arXiv subjects

Rui Liu

Publications and source records attributed to Rui Liu.

At least 253 records · Page 14Linked to original sources

arXiv2024

Reactive Multi-Robot Navigation in Outdoor Environments Through Uncertainty-Aware Active Learning of Human Preference Landscape

Compared with single robots, Multi-Robot Systems (MRS) can perform missions more efficiently due to the presence of multiple members with diverse capabilities. However, deploying an MRS in wide real-world environments is still challenging due to uncertain and various obstacles (e.g., building clusters and trees). With a limited understanding of environmental uncertainty on performance, an MRS cannot flexibly adjust its behaviors (e.g., teaming, load sharing, trajectory planning) to ensure both environment adaptation and task accomplishments. In this work, a novel joint preference landscape learning and behavior adjusting framework (PLBA) is designed. PLBA efficiently integrates real-time human guidance to MRS coordination and utilizes Sparse Variational Gaussian Processes with Varying Output Noise to quickly assess human preferences by leveraging spatial correlations between environment characteristics. An optimization-based behavior-adjusting method then safely adapts MRS behaviors to environments. To validate PLBA's effectiveness in MRS behavior adaption, a flood disaster search and rescue task was designed. 20 human users provided 1764 feedback based on human preferences obtained from MRS behaviors related to "task quality", "task progress", "robot safety". The prediction accuracy and adaptation speed results show the effectiveness of PLBA in preference learning and MRS behavior adaption.

cs.RO↗

arXiv2024

Leveraging Retrieval Augment Approach for Multimodal Emotion Recognition Under Missing Modalities

Multimodal emotion recognition utilizes complete multimodal information and robust multimodal joint representation to gain high performance. However, the ideal condition of full modality integrity is often not applicable in reality and there always appears the situation that some modalities are missing. For example, video, audio, or text data is missing due to sensor failure or network bandwidth problems, which presents a great challenge to MER research. Traditional methods extract useful information from the complete modalities and reconstruct the missing modalities to learn robust multimodal joint representation. These methods have laid a solid foundation for research in this field, and to a certain extent, alleviated the difficulty of multimodal emotion recognition under missing modalities. However, relying solely on internal reconstruction and multimodal joint learning has its limitations, especially when the missing information is critical for emotion recognition. To address this challenge, we propose a novel framework of Retrieval Augment for Missing Modality Multimodal Emotion Recognition (RAMER), which introduces similar multimodal emotion data to enhance the performance of emotion recognition under missing modalities. By leveraging databases, that contain related multimodal emotion data, we can retrieve similar multimodal emotion information to fill in the gaps left by missing modalities. Various experimental results demonstrate that our framework is superior to existing state-of-the-art approaches in missing modality MER tasks. Our whole project is publicly available on https://github.com/WooyoohL/Retrieval_Augment_MER.

cs.CV↗

arXiv2024

Learning Noise-Robust Joint Representation for Multimodal Emotion Recognition under Incomplete Data Scenarios

Multimodal emotion recognition (MER) in practical scenarios is significantly challenged by the presence of missing or incomplete data across different modalities. To overcome these challenges, researchers have aimed to simulate incomplete conditions during the training phase to enhance the system's overall robustness. Traditional methods have often involved discarding data or substituting data segments with zero vectors to approximate these incompletenesses. However, such approaches neither accurately represent real-world conditions nor adequately address the issue of noisy data availability. For instance, a blurry image cannot be simply replaced with zero vectors, while still retaining information. To tackle this issue and develop a more precise MER system, we introduce a novel noise-robust MER model that effectively learns robust multimodal joint representations from noisy data. This approach includes two pivotal components: firstly, a noise scheduler that adjusts the type and level of noise in the data to emulate various realistic incomplete situations. Secondly, a Variational AutoEncoder (VAE)-based module is employed to reconstruct these robust multimodal joint representations from the noisy inputs. Notably, the introduction of the noise scheduler enables the exploration of an entirely new type of incomplete data condition, which is impossible with existing methods. Extensive experimental evaluations on the benchmark datasets IEMOCAP and CMU-MOSEI demonstrate the effectiveness of the noise scheduler and the excellent performance of our proposed model. Our project is publicly available on https://github.com/WooyoohL/Noise-robust_MER.

cs.CV↗

arXiv2024

MCDubber: Multimodal Context-Aware Expressive Video Dubbing

Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized speech. However, it is crucial to consider whether the prosody of the generated dubbing aligns with the multimodal context, as the dubbing will be combined with the original context in the final video. This aspect has been overlooked in previous studies. To address this issue, we propose a Multimodal Context-aware video Dubbing model, termed \textbf{MCDubber}, to convert the modeling object from a single sentence to a longer sequence with context information to ensure the consistency of the global context prosody. MCDubber comprises three main components: (1) A context duration aligner aims to learn the context-aware alignment between the text and lip frames; (2) A context prosody predictor seeks to read the global context visual sequence and predict the context-aware global energy and pitch; (3) A context acoustic decoder ultimately predicts the global context mel-spectrogram with the assistance of adjacent ground-truth mel-spectrograms of the target sentence. Through this process, MCDubber fully considers the influence of multimodal context on the prosody expressiveness of the current sentence when dubbing. The extracted mel-spectrogram belonging to the target sentence from the output context mel-spectrograms is the final required dubbing audio. Extensive experiments on the Chem benchmark dataset demonstrate that our MCDubber significantly improves dubbing expressiveness compared to all advanced baselines. The code and demos are available at https://github.com/XiaoYuanJun-zy/MCDubber.

cs.MM↗

arXiv2024

Benchmarking Time Series Databases with IoTDB-Benchmark for IoT Scenarios

With the wide application of time series databases (TSDBs) in big data fields like cluster monitoring and industrial IoT, there have been developed a number of TSDBs for time series data management. Different TSDBs have test reports comparing themselves with other databases to show their advantages, but the comparisons are typically based on their own tools without using a common well-recognized test framework. To the best of our knowledge, there is no mature TSDB benchmark either. With the goal of establishing a standard of evaluating TSDB systems, we present the IoTDB-Benchmark framework, specifically designed for TSDB and IoT application scenarios. We pay close attention to some special data ingestion scenarios and summarize 10 basic queries types. We use this benchmark to compare four TSDB systems: InfluxDB, OpenTSDB, KairosDB and TimescaleDB. Our benchmark framework/tool not only measures performance metrics but also takes system resource consumption into consideration.

cs.DB↗

arXiv2024

Fast Downflows Observed during a Polar Crown Filament Eruption

Solar filaments can undergo eruptions and result in the formation of coronal mass ejections (CMEs), which could significantly impact planetary space environments. Observations of eruptions involving polar crown filaments, situated in the polar regions of the Sun, are limited. In this study, we report a polar crown filament eruption (SOL2023-06-12), characterized by fast downflows below the filament. The downflows appear instantly after the onset of the filament eruption and persist for approximately 2 hours, exhibiting plane-of-sky (POS) velocities ranging between 92 and 144 km s$^{-1}$. They originate from the leading edge of the filament and no clear acceleration is observed. Intriguingly, these downflows appear at two distinct sites, symmetrically positioned at the opposite ends of the conjugate flare ribbons. Based on the observations, we propose that the filament might be supported by a magnetic flux rope (MFR), and these downflows possibly occur along the legs of the MFR. The downflows likely result from continuous reconnections between the MFR and the overlying magnetic field structures, and could either be reconnection outflows or redirected filament materials. We also observed horizontal drifting of the locations of downflows, which might correspond to the MFR's footpoint drifting. This type of downflows can potentially be utilized to track the footpoints of MFRs during eruptions.

astro-ph.SR↗

arXiv2024

Can Deception Detection Go Deeper? Dataset, Evaluation, and Benchmark for Deception Reasoning

Deception detection has attracted increasing attention due to its importance in real-world scenarios. Its main goal is to detect deceptive behaviors from multimodal clues such as gestures, facial expressions, prosody, etc. However, these bases are usually subjective and related to personal habits. Therefore, we extend deception detection to deception reasoning, further providing objective evidence to support subjective judgment. Specifically, we provide potential lies and basic facts and then analyze why this sentence may be a lie by combining factual inconsistencies and intent behind them. Compared with deception detection, this task is more applicable to real-world scenarios. For example, in interrogation, the police should judge whether a person is lying based on solid evidence. This paper presents our initial attempts at this task, including constructing a dataset and defining evaluation metrics. Meanwhile, this task can serve as a benchmark for evaluating the complex reasoning capability of large language models. Our code and data are provided in the supplementary material.

cs.CL↗

arXiv2024

Generative Expressive Conversational Speech Synthesis

Conversational Speech Synthesis (CSS) aims to express a target utterance with the proper speaking style in a user-agent conversation setting. Existing CSS methods employ effective multi-modal context modeling techniques to achieve empathy understanding and expression. However, they often need to design complex network architectures and meticulously optimize the modules within them. In addition, due to the limitations of small-scale datasets containing scripted recording styles, they often fail to simulate real natural conversational styles. To address the above issues, we propose a novel generative expressive CSS system, termed GPT-Talker.We transform the multimodal information of the multi-turn dialogue history into discrete token sequences and seamlessly integrate them to form a comprehensive user-agent dialogue context. Leveraging the power of GPT, we predict the token sequence, that includes both semantic and style knowledge, of response for the agent. After that, the expressive conversational speech is synthesized by the conversation-enriched VITS to deliver feedback to the user.Furthermore, we propose a large-scale Natural CSS Dataset called NCSSD, that includes both naturally recorded conversational speech in improvised styles and dialogues extracted from TV shows. It encompasses both Chinese and English languages, with a total duration of 236 hours.We conducted comprehensive experiments on the reliability of the NCSSD and the effectiveness of our GPT-Talker. Both subjective and objective evaluations demonstrate that our model outperforms other state-of-the-art CSS systems significantly in terms of naturalness and expressiveness. The Code, Dataset, and Pre-trained Model are available at: https://github.com/AI-S2-Lab/GPT-Talker.

cs.CL↗

arXiv2024

ICAGC 2024: Inspirational and Convincing Audio Generation Challenge 2024

The Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC 2024) is part of the ISCSLP 2024 Competitions and Challenges track. While current text-to-speech (TTS) technology can generate high-quality audio, its ability to convey complex emotions and controlled detail content remains limited. This constraint leads to a discrepancy between the generated audio and human subjective perception in practical applications like companion robots for children and marketing bots. The core issue lies in the inconsistency between high-quality audio generation and the ultimate human subjective experience. Therefore, this challenge aims to enhance the persuasiveness and acceptability of synthesized audio, focusing on human alignment convincing and inspirational audio generation. A total of 19 teams have registered for the challenge, and the results of the competition and the competition are described in this paper.

eess.AS↗

arXiv2024

Navigation Instruction Generation with BEV Perception and Large Language Models

Navigation instruction generation, which requires embodied agents to describe the navigation routes, has been of great interest in robotics and human-computer interaction. Existing studies directly map the sequence of 2D perspective observations to route descriptions. Though straightforward, they overlook the geometric information and object semantics of the 3D environment. To address these challenges, we propose BEVInstructor, which incorporates Bird's Eye View (BEV) features into Multi-Modal Large Language Models (MLLMs) for instruction generation. Specifically, BEVInstructor constructs a PerspectiveBEVVisual Encoder for the comprehension of 3D environments through fusing BEV and perspective features. To leverage the powerful language capabilities of MLLMs, the fused representations are used as visual prompts for MLLMs, and perspective-BEV prompt tuning is proposed for parameter-efficient updating. Based on the perspective-BEV prompts, BEVInstructor further adopts an instance-guided iterative refinement pipeline, which improves the instructions in a progressive manner. BEVInstructor achieves impressive performance across diverse datasets (i.e., R2R, REVERIE, and UrbanWalk).

cs.CV↗

arXiv2024

Nonparametric Statistics on Magnetic Properties at the Footpoints of Erupting Magnetic Flux Ropes

It is under debate whether the magnetic field in the solar atmosphere carries neutralized electric currents; particularly, whether a magnetic flux rope (MFR), which is considered the core structure of coronal mass ejections, carries neutralized electric currents. Recently Wang et al. (2023, ApJ, 943, 80) studied magnetic flux and electric current measured at the footpoints of 28 eruptive MFRs from 2010 to 2015. Because of the small sample size, no rigorous statistics has been done. Here, we include 9 more events from 2016 to 2023 and perform a series of nonparametric statistical tests at a significance level of 5\%. The tests confirm that there exist no significant differences in magnetic properties between conjugated footpoints of the same MFR, which justifies the method of identifying the MFR footpoints through coronal dimming. The tests demonstrate that there exist no significant differences between MFRs with pre-eruption dimming and those with only post-eruption dimming. However, there is a medium level of association between MFRs carrying substantial net current and those produce pre-eruption dimming, which can be understood by the Lorentz-self force of the current channel. The tests also suggest that in estimating the magnetic twist of MFRs, it is necessary to take into account the spatially inhomogeneous distribution of electric current density and magnetic field.

astro-ph.SR↗

arXiv2024

MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition

Multimodal emotion recognition is an important research topic in artificial intelligence. Over the past few decades, researchers have made remarkable progress by increasing the dataset size and building more effective algorithms. However, due to problems such as complex environments and inaccurate annotations, current systems are hard to meet the demands of practical applications. Therefore, we organize the MER series of competitions to promote the development of this field. Last year, we launched MER2023, focusing on three interesting topics: multi-label learning, noise robustness, and semi-supervised learning. In this year's MER2024, besides expanding the dataset size, we further introduce a new track around open-vocabulary emotion recognition. The main purpose of this track is that existing datasets usually fix the label space and use majority voting to enhance the annotator consistency. However, this process may lead to inaccurate annotations, such as ignoring non-majority or non-candidate labels. In this track, we encourage participants to generate any number of labels in any category, aiming to describe emotional states as accurately as possible. Our baseline code relies on MERTools and is available at: https://github.com/zeroQiaoba/MERTools/tree/master/MER2024.

cs.LG↗

arXiv2024

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLMs by inputting continuous speech representations together with contextual information into the LLM. Through stage-wise large-scale training and the elicitation of context-aware capabilities in LLM, Seed-ASR demonstrates significant improvement over end-to-end models on comprehensive evaluation sets, including multiple domains, accents/dialects and languages. Additionally, Seed-ASR can be further deployed to support specific needs in various scenarios without requiring extra language models. Compared to recently released large ASR models, Seed-ASR achieves 10%-40% reduction in word (or character, for Chinese) error rates on Chinese and English public test sets, further demonstrating its powerful performance.

eess.AS↗

arXiv2024

Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clients

The training of large models, involving fine-tuning, faces the scarcity of high-quality data. Compared to the solutions based on centralized data centers, updating large models in the Internet of Things (IoT) faces challenges in coordinating knowledge from distributed clients by using their private and heterogeneous data. To tackle such a challenge, we propose KOALA (Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clients) to impel the training of large models in IoT. Since the resources obtained by IoT clients are limited and restricted, it is infeasible to locally execute large models and also update them in a privacy-preserving manner. Therefore, we leverage federated learning and knowledge distillation to update large models through collaboration with their small models, which can run locally at IoT clients to process their private data separately and enable large-small model knowledge transfer through iterative learning between the server and clients. Moreover, to support clients with similar or different computing capacities, KOALA is designed with two kinds of large-small model joint learning modes, namely to be homogeneous or heterogeneous. Experimental results demonstrate that compared to the conventional approach, our method can not only achieve similar training performance but also significantly reduce the need for local storage and computing power resources.

cs.LG↗

arXiv2024

Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset

Emotion and Intent Joint Understanding in Multimodal Conversation (MC-EIU) aims to decode the semantic information manifested in a multimodal conversational history, while inferring the emotions and intents simultaneously for the current utterance. MC-EIU is enabling technology for many human-computer interfaces. However, there is a lack of available datasets in terms of annotation, modality, language diversity, and accessibility. In this work, we propose an MC-EIU dataset, which features 7 emotion categories, 9 intent categories, 3 modalities, i.e., textual, acoustic, and visual content, and two languages, i.e., English and Mandarin. Furthermore, it is completely open-source for free access. To our knowledge, MC-EIU is the first comprehensive and rich emotion and intent joint understanding dataset for multimodal conversation. Together with the release of the dataset, we also develop an Emotion and Intent Interaction (EI$^2$) network as a reference system by modeling the deep correlation between emotion and intent in the multimodal conversation. With comparative experiments and ablation studies, we demonstrate the effectiveness of the proposed EI$^2$ method on the MC-EIU dataset. The dataset and codes will be made available at: https://github.com/MC-EIU/MC-EIU.

cs.CL↗

arXiv2024

Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge

Speech Self-Supervised Learning (SSL) has demonstrated considerable efficacy in various downstream tasks. Nevertheless, prevailing self-supervised models often overlook the incorporation of emotion-related prior information, thereby neglecting the potential enhancement of emotion task comprehension through emotion prior knowledge in speech. In this paper, we propose an emotion-aware speech representation learning with intensity knowledge. Specifically, we extract frame-level emotion intensities using an established speech-emotion understanding model. Subsequently, we propose a novel emotional masking strategy (EMS) to incorporate emotion intensities into the masking process. We selected two representative models based on Transformer and CNN, namely MockingJay and Non-autoregressive Predictive Coding (NPC), and conducted experiments on IEMOCAP dataset. Experiments have demonstrated that the representations derived from our proposed method outperform the original model in SER task.

eess.AS↗

arXiv2024

High-resolution Observation of Blowout Jets Regulated by Sunspot Rotation

Coronal jets are believed to be the miniature version of large-scale solar eruptions. In particular, the eruption of a mini-filament inside the base arch is suggested to be the trigger and even driver of blowout jets. Here we propose an alternative triggering mechanism, based on high-resolution H-alpha observations of a blowout jet associated with a mini-filament and an M1.2-class flare. The mini-filament remains largely stationary during the blowout jet, except that it is straddled by flare loops connecting two flare ribbons, indicating that the magnetic arcade embedding the mini-filament has been torn into two parts, with the upper part escaping with the blowout jet. In the wake of the flare, the southern end of the mini-filament fans out like neighboring fibrils, indicative of mass and field exchanges between the mini-filament and the fibrils. The blowout jet is preceded by a standard jet. With H-alpha fibrils moving toward the single-strand spire in a sweeping fashion, the standard jet transitions to the blowout jet. The similar pattern of standard-to-blowout jet transition occurs in an earlier C-class flare before the mini-filament forms. The spiraling morphology and sweeping direction of these fibrils are suggestive of their footpoints being dragged by the leading sunspot that undergoes clockwise rotation for over two days. Soon after the sunspot rotation reaches a peak angular speed as fast as 10 deg/hr, the dormant active region becomes flare-productive, and the mini-filament forms through the interaction of moving magnetic features from the rotating sunspot with satellite spots/pores. Hence, we suggest that the sunspot rotation plays a key role in building up free energy for flares and jets and in triggering blowout jets by inducing sweeping motions of fibrils.

astro-ph.SR↗

arXiv2024

Unsupervised Learning of Part Similarity for Goal-Guided Accelerated Experiment Design in Metal Additive Manufacturing

Metal additive manufacturing is gaining broad interest and increased use in the industrial and academic fields. However, the quantification and commercialization of standard parts usually require extensive experiments and expensive post-characterization, which impedes the rapid development and adaptation of metal AM technologies. In this work, a similarity-based acceleration (S-acceleration) method for design of experiments is developed to reduce the time and costs associated with unveiling process-property (porosity defects) relationships during manufacturing. With S-acceleration, part semantic features from machine-setting parameters and physics-effects informed characteristics are explored for measuring mutual part similarities. A user-defined simplification rate of experiments is proposed to purposely remove redundant parts before conducting experiments printing without sacrificing information gain as original full factorial experiment design. This S-acceleration design of experiments is demonstrated on a Concept Laser M2 machine for the experimental plan of modeling relationships between process parameters and part porosity defects. The printed part has 2 mm diameter by 4 mm tall pin geometry considering variations in build location and orientation, laser settings and powder feedstock are held constant. In total, 242 parts are measured to create a ground truth data set of porosity levels by using X-ray tomography microscopy. The S-acceleration method is assessed for performance considering 40%, 50%, and 60% of user-defined experiment simplification rates. The repeated experiments are removed without ignoring the minority experiments outlier, assuring a similar process-property relation in the original experiment plan. The experiment number is significantly reduced based on part similarity with minimal compromise of model accuracy and obtained knowledge.

physics.data-an↗