Search Results for author:
Found 55 papers, 14 papers with code
Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection
Sarcasm fundamentally alters meaning through tone and context, yet detecting it in speech remains a challenge due to data scarcity.
DPCD: A Quality Assessment Database for Dynamic Point Clouds
Recently, the advancements in Virtual/Augmented Reality (VR/AR) have driven the demand for Dynamic Point Clouds (DPC).
Textured mesh Quality Assessment using Geometry and Color Field Similarity
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).
ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction
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
Most existing 3D Gaussian Splatting (3DGS) compression schemes focus on producing compact 3DGS representation via implicit data embedding.
CompGS++: Compressed Gaussian Splatting for Static and Dynamic Scene Representation
We further devise a temporal primitive prediction module to handle dynamic scenes, which exploits primitive correlations across timestamps to effectively reduce temporal redundancy.
Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model
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.
D2GV: Deformable 2D Gaussian Splatting for Video Representation in 400FPS
Implicit Neural Representations (INRs) have emerged as a powerful approach for video representation, offering versatility across tasks such as compression and inpainting.
From Images to Point Clouds: An Efficient Solution for Cross-media Blind Quality Assessment without Annotated Training
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).
Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
We prove that the DFIV algorithm achieves the minimax optimal learning rate when the target structural function lies in a Besov space.
Sparse Point Clouds Assisted Learned Image Compression
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.
Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation
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.
AMuSeD: An Attentive Deep Neural Network for Multimodal Sarcasm Detection Incorporating Bi-modal Data Augmentation
This approach utilizes the Multimodal Sarcasm Detection Dataset (MUStARD) and introduces a two-phase bimodal data augmentation strategy.
Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal
We study the kernel instrumental variable algorithm of \citet{singh2019kernel}, a nonparametric two-stage least squares (2SLS) procedure which has demonstrated strong empirical performance.
Face De-identification: State-of-the-art Methods and Comparative Studies
The widespread use of image acquisition technologies, along with advances in facial recognition, has raised serious privacy concerns.
A Hierarchical Compression Technique for 3D Gaussian Splatting Compression
For non-anchor primitives, each is predicted based on the k-nearest anchor primitives.
Seeking the Sufficiency and Necessity Causal Features in Multimodal Representation Learning
We address these challenges by first conceptualizing multimodal representations as comprising modality-invariant and modality-specific components.
A Functional Trade-off between Prosodic and Semantic Cues in Conveying Sarcasm
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.
A Benchmark for Gaussian Splatting Compression and Quality Assessment Study
Second, based on GGSC, we create a GS Quality Assessment dataset (GSQA) with 120 samples.
Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compression
The state-of-the-art objective metrics are tested in the new dataset.
Multi-Scale Feature Fusion using Channel Transformers for Guided Thermal Image Super Resolution
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.
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
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.
CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting
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
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).
Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithm
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.
Applications of Large Scale Foundation Models for Autonomous Driving
Since DARPA Grand Challenges (rural) in 2004/05 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications.
See SIFT in a Rain
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.
Nonlinear Meta-Learning Can Guarantee Faster Rates
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).
Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching
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.
Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compression
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
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 $\mathcal{H}_Y$.
Inter-Frame Compression for Dynamic Point Cloud Geometry Coding
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.
Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems
In this paper, we present the first large-scale study on the stealthiness of adversarial samples used in the attacks against deep learning.
D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction
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.
Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression
We call this compression method SparsePCGC.
Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data
Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech.
Sharp Analysis of Random Fourier Features in Classification
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.
No-Reference Image Quality Assessment by Hallucinating Pristine Features
In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination.
A Lightweight ReLU-Based Feature Fusion for Aerial Scene Classification
In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem.
Ranked #5 on
Aerial Scene Classification
on UCM (50% as trainset)
Towards an Understanding of Benign Overfitting in Neural Networks
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.
Effective Subspace Indexing via Interpolation on Stiefel and Grassmann manifolds
We propose a novel local Subspace Indexing Model with Interpolation (SIM-I) for low-dimensional embedding of image datasets.
Multiscale Point Cloud Geometry Compression
Recent years have witnessed the growth of point cloud based applications because of its realistic and fine-grained representation of 3D objects and scenes.
Dense-View GEIs Set: View Space Covering for Gait Recognition based on Dense-View GAN
In this paper, we, therefore, introduce a Dense-View GEIs Set (DV-GEIs) to deal with the challenge of limited view angles.
Benign Overfitting and Noisy Features
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
We propose the GraphSIM -- an objective metric to accurately predict the subjective quality of point cloud with superimposed geometry and color impairments.
Hyperspectral Image Classification with Attention Aided CNNs
Specifically, a spectral attention sub-network and a spatial attention sub-network are proposed for spectral and spatial classification, respectively.
Dual Temporal Memory Network for Efficient Video Object Segmentation
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.
Classification of Hyperspectral and LiDAR Data Using Coupled CNNs
For the feature-level fusion, three different fusion strategies are evaluated, including the concatenation strategy, the maximization strategy, and the summation strategy.
Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness
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.
Residual-Guided In-Loop Filter Using Convolution Neural Network
The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc.
Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds
Point cloud is a fundamental 3D representation which is widely used in real world applications such as autonomous driving.
Towards A Unified Analysis of Random Fourier Features
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
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
Emotion recognition from facial expressions is tremendously useful, especially when coupled with smart devices and wireless multimedia applications.
Projection based advanced motion model for cubic mapping for 360-degree video
This paper proposes a novel advanced motion model to handle the irregular motion for the cubic map projection of 360-degree video.
