Search Results for author:
Found 50 papers, 24 papers with code
Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble
We explore the capability of physics-informed neural networks (PINNs) to discover multiple solutions.
PUGS: Zero-shot Physical Understanding with Gaussian Splatting
We propose a new method that reconstructs 3D objects using the Gaussian splatting representation and predicts various physical properties in a zero-shot manner.
FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering
Recently, multi-modal large language models have made significant progress.
Towards Degradation-Robust Reconstruction in Generalizable NeRF
However, despite its potential for real-world applications, there has been limited research on the robustness of GNeRFs to different types of degradation present in the source images.
Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models
In this report, we introduce Takin AudioLLM, a series of techniques and models, mainly including Takin TTS, Takin VC, and Takin Morphing, specifically designed for audiobook production.
ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images
To advance the state of the art in the creation of 3D foundation models, this paper introduces the ConDense framework for 3D pre-training utilizing existing pre-trained 2D networks and large-scale multi-view datasets.
NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements
This study introduces NeuroSEM, a hybrid framework integrating PINNs with the high-fidelity Spectral Element Method (SEM) solver, Nektar++.
Pseudo-Labeling by Multi-Policy Viewfinder Network for Image Cropping
This idea can be implemented in a pseudo-labeling way: producing pseudo labels for unlabeled data by a teacher model and training a student model with these pseudo labels.
A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks
Kolmogorov-Arnold Networks (KANs) were recently introduced as an alternative representation model to MLP.
Kolmogorov-Arnold Networks
Physics-informed machine learning
Eigen-CNN: Eigenimages Plus Eigennoise Level Maps Guided Network for Hyperspectral Image Denoising
Experimental results on both simulated and real HSIs demonstrate the effectiveness of our trained Eigen-CNN compared with state-of-the-art HSI denoising methods.
Low-Cost and Real-Time Industrial Human Action Recognitions Based on Large-Scale Foundation Models
Industrial managements, including quality control, cost and safety optimization, etc., heavily rely on high quality industrial human action recognitions (IHARs) which were hard to be implemented in large-scale industrial scenes due to their high costs and poor real-time performance.
Digging Into Normal Incorporated Stereo Matching
To enhance geometric consistency, especially in low-texture regions, the estimated normal map is then leveraged to calculate a local affinity matrix, providing the residual learning with information about where the correction should refer and thus improving the residual learning efficiency.
Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey
Although the applications of artificial intelligence especially deep learning had greatly improved various aspects of intelligent manufacturing, they still face challenges for wide employment due to the poor generalization ability, difficulties to establish high-quality training datasets, and unsatisfactory performance of deep learning methods.
Operator Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations Characterized by Sharp Solutions
Initially, we utilize DeepONet to learn the solution operator for a set of smooth problems relevant to the PDEs characterized by sharp solutions.
A Self-Supervised Deep Denoiser for Hyperspectral and Multispectral Image Fusion
The plug-and-play (PnP) technique enables us to plug image priors into an alternating direction method of multipliers (ADMM) framework for solving a regularized optimization problem.
Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting
This task is typically addressed by extracting the features of query image and exemplars respectively and then matching their feature similarity, leading to an extract-then-match paradigm.
Ranked #4 on
Object Counting
on FSC147
POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo
Enable neural networks to capture 3D geometrical-aware features is essential in multi-view based vision tasks.
Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing
Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders.
FuRPE: Learning Full-body Reconstruction from Part Experts
These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model.
Joint Chinese Word Segmentation and Span-based Constituency Parsing
In constituency parsing, span-based decoding is an important direction.
Order-sensitive Neural Constituency Parsing
We propose a novel algorithm that improves on the previous neural span-based CKY decoder for constituency parsing.
MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detection
The insight behind introducing MonoSIM is that we propose to simulate the feature learning behaviors of a point cloud based detector for monocular detector during the training period.
Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important.
Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications.
Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association
This paper presents a new method to solve keypoint detection and instance association by using Transformer.
Ranked #10 on
Multi-Person Pose Estimation
on MS COCO
ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation
ACR-Pose consists of a Reconstructor and a Discriminator.
Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads
After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequently derived a series of transformer-based detection heads.
Adaptive Dilated Convolution For Human Pose Estimation
It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels.
SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation
The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance.
Graph-MLP: Node Classification without Message Passing in Graph
Graph Neural Network (GNN) has been demonstrated its effectiveness in dealing with non-Euclidean structural data.
DAVOS: Semi-Supervised Video Object Segmentation via Adversarial Domain Adaptation
Domain shift has always been one of the primary issues in video object segmentation (VOS), for which models suffer from degeneration when tested on unfamiliar datasets.
Physics-informed neural networks (PINNs) for fluid mechanics: A review
Despite the significant progress over the last 50 years in simulating flow problems using numerical discretization of the Navier-Stokes equations (NSE), we still cannot incorporate seamlessly noisy data into existing algorithms, mesh-generation is complex, and we cannot tackle high-dimensional problems governed by parametrized NSE.
TokenPose: Learning Keypoint Tokens for Human Pose Estimation
Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints.
V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection
V2F-Net consists of two sub-networks: Visible region Detection Network (VDN) and Full body Estimation Network (FEN).
Ranked #1 on
Object Detection
on CityPersons
Using Low-rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing
Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain the spatial information in the image.
General Instance Distillation for Object Detection
In recent years, knowledge distillation has been proved to be an effective solution for model compression.
IBRNet: Learning Multi-View Image-Based Rendering
Unlike neural scene representation work that optimizes per-scene functions for rendering, we learn a generic view interpolation function that generalizes to novel scenes.
Physics-informed neural networks with hard constraints for inverse design
We achieve the same objective as conventional PDE-constrained optimization methods based on adjoint methods and numerical PDE solvers, but find that the design obtained from hPINN is often simpler and smoother for problems whose solution is not unique.
Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation
However, for bottom-up methods, which need to handle a large variance of human scales and labeling ambiguities, the current practice seems unreasonable.
Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.
Efficient Learning of Control Policies for Robust Quadruped Bounding using Pretrained Neural Networks
The NN based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully.
EDNet: Efficient Disparity Estimation with Cost Volume Combination and Attention-based Spatial Residual
Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption and slow inference speed.
A Light-Weight Object Detection Framework with FPA Module for Optical Remote Sensing Imagery
On the DOTA dataset, CenterFPANet mAP is 64. 00%, and FPS is 22. 2, which is close to the accuracy of the anchor-based methods currently used and much faster than them.
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score.
Ranked #29 on
Person Re-Identification
on Occluded-DukeMTMC
Learning Delicate Local Representations for Multi-Person Pose Estimation
To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations.
Ranked #1 on
Keypoint Detection
on COCO test-challenge
Differentiating Features for Scene Segmentation Based on Dedicated Attention Mechanisms
In this paper, we differentiate features for scene segmentation based on dedicated attention mechanisms (DF-DAM), and two attention modules are proposed to optimize the high-level and low-level features in the encoder, respectively.
Rethinking on Multi-Stage Networks for Human Pose Estimation
Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods.
Ranked #1 on
Pose Estimation
on COCO minival
Deep Learning of Vortex Induced Vibrations
Of interest is the prediction of the lift and drag forces on the structure given some limited and scattered information on the velocity field.
Cascaded Pyramid Network for Multi-Person Pose Estimation
In this paper, we present a novel network structure called Cascaded Pyramid Network (CPN) which targets to relieve the problem from these "hard" keypoints.
Ranked #4 on
Keypoint Detection
on COCO test-challenge
Context-Aware Gaussian Fields for Non-Rigid Point Set Registration
Point set registration (PSR) is a fundamental problem in computer vision and pattern recognition, and it has been successfully applied to many applications.
