arXiv subjects

Chao Li

Publications and source records attributed to Chao Li.

At least 325 records · Page 18Linked to original sources

arXiv2023

Asca: less audio data is more insightful

Audio recognition in specialized areas such as birdsong and submarine acoustics faces challenges in large-scale pre-training due to the limitations in available samples imposed by sampling environments and specificity requirements. While the Transformer model excels in audio recognition, its dependence on vast amounts of data becomes restrictive in resource-limited settings. Addressing this, we introduce the Audio Spectrogram Convolution Attention (ASCA) based on CoAtNet, integrating a Transformer-convolution hybrid architecture, novel network design, and attention techniques, further augmented with data enhancement and regularization strategies. On the BirdCLEF2023 and AudioSet(Balanced), ASCA achieved accuracies of 81.2% and 35.1%, respectively, significantly outperforming competing methods. The unique structure of our model enriches output, enabling generalization across various audio detection tasks. Our code can be found at https://github.com/LeeCiang/ASCA.

cs.SD↗

arXiv2023

Generalized soap bubbles and the topology of manifolds with positive scalar curvature

We prove that for $n\in \{4,5\}$, a closed aspherical $n$-manifold does not admit a Riemannian metric with positive scalar curvature. Additionally, we show that for $n\leq 7$, the connected sum of a $n$-torus with an arbitrary manifold does not admit a complete metric of positive scalar curvature. When combined with forthcoming contributions by Lesourd--Unger--Yau, this proves that the Schoen--Yau Liouville theorem holds for all locally conformally flat manifolds with non-negative scalar curvature. A key tool in these results are generalized soap bubbles -- surfaces that are stationary for prescribed-mean-curvature functionals (also called $μ$-bubbles).

math.DG↗

arXiv2023

Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet

Multi-person pose understanding from RGB videos involves three complex tasks: pose estimation, tracking and motion forecasting. Intuitively, accurate multi-person pose estimation facilitates robust tracking, and robust tracking builds crucial history for correct motion forecasting. Most existing works either focus on a single task or employ multi-stage approaches to solving multiple tasks separately, which tends to make sub-optimal decision at each stage and also fail to exploit correlations among the three tasks. In this paper, we propose Snipper, a unified framework to perform multi-person 3D pose estimation, tracking, and motion forecasting simultaneously in a single stage. We propose an efficient yet powerful deformable attention mechanism to aggregate spatiotemporal information from the video snippet. Building upon this deformable attention, a video transformer is learned to encode the spatiotemporal features from the multi-frame snippet and to decode informative pose features for multi-person pose queries. Finally, these pose queries are regressed to predict multi-person pose trajectories and future motions in a single shot. In the experiments, we show the effectiveness of Snipper on three challenging public datasets where our generic model rivals specialized state-of-art baselines for pose estimation, tracking, and forecasting.

cs.CV↗

arXiv2023

Generative Action Description Prompts for Skeleton-based Action Recognition

Skeleton-based action recognition has recently received considerable attention. Current approaches to skeleton-based action recognition are typically formulated as one-hot classification tasks and do not fully exploit the semantic relations between actions. For example, "make victory sign" and "thumb up" are two actions of hand gestures, whose major difference lies in the movement of hands. This information is agnostic from the categorical one-hot encoding of action classes but could be unveiled from the action description. Therefore, utilizing action description in training could potentially benefit representation learning. In this work, we propose a Generative Action-description Prompts (GAP) approach for skeleton-based action recognition. More specifically, we employ a pre-trained large-scale language model as the knowledge engine to automatically generate text descriptions for body parts movements of actions, and propose a multi-modal training scheme by utilizing the text encoder to generate feature vectors for different body parts and supervise the skeleton encoder for action representation learning. Experiments show that our proposed GAP method achieves noticeable improvements over various baseline models without extra computation cost at inference. GAP achieves new state-of-the-arts on popular skeleton-based action recognition benchmarks, including NTU RGB+D, NTU RGB+D 120 and NW-UCLA. The source code is available at https://github.com/MartinXM/GAP.

cs.CV↗

arXiv2023

Liquid Democracy in DPoS Blockchains

Voting mechanisms play a crucial role in decentralized governance of blockchain systems. Liquid democracy, also known as delegative voting, allows voters to vote directly or delegate their voting power to others, thereby contributing to the resolution of problems such as low voter turnout. In recent years, liquid democracy has been widely adopted by Delegated-Proof-of-Stake (DPoS) blockchains and implemented successfully on platforms with millions of users. However, little is known regarding the characteristics and actual effectiveness of liquid democracy in decentralized governance. This paper explored for the first time the practical implementation of liquid democracy in DPoS blockchain systems. Using actual data collected from two major DPoS blockchains, EOS and Steem, our study compared and evaluated the participation of different types of users of DPoS blockchain systems in liquid democracy, as well as extracting and analyzing the delegation chains and networks formed during the process of liquid democracy within the systems. We believe that the findings of this paper will contribute to further studies on the design and implementation of liquid democracy and other voting mechanisms in decentralized governance.

cs.CR↗

arXiv2023

MMBench: Benchmarking End-to-End Multi-modal DNNs and Understanding Their Hardware-Software Implications

The explosive growth of various types of big data and advances in AI technologies have catalyzed a new type of workloads called multi-modal DNNs. Multi-modal DNNs are capable of interpreting and reasoning about information from multiple modalities, making them more applicable to real-world AI scenarios. In recent research, multi-modal DNNs have outperformed the best uni-modal DNN in a wide range of distributed computing applications from traditional multimedia systems to emerging autonomous edge systems. However, despite their importance and superiority, very limited research attention has been devoted to understand the characteristics of multi-modal DNNs and their implications on current computing software/hardware platforms. Existing benchmarks either target uni-modal DNNs or only focus on the algorithm characteristics of multi-modal DNNs. There lacks representative benchmark suites that provide comprehensive system and architecture level analysis of multi-modal networks. To advance the understanding of these multi-modal DNN workloads and facilitate related research, we present MMBench, an open-source, end-to-end benchmark suite consisting of a set of real-world multi-modal DNN workloads with relevant performance metrics for evaluation. We then use MMBench to conduct an in-depth analysis on the characteristics of multi-modal DNNs. We demonstrate their unique characteristics of clear multi-stage execution, frequent synchronization and high heterogeneity, which distinguish them from conventional uni-modal DNNs. Finally, we conduct a case study and extend our benchmark to edge devices. We hope that our work can provide insights for future software/hardware design and optimization to underpin multi-modal DNNs on both cloud and edge computing platforms.

cs.PF↗

arXiv2023

Quantifying the Impact of Large Language Models on Collective Opinion Dynamics

The process of opinion expression and exchange is a critical component of democratic societies. As people interact with large language models (LLMs) in the opinion shaping process different from traditional media, the impacts of LLMs are increasingly recognized and being concerned. However, the knowledge about how LLMs affect the process of opinion expression and exchange of social opinion networks is very limited. Here, we create an opinion network dynamics model to encode the opinions of LLMs, cognitive acceptability and usage strategies of individuals, and simulate the impact of LLMs on opinion dynamics in a variety of scenarios. The outcomes of the simulations inform about effective demand-oriented opinion network interventions. The results from this study suggested that the output opinion of LLMs has a unique and positive effect on the collective opinion difference. The marginal effect of cognitive acceptability on collective opinion formation is nonlinear and shows a decreasing trend. When people partially rely on LLMs, the exchange process of opinion becomes more intense and the diversity of opinion becomes more favorable. In fact, there is 38.6% more opinion diversity when people all partially rely on LLMs, compared to prohibiting the use of LLMs entirely. The optimal diversity of opinion was found when the fractions of people who do not use, partially rely on, and fully rely on LLMs reached roughly 4:12:1. Our experiments also find that introducing extra agents with opposite/neutral/random opinions, we can effectively mitigate the impact of biased/toxic output from LLMs. Our findings provide valuable insights into opinion dynamics in the age of LLMs, highlighting the need for customized interventions tailored to specific scenarios to address the drawbacks of improper output and use of LLMs.

cs.SI↗

arXiv2023

KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution

Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution. However, existing designs are parameter-inefficient: they increase the number of convolutional parameters by $n$ times. This and the optimization difficulty lead to no research progress in dynamic convolution that can allow us to use a significant large value of $n$ (e.g., $n>100$ instead of typical setting $n<10$) to push forward the performance boundary. In this paper, we propose $KernelWarehouse$, a more general form of dynamic convolution, which can strike a favorable trade-off between parameter efficiency and representation power. Its key idea is to redefine the basic concepts of "$kernels$" and "$assembling$ $kernels$" in dynamic convolution from the perspective of reducing kernel dimension and increasing kernel number significantly. In principle, KernelWarehouse enhances convolutional parameter dependencies within the same layer and across successive layers via tactful kernel partition and warehouse sharing, yielding a high degree of freedom to fit a desired parameter budget. We validate our method on ImageNet and MS-COCO datasets with different ConvNet architectures, and show that it attains state-of-the-art results. For instance, the ResNet18|ResNet50|MobileNetV2|ConvNeXt-Tiny model trained with KernelWarehouse on ImageNet reaches 76.05%|81.05%|75.52%|82.51% top-1 accuracy. Thanks to its flexible design, KernelWarehouse can even reduce the model size of a ConvNet while improving the accuracy, e.g., our ResNet18 model with 36.45%|65.10% parameter reduction to the baseline shows 2.89%|2.29% absolute improvement to top-1 accuracy.

cs.CV↗

arXiv2023

Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words with high prediction scores can significantly degrade the performance of recognizing common words. To address this issue, we propose an adaptive contextual biasing method based on Context-Aware Transformer Transducer (CATT) that utilizes the biased encoder and predictor embeddings to perform streaming prediction of contextual phrase occurrences. Such prediction is then used to dynamically switch the bias list on and off, enabling the model to adapt to both personalized and common scenarios. Experiments on Librispeech and internal voice assistant datasets show that our approach can achieve up to 6.7% and 20.7% relative reduction in WER and CER compared to the baseline respectively, mitigating up to 96.7% and 84.9% of the relative WER and CER increase for common cases. Furthermore, our approach has a minimal performance impact in personalized scenarios while maintaining a streaming inference pipeline with negligible RTF increase.

cs.SD↗

arXiv2023

Analyzing and controlling diversity in quantum-behaved particle swarm optimization

This paper addresses the issues of controlling and analyzing the population diversity in quantum-behaved particle swarm optimization (QPSO), which is an optimization approach motivated by concepts in quantum mechanics and PSO. In order to gain an in-depth understanding of the role the diversity plays in the evolving process, we first define the genotype diversity by the distance to the average point of the particles' positions and the phenotype diversity by the fitness values for the QPSO. Then, the correlations between the two types of diversities and the search performance are tested and analyzed on several benchmark functions, and the distance-to-average-point diversity is showed to have stronger association with the search performance during the evolving processes. Finally, in the light of the performed diversity analyses, two strategies for controlling the distance-to-average-point diversities are proposed for the purpose of improving the search ability of the QPSO algorithm. Empirical studies on the QPSO with the introduced diversity control methods are performed on a set of benchmark functions from the CEC 2005 benchmark suite. The performance of the proposed methods are evaluated and compared with the original QPSO and other PSO variants.

cs.NE↗

arXiv2023

Decomposing 4-manifolds with positive scalar curvature

We show that every closed, oriented, topologically PSC 4-manifold can be obtained via 0 and 1-surgeries from a topologically PSC 4-orbifold with vanishing first Betti number and second Betti number at most as large as the original one.

math.DG↗

arXiv2023

RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World

Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object. However, these approaches generate conspicuous adversarial patterns that show poor stealthiness. Another physical deployable attack is the optical attack, featuring stealthiness while exhibiting weakly in the daytime with sunlight. In this paper, we propose a novel Reflected Light Attack (RFLA), featuring effective and stealthy in both the digital and physical world, which is implemented by placing the color transparent plastic sheet and a paper cut of a specific shape in front of the mirror to create different colored geometries on the target object. To achieve these goals, we devise a general framework based on the circle to model the reflected light on the target object. Specifically, we optimize a circle (composed of a coordinate and radius) to carry various geometrical shapes determined by the optimized angle. The fill color of the geometry shape and its corresponding transparency are also optimized. We extensively evaluate the effectiveness of RFLA on different datasets and models. Experiment results suggest that the proposed method achieves over 99% success rate on different datasets and models in the digital world. Additionally, we verify the effectiveness of the proposed method in different physical environments by using sunlight or a flashlight.

cs.CV↗

arXiv2023

A Novel Driver Distraction Behavior Detection Method Based on Self-supervised Learning with Masked Image Modeling

Driver distraction causes a significant number of traffic accidents every year, resulting in economic losses and casualties. Currently, the level of automation in commercial vehicles is far from completely unmanned, and drivers still play an important role in operating and controlling the vehicle. Therefore, driver distraction behavior detection is crucial for road safety. At present, driver distraction detection primarily relies on traditional convolutional neural networks (CNN) and supervised learning methods. However, there are still challenges such as the high cost of labeled datasets, limited ability to capture high-level semantic information, and weak generalization performance. In order to solve these problems, this paper proposes a new self-supervised learning method based on masked image modeling for driver distraction behavior detection. Firstly, a self-supervised learning framework for masked image modeling (MIM) is introduced to solve the serious human and material consumption issues caused by dataset labeling. Secondly, the Swin Transformer is employed as an encoder. Performance is enhanced by reconfiguring the Swin Transformer block and adjusting the distribution of the number of window multi-head self-attention (W-MSA) and shifted window multi-head self-attention (SW-MSA) detection heads across all stages, which leads to model more lightening. Finally, various data augmentation strategies are used along with the best random masking strategy to strengthen the model's recognition and generalization ability. Test results on a large-scale driver distraction behavior dataset show that the self-supervised learning method proposed in this paper achieves an accuracy of 99.60%, approximating the excellent performance of advanced supervised learning methods. Our code is publicly available at github.com/Rocky1salady-killer/SL-DDBD.

cs.CV↗

arXiv2023

Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networks

Meta-structures are widely used to define which subset of neighbors to aggregate information in heterogeneous information networks (HINs). In this work, we investigate existing meta-structures, including meta-path and meta-graph, and observe that they are initially designed manually with fixed patterns and hence are insufficient to encode various rich semantic information on diverse HINs. Through reflection on their limitation, we define a new concept called meta-multigraph as a more expressive and flexible generalization of meta-graph, and propose a stable differentiable search method to automatically optimize the meta-multigraph for specific HINs and tasks. As the flexibility of meta-multigraphs may propagate redundant messages, we further introduce a complex-to-concise (C2C) meta-multigraph that propagates messages from complex to concise along the depth of meta-multigraph. Moreover, we observe that the differentiable search typically suffers from unstable search and a significant gap between the meta-structures in search and evaluation. To this end, we propose a progressive search algorithm by implicitly narrowing the search space to improve search stability and reduce inconsistency. Extensive experiments are conducted on six medium-scale benchmark datasets and one large-scale benchmark dataset over two representative tasks, i.e., node classification and recommendation. Empirical results demonstrate that our search methods can automatically find expressive meta-multigraphs and C2C meta-multigraphs, enabling our model to outperform state-of-the-art heterogeneous graph neural networks.

cs.AI↗

arXiv2023

DFlow: Efficient Dataflow-based Invocation Workflow Execution for Function-as-a-Service

The Serverless Computing is becoming increasingly popular due to its ease of use and fine-grained billing. These features make it appealing for stateful application or serverless workflow. However, current serverless workflow systems utilize a controlflow-based invocation pattern to invoke functions. In this execution pattern, the function invocation depends on the state of the function. A function can only begin executing once all its precursor functions have completed. As a result, this pattern may potentially lead to longer end-to-end execution time. We design and implement the DFlow, a novel dataflow-based serverless workflow system that achieves high performance for serverless workflow. DFlow introduces a distributed scheduler (DScheduler) by using the dataflow-based invocation pattern to invoke functions. In this pattern, the function invocation depends on the data dependency between functions. The function can start to execute even its precursor functions are still running. DFlow further features a distributed store (DStore) that utilizes effective fine-grained optimization techniques to eliminate function interaction, thereby enabling efficient data exchange. With the support of DScheduler and DStore, DFlow can achieving an average improvement of 60% over CFlow, 40% over FaaSFlow, 25% over FaasFlowRedis, and 40% over KNIX on 99%-ile latency respectively. Further, it can improve network bandwidth utilization by 2x-4x over CFlow and 1.5x-3x over FaaSFlow, FaaSFlowRedis and KNIX, respectively. DFlow effectively reduces the cold startup latency, achieving an average improvement of 5.6x over CFlow and 1.1x over FaaSFlow

cs.DC↗

arXiv2023

Extensions of extremal Kähler submanifolds of complex projective spaces

In this paper we showed that every connected extremal Kähler submanifold of a complex projetive space has a natural extension which is a complete Kähler manifold and admits a holomorphic isometric immersion into the same ambient space. We also give an application to study extremal Kähler hypersurfaces of complex projective spaces.

math.DG↗

arXiv2023

Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma

Most recently, the pathology diagnosis of cancer is shifting to integrating molecular makers with histology features. It is a urgent need for digital pathology methods to effectively integrate molecular markers with histology, which could lead to more accurate diagnosis in the real world scenarios. This paper presents a first attempt to jointly predict molecular markers and histology features and model their interactions for classifying diffuse glioma bases on whole slide images. Specifically, we propose a hierarchical multi-task multi-instance learning framework to jointly predict histology and molecular markers. Moreover, we propose a co-occurrence probability-based label correction graph network to model the co-occurrence of molecular markers. Lastly, we design an inter-omic interaction strategy with the dynamical confidence constraint loss to model the interactions of histology and molecular markers. Our experiments show that our method outperforms other state-of-the-art methods in classifying diffuse glioma,as well as related histology and molecular markers on a multi-institutional dataset.

eess.IV↗

arXiv2023

GroundNLQ @ Ego4D Natural Language Queries Challenge 2023

In this report, we present our champion solution for Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2023. Essentially, to accurately ground in a video, an effective egocentric feature extractor and a powerful grounding model are required. Motivated by this, we leverage a two-stage pre-training strategy to train egocentric feature extractors and the grounding model on video narrations, and further fine-tune the model on annotated data. In addition, we introduce a novel grounding model GroundNLQ, which employs a multi-modal multi-scale grounding module for effective video and text fusion and various temporal intervals, especially for long videos. On the blind test set, GroundNLQ achieves 25.67 and 18.18 for R1@IoU=0.3 and R1@IoU=0.5, respectively, and surpasses all other teams by a noticeable margin. Our code will be released at\url{https://github.com/houzhijian/GroundNLQ}.

cs.CV↗