Search Results for author: Zhu Li

Found 55 papers, 14 papers with code

Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection

no code implementations1 Jun 2025 Zhu Li, Yuqing Zhang, Xiyuan Gao, Shekhar Nayak, Matt Coler

Sarcasm fundamentally alters meaning through tone and context, yet detecting it in speech remains a challenge due to data scarcity.

Sarcasm Detection

DPCD: A Quality Assessment Database for Dynamic Point Clouds

no code implementations18 May 2025 Yating Liu, Yujie Zhang, Qi Yang, Yiling Xu, Zhu Li, Ye-kui Wang

Recently, the advancements in Virtual/Augmented Reality (VR/AR) have driven the demand for Dynamic Point Clouds (DPC).

Point Cloud Quality Assessment

Textured mesh Quality Assessment using Geometry and Color Field Similarity

1 code implementation16 May 2025 Kaifa Yang, Qi Yang, Zhu Li, Yiling Xu

Motivated by the effectiveness of fields in representing both 3D geometry and color information, we propose a novel point-based TMQA method called field mesh quality metric (FMQM).

3D geometry

ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction

1 code implementation13 May 2025 He Huang, Qi Yang, Mufan Liu, Yiling Xu, Zhu Li

Existing 4D Gaussian Splatting methods rely on per-Gaussian deformation from a canonical space to target frames, which overlooks redundancy among adjacent Gaussian primitives and results in suboptimal performance.

HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder

1 code implementation3 May 2025 Qi Yang, Le Yang, Geert Van der Auwera, Zhu Li

Most existing 3D Gaussian Splatting (3DGS) compression schemes focus on producing compact 3DGS representation via implicit data embedding.

3DGS Data Compression

CompGS++: Compressed Gaussian Splatting for Static and Dynamic Scene Representation

no code implementations17 Apr 2025 Xiangrui Liu, Xinju Wu, Shiqi Wang, Zhu Li, Sam Kwong

We further devise a temporal primitive prediction module to handle dynamic scenes, which exploits primitive correlations across timestamps to effectively reduce temporal redundancy.

Prediction

Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model

no code implementations18 Mar 2025 Mufan Liu, Qi Yang, He Huang, Wenjie Huang, Zhenlong Yuan, Zhu Li, Yiling Xu

Specifically, our framework is built upon two core components: (1) a spatio-temporal significance pruning strategy that eliminates over 64\% of the deformable primitives, followed by an entropy-constrained spherical harmonics compression applied to the remainder; and (2) a deep context model that integrates intra- and inter-prediction with hyperprior into a coarse-to-fine context structure to enable efficient multiscale latent embedding compression.

3DGS Novel View Synthesis

D2GV: Deformable 2D Gaussian Splatting for Video Representation in 400FPS

1 code implementation7 Mar 2025 Mufan Liu, Qi Yang, Miaoran Zhao, He Huang, Le Yang, Zhu Li, Yiling Xu

Implicit Neural Representations (INRs) have emerged as a powerful approach for video representation, offering versatility across tasks such as compression and inpainting.

Denoising Quantization

From Images to Point Clouds: An Efficient Solution for Cross-media Blind Quality Assessment without Annotated Training

no code implementations23 Jan 2025 Yipeng Liu, Qi Yang, Yujie Zhang, Yiling Xu, Le Yang, Zhu Li

We present a novel quality assessment method which can predict the perceptual quality of point clouds from new scenes without available annotations by leveraging the rich prior knowledge in images, called the Distribution-Weighted Image-Transferred Point Cloud Quality Assessment (DWIT-PCQA).

Disentanglement Domain Adaptation +1

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

no code implementations9 Jan 2025 Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li

We prove that the DFIV algorithm achieves the minimax optimal learning rate when the target structural function lies in a Besov space.

regression

Sparse Point Clouds Assisted Learned Image Compression

no code implementations20 Dec 2024 Yiheng Jiang, Haotian Zhang, Li Li, Dong Liu, Zhu Li

In this paper, motivated by the recent success of learned image compression, we propose a new framework that uses sparse point clouds to assist in learned image compression in the autonomous driving scenario.

Autonomous Driving Image Compression

Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation

no code implementations15 Dec 2024 Yujie Zhang, Bingyang Cui, Qi Yang, Zhu Li, Yiling Xu

Text-to-3D generation has achieved remarkable progress in recent years, yet evaluating these methods remains challenging for two reasons: i) Existing benchmarks lack fine-grained evaluation on different prompt categories and evaluation dimensions.

3D Generation Benchmarking +1

Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal

no code implementations29 Nov 2024 Dimitri Meunier, Zhu Li, Tim Christensen, Arthur Gretton

We study the kernel instrumental variable algorithm of \citet{singh2019kernel}, a nonparametric two-stage least squares (2SLS) procedure which has demonstrated strong empirical performance.

regression

Face De-identification: State-of-the-art Methods and Comparative Studies

no code implementations15 Nov 2024 Jingyi Cao, Xiangyi Chen, Bo Liu, Ming Ding, Rong Xie, Li Song, Zhu Li, Wenjun Zhang

The widespread use of image acquisition technologies, along with advances in facial recognition, has raised serious privacy concerns.

De-identification Survey

Seeking the Sufficiency and Necessity Causal Features in Multimodal Representation Learning

no code implementations29 Aug 2024 BoYu Chen, Junjie Liu, Zhu Li, Mengyue Yang

We address these challenges by first conceptualizing multimodal representations as comprising modality-invariant and modality-specific components.

Representation Learning

A Functional Trade-off between Prosodic and Semantic Cues in Conveying Sarcasm

no code implementations27 Aug 2024 Zhu Li, Xiyuan Gao, Yuqing Zhang, Shekhar Nayak, Matt Coler

This study investigates the acoustic features of sarcasm and disentangles the interplay between the propensity of an utterance being used sarcastically and the presence of prosodic cues signaling sarcasm.

Multi-Scale Feature Fusion using Channel Transformers for Guided Thermal Image Super Resolution

no code implementations CVPR Workshop 2024 Raghunath Sai Puttagunta, Birendra Kathariya, Zhu Li, George York

MSFFCT achieved state-of-the-art results on the ×8 and ×16 GTISR tasks of the 2024 Perception Beyond Visual Spectrum (PBVS) challenge, winning 2nd place in both tasks and demonstrating its effectiveness in real-world scenarios.

Image Super-Resolution Infrared And Visible Image Fusion +1

Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms

no code implementations23 May 2024 Dimitri Meunier, Zikai Shen, Mattes Mollenhauer, Arthur Gretton, Zhu Li

First, we rigorously confirm the so-called saturation effect for ridge regression with vector-valued output by deriving a novel lower bound on learning rates; this bound is shown to be suboptimal when the smoothness of the regression function exceeds a certain level.

regression

CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting

no code implementations15 Apr 2024 Xiangrui Liu, Xinju Wu, Pingping Zhang, Shiqi Wang, Zhu Li, Sam Kwong

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation.

MODIPHY: Multimodal Obscured Detection for IoT using PHantom Convolution-Enabled Faster YOLO

1 code implementation12 Feb 2024 Shubhabrata Mukherjee, Cory Beard, Zhu Li

YOLO Phantom utilizes the novel Phantom Convolution block, achieving comparable accuracy to the latest YOLOv8n model while simultaneously reducing both parameters and model size by 43\%, resulting in a significant 19\% reduction in Giga Floating-Point Operations (GFLOPs).

Autonomous Vehicles object-detection +2

Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithm

no code implementations12 Dec 2023 Zhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur Gretton

We present the first optimal rates for infinite-dimensional vector-valued ridge regression on a continuous scale of norms that interpolate between $L_2$ and the hypothesis space, which we consider as a vector-valued reproducing kernel Hilbert space.

regression

Applications of Large Scale Foundation Models for Autonomous Driving

no code implementations20 Nov 2023 Yu Huang, Yue Chen, Zhu Li

Since DARPA Grand Challenges (rural) in 2004/05 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications.

Autonomous Driving

See SIFT in a Rain

1 code implementation1 Nov 2023 Wei Wu, Hao Chang, Zhu Li

One is difference of Gaussian (DoG) pyramid recovery network (DPRNet) for SIFT detection, and the other gradients of Gaussian images recovery network (GGIRNet) for SIFT description.

Rain Removal

Nonlinear Meta-Learning Can Guarantee Faster Rates

no code implementations20 Jul 2023 Dimitri Meunier, Zhu Li, Arthur Gretton, Samory Kpotufe

The main aim of theoretical guarantees on the subject is to establish the extent to which convergence rates -- in learning a common representation -- \emph{may scale with the number $N$ of tasks} (as well as the number of samples per task).

Meta-Learning regression

Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching

1 code implementation9 May 2023 Shuting Xia, Tingyu Fan, Yiling Xu, Jenq-Neng Hwang, Zhu Li

3D dynamic point cloud (DPC) compression relies on mining its temporal context, which faces significant challenges due to DPC's sparsity and non-uniform structure.

Feature Correlation Motion Compensation +3

Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compression

no code implementations26 Sep 2022 Tingyu Fan, Linyao Gao, Yiling Xu, Dong Wang, Zhu Li

Besides, we propose a residual coding framework for the compression of the latent variable, which explores the spatial correlation of each layer by progressive downsampling, and model the corresponding residual with a fully-factorized entropy model.

Optimal Rates for Regularized Conditional Mean Embedding Learning

no code implementations2 Aug 2022 Zhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur Gretton

We address the misspecified setting, where the target CME is in the space of Hilbert-Schmidt operators acting from an input interpolation space between $\mathcal{H}_X$ and $L_2$, to $\mathcal{H}_Y$.

Bayesian Inference

Inter-Frame Compression for Dynamic Point Cloud Geometry Coding

no code implementations25 Jul 2022 Anique Akhtar, Zhu Li, Geert Van der Auwera

The proposed method introduces a novel predictor network for motion compensation in the feature domain to map the latent representation of the previous frame to the coordinates of the current frame to predict the current frame's feature embedding.

Autonomous Driving Decoder +2

Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems

no code implementations31 May 2022 Zeyan Liu, Fengjun Li, Jingqiang Lin, Zhu Li, Bo Luo

In this paper, we present the first large-scale study on the stealthiness of adversarial samples used in the attacks against deep learning.

Benchmarking

D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction

1 code implementation2 May 2022 Tingyu Fan, Linyao Gao, Yiling Xu, Zhu Li, Dong Wang

This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space.

Motion Compensation Motion Estimation +2

Sharp Analysis of Random Fourier Features in Classification

no code implementations22 Sep 2021 Zhu Li

Utilizing the regularity condition, we show for the first time that random Fourier features classification can achieve $O(1/\sqrt{n})$ learning rate with only $\Omega(\sqrt{n} \log n)$ features, as opposed to $\Omega(n)$ features suggested by previous results.

Classification

No-Reference Image Quality Assessment by Hallucinating Pristine Features

1 code implementation9 Aug 2021 Baoliang Chen, Lingyu Zhu, Chenqi Kong, Hanwei Zhu, Shiqi Wang, Zhu Li

In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination.

Disentanglement Hallucination +2

Towards an Understanding of Benign Overfitting in Neural Networks

no code implementations6 Jun 2021 Zhu Li, Zhi-Hua Zhou, Arthur Gretton

Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory.

Learning Theory

Effective Subspace Indexing via Interpolation on Stiefel and Grassmann manifolds

no code implementations1 Jan 2021 Wenqing Hu, Tiefeng Jiang, Zhu Li

We propose a novel local Subspace Indexing Model with Interpolation (SIM-I) for low-dimensional embedding of image datasets.

Multiscale Point Cloud Geometry Compression

2 code implementations7 Nov 2020 Jianqiang Wang, Dandan Ding, Zhu Li, Zhan Ma

Recent years have witnessed the growth of point cloud based applications because of its realistic and fine-grained representation of 3D objects and scenes.

Attribute

Dense-View GEIs Set: View Space Covering for Gait Recognition based on Dense-View GAN

no code implementations26 Sep 2020 Rijun Liao, Weizhi An, Shiqi Yu, Zhu Li, Yongzhen Huang

In this paper, we, therefore, introduce a Dense-View GEIs Set (DV-GEIs) to deal with the challenge of limited view angles.

Gait Recognition

Benign Overfitting and Noisy Features

no code implementations6 Aug 2020 Zhu Li, Weijie Su, Dino Sejdinovic

Modern machine learning often operates in the regime where the number of parameters is much higher than the number of data points, with zero training loss and yet good generalization, thereby contradicting the classical bias-variance trade-off.

Inferring Point Cloud Quality via Graph Similarity

1 code implementation31 May 2020 Qi Yang, Zhan Ma, Yiling Xu, Zhu Li, Jun Sun

We propose the GraphSIM -- an objective metric to accurately predict the subjective quality of point cloud with superimposed geometry and color impairments.

All Graph Similarity

Hyperspectral Image Classification with Attention Aided CNNs

1 code implementation25 May 2020 Renlong Hang, Zhu Li, Qingshan Liu, Pedram Ghamisi, Shuvra S. Bhattacharyya

Specifically, a spectral attention sub-network and a spatial attention sub-network are proposed for spectral and spatial classification, respectively.

Classification General Classification +2

Dual Temporal Memory Network for Efficient Video Object Segmentation

no code implementations13 Mar 2020 Kaihua Zhang, Long Wang, Dong Liu, Bo Liu, Qingshan Liu, Zhu Li

We present an end-to-end network which stores short- and long-term video sequence information preceding the current frame as the temporal memories to address the temporal modeling in VOS.

Object One-shot visual object segmentation +4

Classification of Hyperspectral and LiDAR Data Using Coupled CNNs

no code implementations4 Feb 2020 Renlong Hang, Zhu Li, Pedram Ghamisi, Danfeng Hong, Guiyu Xia, Qingshan Liu

For the feature-level fusion, three different fusion strategies are evaluated, including the concatenation strategy, the maximization strategy, and the summation strategy.

Classification General Classification

Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness

no code implementations11 Nov 2019 Zhu Li, Adrian Perez-Suay, Gustau Camps-Valls, Dino Sejdinovic

We present a regularization approach to this problem that trades off predictive accuracy of the learned models (with respect to biased labels) for the fairness in terms of statistical parity, i. e. independence of the decisions from the sensitive covariates.

Crime Prediction Ethics +2

Residual-Guided In-Loop Filter Using Convolution Neural Network

no code implementations29 Jul 2019 Wei Jia, Li Li, Zhu Li, Xiang Zhang, Shan Liu

The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc.

Blocking

Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds

no code implementations18 Apr 2019 Wei Yan, Yiting shao, Shan Liu, Thomas H. Li, Zhu Li, Ge Li

Point cloud is a fundamental 3D representation which is widely used in real world applications such as autonomous driving.

Autonomous Driving Image Compression

Towards A Unified Analysis of Random Fourier Features

no code implementations24 Jun 2018 Zhu Li, Jean-Francois Ton, Dino Oglic, Dino Sejdinovic

We study both the standard random Fourier features method for which we improve the existing bounds on the number of features required to guarantee the corresponding minimax risk convergence rate of kernel ridge regression, as well as a data-dependent modification which samples features proportional to \emph{ridge leverage scores} and further reduces the required number of features.

Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction

no code implementations28 Apr 2018 Yiting Shao, Qi Zhang, Ge Li, Zhu Li

In intra-frame compression of point cloud color attributes, results demonstrate that our method performs better than the state-of-the-art region-adaptive hierarchical transform (RAHT) system, and on average a 29. 37$\%$ BD-rate gain is achieved.

Multimedia

Robust Emotion Recognition from Low Quality and Low Bit Rate Video: A Deep Learning Approach

no code implementations10 Sep 2017 Bowen Cheng, Zhangyang Wang, Zhaobin Zhang, Zhu Li, Ding Liu, Jianchao Yang, Shuai Huang, Thomas S. Huang

Emotion recognition from facial expressions is tremendously useful, especially when coupled with smart devices and wireless multimedia applications.

Decoder Emotion Recognition +1

Projection based advanced motion model for cubic mapping for 360-degree video

no code implementations21 Feb 2017 Li Li, Zhu Li, Madhukar Budagavi, Houqiang Li

This paper proposes a novel advanced motion model to handle the irregular motion for the cubic map projection of 360-degree video.

Cannot find the paper you are looking for? You can Submit a new open access paper.