arXiv subjects

Long Chen

Publications and source records attributed to Long Chen.

At least 397 records · Page 22Linked to original sources

arXiv2024

SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos

We study the problem of procedure planning in instructional videos, which aims to make a goal-oriented sequence of action steps given partial visual state observations. The motivation of this problem is to learn a structured and plannable state and action space. Recent works succeeded in sequence modeling of steps with only sequence-level annotations accessible during training, which overlooked the roles of states in the procedures. In this work, we point out that State CHangEs MAtter (SCHEMA) for procedure planning in instructional videos. We aim to establish a more structured state space by investigating the causal relations between steps and states in procedures. Specifically, we explicitly represent each step as state changes and track the state changes in procedures. For step representation, we leveraged the commonsense knowledge in large language models (LLMs) to describe the state changes of steps via our designed chain-of-thought prompting. For state change tracking, we align visual state observations with language state descriptions via cross-modal contrastive learning, and explicitly model the intermediate states of the procedure using LLM-generated state descriptions. Experiments on CrossTask, COIN, and NIV benchmark datasets demonstrate that our proposed SCHEMA model achieves state-of-the-art performance and obtains explainable visualizations.

cs.CV↗

arXiv2024

BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments

The rapid developments of mobile robotics and autonomous navigation over the years are largely empowered by public datasets for testing and upgrading, such as sensor odometry and SLAM tasks. Impressive demos and benchmark scores have arisen, which may suggest the maturity of existing navigation techniques. However, these results are primarily based on moderate structured scenario testing. When transitioning to challenging unstructured environments, especially in GNSS-denied, texture-monotonous, and dense-vegetated natural fields, their performance can hardly sustain at a high level and requires further validation and improvement. To bridge this gap, we build a novel robot navigation dataset in a luxuriant botanic garden of more than 48000m2. Comprehensive sensors are used, including Gray and RGB stereo cameras, spinning and MEMS 3D LiDARs, and low-cost and industrial-grade IMUs, all of which are well calibrated and hardware-synchronized. An all-terrain wheeled robot is employed for data collection, traversing through thick woods, riversides, narrow trails, bridges, and grasslands, which are scarce in previous resources. This yields 33 short and long sequences, forming 17.1km trajectories in total. Excitedly, both highly-accurate ego-motions and 3D map ground truth are provided, along with fine-annotated vision semantics. We firmly believe that our dataset can advance robot navigation and sensor fusion research to a higher level.

cs.RO↗

arXiv2024

Edge-averaged virtual element methods for convection-diffusion and convection-dominated problems

This manuscript develops edge-averaged virtual element (EAVE) methodologies to address convection-diffusion problems effectively in the convection-dominated regime. It introduces a variant of EAVE that ensures monotonicity (producing an $M$-matrix) on Voronoi polygonal meshes, provided their duals are Delaunay triangulations with acute angles. Furthermore, the study outlines a comprehensive framework for EAVE methodologies, introducing another variant that integrates with the stiffness matrix derived from the lowest-order virtual element method for the Poisson equation. Numerical experiments confirm the theoretical advantages of the monotonicity property and demonstrate an optimal convergence rate across various mesh configurations.

math.NA↗

arXiv2024

Anisotropic magnetism and band evolution induced by ferromagnetic phase transition in titanium-based kagome ferromagnet SmTi3Bi4

Kagome magnets with diverse topological quantum responses are crucial for next-generation topological engineering. The anisotropic magnetism and band evolution induced by ferromagnetic phase transition (FMPT) is reported in a newly discovered titanium-based kagome ferromagnet S mTi3 Bi4, which features a distorted Ti kagome lattice and S m atomic zig-zag chains. Temperature-dependent resistivity, heat capacity, and magnetic susceptibility reveal a ferromagnetic ordering temperature Tc of 23.2 K. A large magnetic anisotropy, observed by applying the magnetic field along three crystallographic axes, identifies the b axis as the easy axis. Angle-resolved photoemission spectroscopy with first-principles calculations unveils the characteristic kagome motif, including the Dirac point at the Fermi level and multiple van Hove singularities. Notably, a band splitting and gap closing attributed to FMPT is observed, originating from the exchange coupling between S m 4 f local moments and itinerant electrons of the kagome Ti atoms, as well as the time-reversal symmetry breaking induced by the long-range ferromagnetic order. Considering the large in-plane magnetization and the evolution of electronic structure under the influence of ferromagnetic ordering, such materials promise to be a new platform for exploring the intricate electronic properties and magnetic phases based on the kagome lattice.

cond-mat.mtrl-sci↗

arXiv2024

Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning

Being widely used in learning unbiased visual question answering (VQA) models, Data Augmentation (DA) helps mitigate language biases by generating extra training samples beyond the original samples. While today's DA methods can generate robust samples, the augmented training set, significantly larger than the original dataset, often exhibits redundancy in terms of difficulty or content repetition, leading to inefficient model training and even compromising the model performance. To this end, we design an Effective Curriculum Learning strategy ECL to enhance DA-based VQA methods. Intuitively, ECL trains VQA models on relatively ``easy'' samples first, and then gradually changes to ``harder'' samples, and less-valuable samples are dynamically removed. Compared to training on the entire augmented dataset, our ECL strategy can further enhance VQA models' performance with fewer training samples. Extensive ablations have demonstrated the effectiveness of ECL on various methods.

cs.CV↗

arXiv2024

Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion

We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM). Experiments on the Switchboard human-human conversation dataset demonstrate that our approach consistently outperforms the baseline models with single modality. We also develop a novel multi-task instruction fine-tuning strategy to further benefit from LLM-encoded knowledge for understanding the tasks and conversational contexts, leading to additional improvements. Our approach demonstrates the potential of combined LLMs and acoustic models for a more natural and conversational interaction between humans and speech-enabled AI agents.

cs.CL↗

arXiv2024

Two-pass Endpoint Detection for Speech Recognition

Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being cut-off early. We propose a novel two-pass solution for endpointing, where the utterance endpoint detected from a first pass endpointer is verified by a 2nd-pass model termed EP Arbitrator. Our method improves the trade-off between early cut-offs and latency over a baseline endpointer, as tested on datasets including voice-assistant transactional queries, conversational speech, and the public SLURP corpus. We demonstrate that our method shows improvements regardless of the first-pass EP model used.

eess.AS↗

arXiv2024

Multiperson Detection and Vital-Sign Sensing Empowered by Space-Time-Coding RISs

Passive human sensing using wireless signals has attracted increasing attention due to its superiorities of non-contact and robustness in various lighting conditions. However, when multiple human individuals are present, their reflected signals could be intertwined in the time, frequency and spatial domains, making it challenging to separate them. To address this issue, this paper proposes a novel system for multiperson detection and monitoring of vital signs (i.e., respiration and heartbeat) with the assistance of space-time-coding (STC) reconfigurable intelligent metasurfaces (RISs). Specifically, the proposed system scans the area of interest (AoI) for human detection by using the harmonic beams generated by the STC RIS. Simultaneously, frequencyorthogonal beams are assigned to each detected person for accurate estimation of their respiration rate (RR) and heartbeat rate (HR). Furthermore, to efficiently extract the respiration signal and the much weaker heartbeat signal, we propose an improved variational mode decomposition (VMD) algorithm to accurately decompose the complex reflected signals into a smaller number of intrinsic mode functions (IMFs). We build a prototype to validate the proposed multiperson detection and vital-sign monitoring system. Experimental results demonstrate that the proposed system can simultaneously monitor the vital signs of up to four persons. The errors of RR and HR estimation using the improved VMD algorithm are below 1 RPM (respiration per minute) and 5 BPM (beats per minute), respectively. Further analysis reveals that the flexible beam controlling mechanism empowered by the STC RIS can reduce the noise reflected from other irrelative objects on the physical layer, and improve the signal-to-noise ratio of echoes from the human chest.

eess.SP↗

arXiv2023

SoundCount: Sound Counting from Raw Audio with Dyadic Decomposition Neural Network

In this paper, we study an underexplored, yet important and challenging problem: counting the number of distinct sounds in raw audio characterized by a high degree of polyphonicity. We do so by systematically proposing a novel end-to-end trainable neural network (which we call DyDecNet, consisting of a dyadic decomposition front-end and backbone network), and quantifying the difficulty level of counting depending on sound polyphonicity. The dyadic decomposition front-end progressively decomposes the raw waveform dyadically along the frequency axis to obtain time-frequency representation in multi-stage, coarse-to-fine manner. Each intermediate waveform convolved by a parent filter is further processed by a pair of child filters that evenly split the parent filter's carried frequency response, with the higher-half child filter encoding the detail and lower-half child filter encoding the approximation. We further introduce an energy gain normalization to normalize sound loudness variance and spectrum overlap, and apply it to each intermediate parent waveform before feeding it to the two child filters. To better quantify sound counting difficulty level, we further design three polyphony-aware metrics: polyphony ratio, max polyphony and mean polyphony. We test DyDecNet on various datasets to show its superiority, and we further show dyadic decomposition network can be used as a general front-end to tackle other acoustic tasks.

cs.SD↗

arXiv2023

Beyond Grounding: Extracting Fine-Grained Event Hierarchies Across Modalities

Events describe happenings in our world that are of importance. Naturally, understanding events mentioned in multimedia content and how they are related forms an important way of comprehending our world. Existing literature can infer if events across textual and visual (video) domains are identical (via grounding) and thus, on the same semantic level. However, grounding fails to capture the intricate cross-event relations that exist due to the same events being referred to on many semantic levels. For example, in Figure 1, the abstract event of "war" manifests at a lower semantic level through subevents "tanks firing" (in video) and airplane "shot" (in text), leading to a hierarchical, multimodal relationship between the events. In this paper, we propose the task of extracting event hierarchies from multimodal (video and text) data to capture how the same event manifests itself in different modalities at different semantic levels. This reveals the structure of events and is critical to understanding them. To support research on this task, we introduce the Multimodal Hierarchical Events (MultiHiEve) dataset. Unlike prior video-language datasets, MultiHiEve is composed of news video-article pairs, which makes it rich in event hierarchies. We densely annotate a part of the dataset to construct the test benchmark. We show the limitations of state-of-the-art unimodal and multimodal baselines on this task. Further, we address these limitations via a new weakly supervised model, leveraging only unannotated video-article pairs from MultiHiEve. We perform a thorough evaluation of our proposed method which demonstrates improved performance on this task and highlight opportunities for future research.

cs.CV↗

arXiv2023

Transformed Primal-Dual Methods with Variable-Preconditioners

This paper introduces a novel Transformed Primal-Dual with variable-metric/preconditioner (TPDv) algorithm, designed to efficiently solve affine constrained optimization problems common in nonlinear partial differential equations (PDEs). Diverging from traditional methods, TPDv iteratively updates time-evolving preconditioning operators, enhancing adaptability. The algorithm is derived and analyzed, demonstrating global linear convergence rates under mild assumptions. Numerical experiments on challenging nonlinear PDEs, including the Darcy-Forchheimer model and a nonlinear electromagnetic problem, showcase the algorithm's superiority over existing methods in terms of iteration numbers and computational efficiency. The paper concludes with a comprehensive convergence analysis.

math.NA↗

arXiv2023

FusionPlanner: A Multi-task Motion Planner for Mining Trucks via Multi-sensor Fusion

In recent years, significant achievements have been made in motion planning for intelligent vehicles. However, as a typical unstructured environment, open-pit mining attracts limited attention due to its complex operational conditions and adverse environmental factors. A comprehensive paradigm for unmanned transportation in open-pit mines is proposed in this research. Firstly, we propose a multi-task motion planning algorithm, called FusionPlanner, for autonomous mining trucks by the multi-sensor fusion method to adapt both lateral and longitudinal control tasks for unmanned transportation. Then, we develop a novel benchmark called MiningNav, which offers three validation approaches to evaluate the trustworthiness and robustness of well-trained algorithms in transportation roads of open-pit mines. Finally, we introduce the Parallel Mining Simulator (PMS), a new high-fidelity simulator specifically designed for open-pit mining scenarios. PMS enables the users to manage and control open-pit mine transportation from both the single-truck control and multi-truck scheduling perspectives. The performance of FusionPlanner is tested by MiningNav in PMS, and the empirical results demonstrate a significant reduction in the number of collisions and takeovers of our planner. We anticipate our unmanned transportation paradigm will bring mining trucks one step closer to trustworthiness and robustness in continuous round-the-clock unmanned transportation.

cs.RO↗

arXiv2023

Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models

The age of social media is rife with memes. Understanding and detecting harmful memes pose a significant challenge due to their implicit meaning that is not explicitly conveyed through the surface text and image. However, existing harmful meme detection approaches only recognize superficial harm-indicative signals in an end-to-end classification manner but ignore in-depth cognition of the meme text and image. In this paper, we attempt to detect harmful memes based on advanced reasoning over the interplay of multimodal information in memes. Inspired by the success of Large Language Models (LLMs) on complex reasoning, we first conduct abductive reasoning with LLMs. Then we propose a novel generative framework to learn reasonable thoughts from LLMs for better multimodal fusion and lightweight fine-tuning, which consists of two training stages: 1) Distill multimodal reasoning knowledge from LLMs; and 2) Fine-tune the generative framework to infer harmfulness. Extensive experiments conducted on three meme datasets demonstrate that our proposed approach achieves superior performance than state-of-the-art methods on the harmful meme detection task.

cs.CL↗

arXiv2023

CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

While features of different scales are perceptually important to visual inputs, existing vision transformers do not yet take advantage of them explicitly. To this end, we first propose a cross-scale vision transformer, CrossFormer. It introduces a cross-scale embedding layer (CEL) and a long-short distance attention (LSDA). On the one hand, CEL blends each token with multiple patches of different scales, providing the self-attention module itself with cross-scale features. On the other hand, LSDA splits the self-attention module into a short-distance one and a long-distance counterpart, which not only reduces the computational burden but also keeps both small-scale and large-scale features in the tokens. Moreover, through experiments on CrossFormer, we observe another two issues that affect vision transformers' performance, i.e., the enlarging self-attention maps and amplitude explosion. Thus, we further propose a progressive group size (PGS) paradigm and an amplitude cooling layer (ACL) to alleviate the two issues, respectively. The CrossFormer incorporating with PGS and ACL is called CrossFormer++. Extensive experiments show that CrossFormer++ outperforms the other vision transformers on image classification, object detection, instance segmentation, and semantic segmentation tasks. The code will be available at: https://github.com/cheerss/CrossFormer.

cs.CV↗

arXiv2023

Automatic Detection of Alzheimer's Disease with Multi-Modal Fusion of Clinical MRI Scans

The aging population of the U.S. drives the prevalence of Alzheimer's disease. Brookmeyer et al. forecasts approximately 15 million Americans will have either clinical AD or mild cognitive impairment by 2060. In response to this urgent call, methods for early detection of Alzheimer's disease have been developed for prevention and pre-treatment. Notably, literature on the application of deep learning in the automatic detection of the disease has been proliferating. This study builds upon previous literature and maintains a focus on leveraging multi-modal information to enhance automatic detection. We aim to predict the stage of the disease - Cognitively Normal (CN), Mildly Cognitive Impairment (MCI), and Alzheimer's Disease (AD), based on two different types of brain MRI scans. We design an AlexNet-based deep learning model that learns the synergy of complementary information from both T1 and FLAIR MRI scans.

eess.IV↗

arXiv2023

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual relation detection (VRD) is a typical task that identifies relationship (or interaction) types between object pairs within an image. However, naively utilizing CLIP with prevalent class-based prompts for zero-shot VRD has several weaknesses, e.g., it struggles to distinguish between different fine-grained relation types and it neglects essential spatial information of two objects. To this end, we propose a novel method for zero-shot VRD: RECODE, which solves RElation detection via COmposite DEscription prompts. Specifically, RECODE first decomposes each predicate category into subject, object, and spatial components. Then, it leverages large language models (LLMs) to generate description-based prompts (or visual cues) for each component. Different visual cues enhance the discriminability of similar relation categories from different perspectives, which significantly boosts performance in VRD. To dynamically fuse different cues, we further introduce a chain-of-thought method that prompts LLMs to generate reasonable weights for different visual cues. Extensive experiments on four VRD benchmarks have demonstrated the effectiveness and interpretability of RECODE.

cs.CV↗

arXiv2023

The First LHAASO Catalog of Gamma-Ray Sources

We present the first catalog of very-high energy and ultra-high energy gamma-ray sources detected by the Large High Altitude Air Shower Observatory (LHAASO). The catalog was compiled using 508 days of data collected by the Water Cherenkov Detector Array (WCDA) from March 2021 to September 2022 and 933 days of data recorded by the Kilometer Squared Array (KM2A) from January 2020 to September 2022. This catalog represents the main result from the most sensitive large coverage gamma-ray survey of the sky above 1 TeV, covering declination from $-$20$^{\circ}$ to 80$^{\circ}$. In total, the catalog contains 90 sources with an extended size smaller than $2^\circ$ and a significance of detection at $> 5σ$. Based on our source association criteria, 32 new TeV sources are proposed in this study. Among the 90 sources, 43 sources are detected with ultra-high energy ($E > 100$ TeV) emission at $> 4σ$ significance level. We provide the position, extension, and spectral characteristics of all the sources in this catalog.

astro-ph.HE↗

arXiv2023

Very high energy gamma-ray emission beyond 10 TeV from GRB 221009A

The highest energy gamma-rays from gamma-ray bursts (GRBs) have important implications for their radiation mechanism. Here we report for the first time the detection of gamma-rays up to 13 TeV from the brightest GRB 221009A by the Large High Altitude Air-shower Observatory (LHAASO). The LHAASO-KM2A detector registered more than 140 gamma-rays with energies above 3 TeV during 230$-$900s after the trigger. The intrinsic energy spectrum of gamma-rays can be described by a power-law after correcting for extragalactic background light (EBL) absorption. Such a hard spectrum challenges the synchrotron self-Compton (SSC) scenario of relativistic electrons for the afterglow emission above several TeV. Observations of gamma-rays up to 13 TeV from a source with a measured redshift of z=0.151 hints more transparency in intergalactic space than previously expected. Alternatively, one may invoke new physics such as Lorentz Invariance Violation (LIV) or an axion origin of very high energy (VHE) signals.

astro-ph.HE↗