proposed GNN backends significantly outperform current mainstream methods.

eess.AS↗

arXiv2023

Measurement-induced integer families of critical dynamical scaling in quantum many-body systems

A quantum many-body system can undergo transitions in the presence of continuous measurement. In this work, we find that a generic class of critical dynamical scaling behavior can emerge at these measurement-induced transitions. Remarkably, depending on the symmetry that can be respected by the system, different integer families of dynamical scaling can emerge. The origin of these scaling families can be traced back to the presence of hierarchies of high order exceptional points in the effective non-Hermitian descriptions of the systems. Direct experimental observation of this class of dynamical scaling behavior can be readily achieved using ultracold atoms in optical lattices or through intermediate-scale quantum computing systems.

cond-mat.quant-gas↗

arXiv2023

3D Printing Magnetophoretic Displays

We present a pipeline for printing interactive and always-on magnetophoretic displays using affordable Fused Deposition Modeling (FDM) 3D printers. Using our pipeline, an end-user can convert the surface of a 3D shape into a matrix of voxels. The generated model can be sent to an FDM 3D printer equipped with an additional syringe-based injector. During the printing process, an oil and iron powder-based liquid mixture is injected into each voxel cell, allowing the appearance of the once-printed object to be editable with external magnetic sources. To achieve this, we made modifications to the 3D printer hardware and the firmware. We also developed a 3D editor to prepare printable models. We demonstrate our pipeline with a variety of examples, including a printed Stanford bunny with customizable appearances, a small espresso mug that can be used as a post-it note surface, a board game figurine with a computationally updated display, and a collection of flexible wearable accessories with editable visuals.

cs.HC↗