Search Results for author:
Found 60 papers, 28 papers with code
A Coarse-to-Fine Model for 3D Pose Estimation and Sub-category Recognition
Despite the fact that object detection, 3D pose estimation, and sub-category recognition are highly correlated tasks, they are usually addressed independently from each other because of the huge space of parameters.
Data-Driven 3D Voxel Patterns for Object Category Recognition
Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image.
Deep Metric Learning via Lifted Structured Feature Embedding
Additionally, we collected Online Products dataset: 120k images of 23k classes of online products for metric learning.
Learning to Track: Online Multi-Object Tracking by Decision Making
Online Multi-Object Tracking (MOT) has wide applications in time-critical video analysis scenarios, such as robot navigation and autonomous driving.
Ranked #19 on
Multiple Object Tracking
on KITTI Tracking test
Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation.
Ranked #4 on
Vehicle Pose Estimation
on KITTI Cars Hard
DA-RNN: Semantic Mapping with Data Associated Recurrent Neural Networks
3D scene understanding is important for robots to interact with the 3D world in a meaningful way.
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
We conduct extensive experiments on our YCB-Video dataset and the OccludedLINEMOD dataset to show that PoseCNN is highly robust to occlusions, can handle symmetric objects, and provide accurate pose estimation using only color images as input.
Ranked #3 on
6D Pose Estimation using RGB
on YCB-Video
Recurrent Autoregressive Networks for Online Multi-Object Tracking
The external memory explicitly stores previous inputs of each trajectory in a time window, while the internal memory learns to summarize long-term tracking history and associate detections by processing the external memory.
DeepIM: Deep Iterative Matching for 6D Pose Estimation
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality.
Ranked #1 on
6D Pose Estimation using RGB
on YCB-Video
Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
Using synthetic data generated in this manner, we introduce a one-shot deep neural network that is able to perform competitively against a state-of-the-art network trained on a combination of real and synthetic data.
Robotics
Object Discovery in Videos as Foreground Motion Clustering
We consider the problem of providing dense segmentation masks for object discovery in videos.
PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking
In this work, we formulate the 6D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3D rotation and the 3D translation of an object are decoupled.
The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation
We show that our method, trained on this dataset, can produce sharp and accurate masks, outperforming state-of-the-art methods on unseen object instance segmentation.
Self-supervised 6D Object Pose Estimation for Robot Manipulation
In this way, our system is able to continuously collect data and improve its pose estimation modules.
Robotics
Manipulation Trajectory Optimization with Online Grasp Synthesis and Selection
In robot manipulation, planning the motion of a robot manipulator to grasp an object is a fundamental problem.
Robotics
LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation
We evaluate the performance of our method for unseen object pose estimation on MOPED as well as the ModelNet and LINEMOD datasets.
Unseen Object Instance Segmentation for Robotic Environments
We also show that our method can segment unseen objects for robot grasping.
Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
In this work, we propose a new method for unseen object instance segmentation by learning RGB-D feature embeddings from synthetic data.
Flow Field Reconstructions with GANs based on Radial Basis Functions
Motivated by the problems of existing approaches and inspired by the success of the generative adversarial networks (GANs) in the field of computer vision, we prove an optimal discriminator theorem that the optimal discriminator of a GAN is a radial basis function neural network (RBFNN) while dealing with nonlinear sparse FFD regression and generation.
Information Laundering for Model Privacy
In this work, we propose information laundering, a novel framework for enhancing model privacy.
Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds
We demonstrate that our learned policy can be integrated into a tabletop 6D grasping system and a human-robot handover system to improve the grasping performance of unseen objects.
Aerodynamic Data Predictions Based on Multi-task Learning
Predicting high-speed data is more difficult than predicting low-speed data, owing to that the number of high-speed data is limited, i. e. the quality of the Burgers' dataset is not satisfactory.
Causal Inference from Slowly Varying Nonstationary Processes
Causal inference from observational data following the restricted structural causal model (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or nonlinearity.
Deterministic distribution of multipartite entanglement and steering in a quantum network by separable states
We experimentally demonstrate the deterministic distribution of two- and three-mode Gaussian entanglement and steering by transmitting separable states in a network consisting of a quantum server and multiple users.
Quantum Physics
RGB-D Local Implicit Function for Depth Completion of Transparent Objects
Key to our approach is a local implicit neural representation built on ray-voxel pairs that allows our method to generalize to unseen objects and achieve fast inference speed.
DexYCB: A Benchmark for Capturing Hand Grasping of Objects
We introduce DexYCB, a new dataset for capturing hand grasping of objects.
RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks
We postulate that a network architecture that encodes relations between objects at a high-level can be beneficial.
A Subsampling-Based Method for Causal Discovery on Discrete Data
Inferring causal directions on discrete and categorical data is an important yet challenging problem.
Differentially Private Variable Selection via the Knockoff Filter
The knockoff filter, recently developed by Barber and Candes, is an effective procedure to perform variable selection with a controlled false discovery rate (FDR).
TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information
We propose TALISMAN, a novel framework for Targeted Active Learning or object detectIon with rare slices using Submodular MutuAl iNformation.
iCaps: Iterative Category-level Object Pose and Shape Estimation
The auto-encoder can be used in a particle filter framework to estimate and track 6D poses of objects in a category.
Variable Selection with the Knockoffs: Composite Null Hypotheses
The fixed-X knockoff filter is a flexible framework for variable selection with false discovery rate (FDR) control in linear models with arbitrary design matrices (of full column rank) and it allows for finite-sample selective inference via the Lasso estimates.
A Multi-Characteristic Learning Method with Micro-Doppler Signatures for Pedestrian Identification
The identification of pedestrians using radar micro-Doppler signatures has become a hot topic in recent years.
An Invariant Matching Property for Distribution Generalization under Intervened Response
The task of distribution generalization concerns making reliable prediction of a response in unseen environments.
HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers
We analyze the performance of a set of baselines and show a correlation with a real-world evaluation.
A Manifold-based Airfoil Geometric-feature Extraction and Discrepant Data Fusion Learning Method
Geometrical shape of airfoils, together with the corresponding flight conditions, are crucial factors for aerodynamic performances prediction.
FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments
We introduce the Few-Shot Object Learning (FewSOL) dataset for object recognition with a few images per object.
Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network
In this paper, we present a Memory Prior Contrastive Network (MPCN) that can store shape prior knowledge in a few-shot learning based 3D reconstruction framework.
Learning Invariant Representations under General Interventions on the Response
One principled approach is to adopt the structural causal models to describe training and test models, following the invariance principle which says that the conditional distribution of the response given its predictors remains the same across environments.
Sample-and-Forward: Communication-Efficient Control of the False Discovery Rate in Networks
This work concerns controlling the false discovery rate (FDR) in networks under communication constraints.
Mean Shift Mask Transformer for Unseen Object Instance Segmentation
To illustrate the effectiveness of our method, we apply MSMFormer to unseen object instance segmentation.
Ranked #1 on
Unseen Object Instance Segmentation
on OCID
On Large-Scale Multiple Testing Over Networks: An Asymptotic Approach
We take an asymptotic approach and propose two methods, proportion-matching and greedy aggregation, tailored to distributed settings.
SLGTformer: An Attention-Based Approach to Sign Language Recognition
However, this frontal appearance can be quantified as a temporal sequence of human body pose, leading to Sign Language Recognition through the learning of spatiotemporal dynamics of skeleton keypoints.
Generalized Invariant Matching Property via LASSO
In this work, by formulating a high-dimensional problem with intrinsic sparsity, we generalize the invariant matching property for an important setting when only the target is intervened.
Deep Dependency Networks for Multi-Label Classification
We propose a simple approach which combines the strengths of probabilistic graphical models and deep learning architectures for solving the multi-label classification task, focusing specifically on image and video data.
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction
By applying multi-object tracking and video object segmentation on the images collected via robot pushing, our system can generate segmentation masks of all the objects in these images in a self-supervised way.
Dual Residual Attention Network for Image Denoising
The proposed DRANet includes two different parallel branches, which can capture complementary features to enhance the learning ability of the model.
Ranked #1 on
Image Denoising
on SIDD
(Average PSNR metric)
Structural Hawkes Processes for Learning Causal Structure from Discrete-Time Event Sequences
Learning causal structure among event types from discrete-time event sequences is a particularly important but challenging task.
Novel deep learning methods for 3D flow field segmentation and classification
Flow field segmentation and classification help researchers to understand vortex structure and thus turbulent flow.
Pedestrian Recognition with Radar Data-Enhanced Deep Learning Approach Based on Micro-Doppler Signatures
As a hot topic in recent years, the ability of pedestrians identification based on radar micro-Doppler signatures is limited by the lack of adequate training data.
SCENEREPLICA: Benchmarking Real-World Robot Manipulation by Creating Replicable Scenes
We present a new reproducible benchmark for evaluating robot manipulation in the real world, specifically focusing on pick-and-place.
Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
The two encoders are used to compute prototypes of image classes for classification.
AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer
This method uses the Attention mechanism of Transformer itself to reduce the influence of noises and aberrant values in the original samples on the prediction results, without increasing additional trainable parameters, and the computational cost is very low, thereby avoiding the problem of high resource consumption in common Mixup methods such as Sentence Mixup .
Segment Every Out-of-Distribution Object
Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects.
CaptainCook4D: A dataset for understanding errors in procedural activities
Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives.
Incorporating Riemannian Geometric Features for Learning Coefficient of Pressure Distributions on Airplane Wings
The aerodynamic coefficients of aircrafts are significantly impacted by its geometry, especially when the angle of attack (AoA) is large.
Low-Rank Approximation of Structural Redundancy for Self-Supervised Learning
We study the data-generating mechanism for reconstructive SSL to shed light on its effectiveness.
RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features
In order to successfully perform manipulation tasks in new environments, such as grasping, robots must be proficient in segmenting unseen objects from the background and/or other objects.
Grasping Trajectory Optimization with Point Clouds
The task space of a robot is represented by a point cloud that can be obtained from depth sensors.
Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis
Fortunately, in this work, we found that the causal order from $X$ to its child $Y$ is identifiable if $X$ is a root vertex and has at least two directed paths to $Y$, or the ancestor of $X$ with the most directed path to $X$ has a directed path to $Y$ without passing $X$.
