Search Results for author:
Found 48 papers, 15 papers with code
SCoralDet: Efficient real-time underwater soft coral detection with YOLO
To address these challenges, we propose SCoralDet, a soft coral detection model based on the YOLO architecture.
Ranked #1 on
2D Object Detection
on SCoralDet Dataset
Rate-Distortion Optimized Skip Coding of Region Adaptive Hierarchical Transform Coefficients for MPEG G-PCC
To address this problem, we propose an adaptive skip coding method for RAHT, which adaptively determines whether to encode the residuals of the last several layers or not, thereby improving the coding efficiency.
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
In this paper, we identify a common pitfall of margin-based methods -- the under-specification of ideal LM behavior on preferred and dispreferred responses individually, which leads to two unintended consequences as the margin increases: (1) The probability of dispreferred (e. g., unsafe) responses may increase, resulting in potential safety alignment failures.
Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds
In addition, this work establishes a database named WPC6. 0, the first and largest PCQA database dedicated to Trisoup-Lifting encoding mode, encompassing 400 distorted point clouds with both 4 geometric multiplied by 5 texture distortion levels.
EEPNet: Efficient Edge Pixel-based Matching Network for Cross-Modal Dynamic Registration between LiDAR and Camera
To address these issues, we propose EEPNet, an advanced network that leverages reflectance maps obtained from point cloud projections to enhance registration accuracy.
SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds
We propose an end-to-end attribute compression method for dense point clouds.
Feature Compression for Cloud-Edge Multimodal 3D Object Detection
Given a sparse tensor-based object detection network at the edge device, we introduce two modes to accommodate different application requirements: Transmission-Friendly Feature Compression (T-FFC) and Accuracy-Friendly Feature Compression (A-FFC).
Approximately Invertible Neural Network for Learned Image Compression
The analysis transform and synthesis transform are used to encode an image to latent feature and decode the quantized feature to reconstruct the image, and can be regarded as coupled transforms.
Conversational Dueling Bandits in Generalized Linear Models
Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities.
Cuboid-Net: A Multi-Branch Convolutional Neural Network for Joint Space-Time Video Super Resolution
The demand for high-resolution videos has been consistently rising across various domains, propelled by continuous advancements in science, technology, and societal.
3DAttGAN: A 3D Attention-based Generative Adversarial Network for Joint Space-Time Video Super-Resolution
The discriminative network uses a two-branch structure to handle details and motion information, making the generated results more accurate.
Generative Adversarial Network
Space-time Video Super-resolution
+1
Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction
The proposed module can predict the number of occupied child nodes and map it into an 8- dimensional vector to assist the context model in predicting the probability distribution of the occupancy of the current node for efficient entropy coding.
OMR-NET: a two-stage octave multi-scale residual network for screen content image compression
Screen content (SC) differs from natural scene (NS) with unique characteristics such as noise-free, repetitive patterns, and high contrast.
Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss
In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss function.
Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution
To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module.
PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression
Learning-based methods have proven successful in compressing geometric information for point clouds.
Gradient Guidance for Diffusion Models: An Optimization Perspective
As for guidance design, directly bringing in the gradient of an external objective function as guidance would jeopardize the structure in generated samples.
Physics-based reward driven image analysis in microscopy
We present a methodology based on the concept of a Reward Function coupled with Bayesian Optimization, to optimize image analysis workflows dynamically.
Diffusion Model for Data-Driven Black-Box Optimization
In this paper, we focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization over complex structured variables.
Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization
To enhance the efficiency of such a process, we propose a tree search-based bandit learning method, which expands a tree starting from the initial sequence with the guidance of a bandit machine learning model.
Global Structure-Aware Diffusion Process for Low-Light Image Enhancement
To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory.
Ranked #3 on
Low-Light Image Enhancement
on LOL
Spatial-Temporal Transformer based Video Compression Framework
Similar as the traditional video coding, LVC inherits motion estimation/compensation, residual coding and other modules, all of which are implemented with neural networks (NNs).
Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
Building upon this, we leverage offline RL techniques for off-policy LTR and propose the Click Model-Agnostic Unified Off-policy Learning to Rank (CUOLR) method, which could be easily applied to a wide range of click models.
Adversarial Attacks on Online Learning to Rank with Stochastic Click Models
We propose the first study of adversarial attacks on online learning to rank.
Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation
Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.
Ranked #1 on
3D Object Classification
on ModelNet40
GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute
To reduce color distortion in point clouds, we propose a graph-based quality enhancement network (GQE-Net) that uses geometry information as an auxiliary input and graph convolution blocks to extract local features efficiently.
Dynamic Local Feature Aggregation for Learning on Point Clouds
Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers.
Progressive Knowledge Transfer Based on Human Visual Perception Mechanism for Perceptual Quality Assessment of Point Clouds
In this paper, a progressive knowledge transfer based on human visual perception mechanism for perceptual quality assessment of point clouds (PKT-PCQA) is proposed.
Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization
We propose a Thompson Sampling-guided Directed Evolution (TS-DE) framework for sequence optimization, where the sequence-to-function mapping is unknown and querying a single value is subject to costly and noisy measurements.
PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions.
Neural network is heterogeneous: Phase matters more
We find a heterogeneity in both complex and real valued neural networks with the insight from wave optics, claiming a much more important role of phase than its amplitude counterpart in the weight matrix.
A Global Appearance and Local Coding Distortion based Fusion Framework for CNN based Filtering in Video Coding
To the best of our knowledge, we are the first one that clearly characterizes the video filtering process from the above global appearance and local coding distortion restoration aspects with experimental verification, providing a clear pathway to developing filter techniques.
Nodal Frequency Performance of Power Networks
Then, we present how the initial RoCoF of the nodal frequencies are related to the inertia constants of multiple generators in a power network, which leads to a performance metric to analyze nodal frequency performance.
Adaptive Deconvolution-based stereo matching Net for Local Stereo Matching
In deep learning-based local stereo matching methods, larger image patches usually bring better stereo matching accuracy.
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence.
Ranked #6 on
3D Dense Shape Correspondence
on SHREC'19
(using extra training data)
Reduced Reference Perceptual Quality Model and Application to Rate Control for 3D Point Cloud Compression
In rate-distortion optimization, the encoder settings are determined by maximizing a reconstruction quality measure subject to a constraint on the bit rate.
Random Walk for modelling Multi Core Fiber cross-talk and step distribution characterisation
In addition, this model is consistent with statistical analysis such as short term average crosstalk (STAXT), keeping the same convergence properties and it showed to be almost independent to time-window.
Experimental Analysis on Variations and Accuracy of Crosstalk in Trench-Assisted Multi-core Fibers
Space division multiplexing using multi-core fiber (MCF) is a promising solution to cope with the capacity crunch in standard single-mode fiber based optical communication systems.
Learning Entangled Single-Sample Gaussians in the Subset-of-Signals Model
In the setting of entangled single-sample distributions, the goal is to estimate some common parameter shared by a family of $n$ distributions, given one single sample from each distribution.
Learning Entangled Single-Sample Distributions via Iterative Trimming
We study mean estimation and linear regression under general conditions, and analyze a simple and computationally efficient method based on iteratively trimming samples and re-estimating the parameter on the trimmed sample set.
Learning Light Field Angular Super-Resolution via a Geometry-Aware Network
In addition, our method preserves the light field parallax structure better.
Non-Cooperative Game Theory Based Rate Adaptation for Dynamic Video Streaming over HTTP
The proposed algorithm is proxy-free.
An Ensemble Rate Adaptation Framework for Dynamic Adaptive Streaming Over HTTP
Specifically, the proposed framework is composed of two modules, i. e., the method pool and method controller.
Spatial and Temporal Consistency-Aware Dynamic Adaptive Streaming for 360-Degree Videos
That is, our method preserves both the quality and the smoothness of tiles in FoV, thus providing the best QoE for users.
A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression
Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way.
Single Image based Head Pose Estimation with Spherical Parameterization and 3D Morphing
Specifically, the rectangular coordinates of only four non-coplanar feature points from a predefined 3D facial model as well as the corresponding ones automatically/ manually extracted from a 2D face image are first normalized to exclude the effect of external factors (i. e., scale factor and translation parameters).
Removing Stripes, Scratches, and Curtaining with Non-Recoverable Compressed Sensing
Highly-directional image artifacts such as ion mill curtaining, mechanical scratches, or image striping from beam instability degrade the interpretability of micrographs.
