Search Results for author:
Found 92 papers, 42 papers with code
A Linguistically Motivated Test Suite to Semi-Automatically Evaluate German–English Machine Translation Output
Furthermore, we present various exemplary applications of our test suite that have been implemented in the past years, like contributions to the Conference of Machine Translation, the usage of the test suite and MT outputs for quality estimation, and the expansion of the test suite to the language pair Portuguese–English.
CHAIRS: Towards Full-Body Articulated Human-Object Interaction
By learning the geometrical relationships in HOI, we devise the very first model that leverage human pose estimation to tackle the estimation of articulated object poses and shapes during whole-body interactions.
3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification
However, leveraging 3D scene representation can be prohibitively unpractical for policy learning in this floor-level task, due to low sample efficiency and expensive computational cost.
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.
LoopDA: Constructing Self-loops to Adapt Nighttime Semantic Segmentation
In this paper, we propose LoopDA for domain adaptive nighttime semantic segmentation.
GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts
By identifying and defining 9 GAPart classes (e. g. buttons, handles, etc), we show that our part-centric approach allows our method to learn object perception and manipulation skills from seen object categories and directly generalize to unseen categories.
LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise
In general, LeNo consists of a simple shallow noise and noise estimation that embedded in the encoder and decoder of arbitrary SOD networks respectively.
GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF
In this work, we tackle 6-DoF grasp detection for transparent and specular objects, which is an important yet challenging problem in vision-based robotic systems, due to the failure of depth cameras in sensing their geometry.
The Extreme Cardiac MRI Analysis Challenge under Respiratory Motion (CMRxMotion)
The quality of cardiac magnetic resonance (CMR) imaging is susceptible to respiratory motion artifacts.
Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing
To test our method in real scenarios and enable future studies on generalizable visual-tactile tracking, we collect a real visual-tactile in-hand object pose tracking dataset.
DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
Compared with the field of object grasping with parallel grippers, dexterous grasping is very under-explored, partially owing to the lack of a large-scale dataset.
Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild
We for the first time propose a point cloud based hand joint tracking network, HandTrackNet, to estimate the inter-frame hand joint motion.
MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
The final of the 4 provided datasets contained real noise from the O3a observing run and signals up to a duration of 20 seconds with the inclusion of precession effects and higher order modes.
Shape Completion with Points in the Shadow
The core challenge is to generate plausible geometries to fill the unobserved part of the object based on a partial scan, which is under-constrained and suffers from a huge solution space.
Talking Head from Speech Audio using a Pre-trained Image Generator
We train a recurrent neural network to map from speech utterances to displacements in the latent space of the image generator.
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-based tasks.
Human Trajectory Prediction via Neural Social Physics
Our new model (Neural Social Physics or NSP) is a deep neural network within which we use an explicit physics model with learnable parameters.
Ranked #1 on
Trajectory Prediction
on Stanford Drone
Space-based gravitational wave signal detection and extraction with deep neural network
Space-based gravitational wave (GW) detectors will be able to observe signals from sources that are otherwise nearly impossible from current ground-based detection.
Underdetermined 2D-DOD and 2D-DOA Estimation for Bistatic Coprime EMVS-MIMO Radar: From the Difference Coarray Perspective
Firstly, a 5-D tensor model was constructed by using the multi-dimensional space-time characteristics of the received data.
8D Parameters Estimation for Bistatic EMVS-MIMO Radar via the nested PARAFAC
Firstly, the outer part PARAFAC algorithm was carried out to estimate the receive spatial response matrix and its first way factor matrix.
Real-time Controllable Motion Transition for Characters
Then, during generation, we design a transition model which is essentially a sampling strategy to sample from the learned manifold, based on the target frame and the aimed transition duration.
A Practical Two-stage Ranking Framework for Cross-market Recommendation
The proposed solution of our team WSDM_Coggle_ is selected as the second place submission.
Attention U-Net as a surrogate model for groundwater prediction
This manuscript presents an Attention U-Net model that attempts to capture the fundamental input-output relations of the groundwater system and generates solutions of hydraulic head in the whole domain given a set of physical parameters and boundary conditions.
Multi-Robot Active Mapping via Neural Bipartite Graph Matching
Previous approaches either choose the frontier as the goal position via a myopic solution that hinders the time efficiency, or maximize the long-term value via reinforcement learning to directly regress the goal position, but does not guarantee the complete map construction.
FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering
Inspired by the popular semi-supervised approach, FixMatch, we propose to leverage pseudo label filtering to facilitate the information flow from labeled data to unlabeled data in a teacher-student mutual learning framework.
iPLAN: Interactive and Procedural Layout Planning
However, the capability of involving humans into the loop has been largely ignored in existing methods which are mostly end-to-end approaches.
CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance
We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers.
Defending Black-box Skeleton-based Human Activity Classifiers
Our method is featured by full Bayesian treatments of the clean data, the adversaries and the classifier, leading to (1) a new Bayesian Energy-based formulation of robust discriminative classifiers, (2) a new adversary sampling scheme based on natural motion manifolds, and (3) a new post-train Bayesian strategy for black-box defense.
Region Proposal Rectification Towards Robust Instance Segmentation of Biological Images
Top-down instance segmentation framework has shown its superiority in object detection compared to the bottom-up framework.
Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrations
Generalizable object manipulation skills are critical for intelligent and multi-functional robots to work in real-world complex scenes.
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction.
PartAfford: Part-level Affordance Discovery from 3D Objects
We propose a novel learning framework for PartAfford, which discovers part-level representations by leveraging only the affordance set supervision and geometric primitive regularization, without dense supervision.
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques.
Fine-grained differentiable physics: a yarn-level model for fabrics
To this end, we propose several differentiable forces, whose counterparts in empirical physics are indifferentiable, to facilitate gradient-based learning.
ADeLA: Automatic Dense Labeling With Attention for Viewpoint Shift in Semantic Segmentation
We describe a method to deal with performance drop in semantic segmentation caused by viewpoint changes within multi-camera systems, where temporally paired images are readily available, but the annotations may only be abundant for a few typical views.
Domain Adaptation on Point Clouds via Geometry-Aware Implicits
Here we propose a simple yet effective method for unsupervised domain adaptation on point clouds by employing a self-supervised task of learning geometry-aware implicits, which plays two critical roles in one shot.
Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network
It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward.
Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimation
Category-level object pose estimation aims to find 6D object poses of previously unseen object instances from known categories without access to object CAD models.
Projective Manifold Gradient Layer for Deep Rotation Regression
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem.
Unsupervised Image Generation with Infinite Generative Adversarial Networks
Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision.
ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation
Furthermore, to resolve ambiguities in converting the semantic images to semantic labels, we treat the view transformation network as a functional representation of an unknown mapping implied by the color images and propose functional label hallucination to generate pseudo-labels in the target domain.
Survey of Image Based Graph Neural Networks
In this survey paper, we analyze image based graph neural networks and propose a three-step classification approach.
Leveraging SE(3) Equivariance for Self-supervised Category-Level Object Pose Estimation from Point Clouds
To reduce the huge amount of pose annotations needed for category-level learning, we propose for the first time a self-supervised learning framework to estimate category-level 6D object pose from single 3D point clouds.
Maneuver-Aware Pooling for Vehicle Trajectory Prediction
Behavior of each of the surrounding vehicles is governed by the motion of its neighbor vehicles.
Maneuver-based Anchor Trajectory Hypotheses at Roundabouts
Accordingly, our model employs a set of maneuver-specific anchor trajectories that cover the space of possible outcomes at the roundabout.
CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds
For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories.
Decentralized Statistical Inference with Unrolled Graph Neural Networks
In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination.
Data-Driven Optimization for Atlanta Police Zone Design
By analyzing data before and after the zone redesign, we show that the new design has reduced the response time to high priority 911 calls by 5. 8\% and the imbalance of police workload among different zones by 43\%.
BASAR:Black-box Attack on Skeletal Action Recognition
The robustness of skeleton-based activity recognizers has been questioned recently, which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker.
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far.
Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions
In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other forms of constraints can be incorporated into the attention framework for learning long-range dependencies for the task of pose estimation.
Ranked #5 on
3D Human Pose Estimation
on HumanEva-I
Distributed Optimization with Coupling Constraints
In this paper, we develop a novel distributed algorithm for addressing convex optimization with both nonlinear inequality and linear equality constraints, where the objective function can be a general nonsmooth convex function and all the constraints can be fully coupled.
Distributed Optimization
Optimization and Control
High-order Differentiable Autoencoder for Nonlinear Model Reduction
This paper provides a new avenue for exploiting deep neural networks to improve physics-based simulation.
In-game Residential Home Planning via Visual Context-aware Global Relation Learning
In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex.
MoDL-QSM: Model-based Deep Learning for Quantitative Susceptibility Mapping
However, there exists a mismatch between the observed phase and the theoretical forward phase estimated by the susceptibility label.
Systematic electrochemical etching of various metal tips for tunneling spectroscopy and scanning probe microscopy
To ensure the reproducibility of experimental results, the fabrication of tips should be standardized, and a controllable and convenient system should be set up.
Materials Science
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.
Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning
Inspired by the great success in recent contrastive learning works on self-supervised representation learning, we propose a novel IBSR pipeline leveraging contrastive learning.
Detection of magnetic gap in the topological surface states of MnBi2Te4
An essential ingredient to realize these quantum states is the magnetic gap in the topological surface states induced by the out-of-plane ferromagnetism on the surface of MnBi2Te4.
Materials Science
Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments
Localizing the camera in a known indoor environment is a key building block for scene mapping, robot navigation, AR, etc.
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
On KITTI, we are the first to demonstrate semi-supervised 3D object detection and our method surpasses a fully supervised baseline from 1. 8% to 7. 6% under different label ratios and categories.
IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
The former aims to recover the surface of point cloud through implicit function, while the latter encourages evenly-distributed points.
Constant Regret Re-solving Heuristics for Price-based Revenue Management
First, we prove that a natural re-solving heuristic attains $O(1)$ regret compared to the value of the optimal policy.
Dynamic Future Net: Diversified Human Motion Generation
We evaluate our model on a wide range of motions and compare it with the state-of-the-art methods.
Object-Centric Multi-View Aggregation
We present an approach for aggregating a sparse set of views of an object in order to compute a semi-implicit 3D representation in the form of a volumetric feature grid.
Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data
In particular, we present a novel training framework to jointly target both PU classification and conditional generation when exposing to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Conditional Generative Adversarial Network~(CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation.
Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks
We further study how different evaluation metrics weigh the sampling pattern against the geometry and propose several perceptual metrics forming a sampling spectrum of metrics.
Informative Scene Decomposition for Crowd Analysis, Comparison and Simulation Guidance
The method takes as input raw and noisy data with highly mixed multi-dimensional (space, time and dynamics) information, and automatically structure it by learning the correlations among these dimensions.
MeshingNet: A New Mesh Generation Method based on Deep Learning
The framework that we have developed is based around training an artificial neural network (ANN) to guide standard mesh generation software, based upon a prediction of the required local mesh density throughout the domain.
SAPIEN: A SimulAted Part-based Interactive ENvironment
To achieve this task, a simulated environment with physically realistic simulation, sufficient articulated objects, and transferability to the real robot is indispensable.
Curriculum DeepSDF
When learning to sketch, beginners start with simple and flexible shapes, and then gradually strive for more complex and accurate ones in the subsequent training sessions.
PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
3D generative shape modeling is a fundamental research area in computer vision and interactive computer graphics, with many real-world applications.
Human-like Planning for Reaching in Cluttered Environments
From this, we devised a qualitative representation of the task space to abstract the decision making, irrespective of the number of obstacles.
Predicting the Physical Dynamics of Unseen 3D Objects
Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.
Category-Level Articulated Object Pose Estimation
We develop a deep network based on PointNet++ that predicts ANCSH from a single depth point cloud, including part segmentation, normalized coordinates, and joint parameters in the canonical object space.
SMART: Skeletal Motion Action Recognition aTtack
In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions.
Gravitational wave signal recognition of O1 data by deep learning
Our adjusted convolutional neural network admits comparable accuracy and efficiency of signal recognition as other deep learning works published in the literature.
Instrumentation and Methods for Astrophysics General Relativity and Quantum Cosmology
Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
In this paper, we propose a new deep network to tackle these challenges by creating a natural motion manifold that is versatile for many applications.
Competing Against Equilibria in Zero-Sum Games with Evolving Payoffs
Finding the Nash Equilibrium (NE) of a two player zero-sum game is core to many problems in statistics, optimization, and economics, and for a fixed game matrix this can be easily reduced to solving a linear program.
Large Scale Markov Decision Processes with Changing Rewards
We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner.
DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark
Driver attention prediction is currently becoming the focus in safe driving research community, such as the DR(eye)VE project and newly emerged Berkeley DeepDrive Attention (BDD-A) database in critical situations.
Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image.
Ranked #2 on
6D Pose Estimation using RGBD
on CAMERA25
Learning Generalizable Physical Dynamics of 3D Rigid Objects
In this work, we focus on predicting the dynamics of 3D rigid objects, in particular an object's final resting position and total rotation when subjected to an impulsive force.
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data.
Ranked #17 on
3D Object Detection
on ScanNetV2
Globally Continuous and Non-Markovian Activity Analysis from Videos
By combining these patterns with detailed environment information, we interpret the semantics of activities and report anomalies.
Novelty Detection Meets Collider Physics
Complementary to supervised learning, it allows to analyze data model-independently.
The Online Saddle Point Problem and Online Convex Optimization with Knapsacks
We relate this problem to the online saddle point problem and establish $O(\sqrt{T})$ regret using a primal-dual algorithm.
Common Round: Application of Language Technologies to Large-Scale Web Debates
Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking.
“Congruent” and “Opposite” Neurons: Sisters for Multisensory Integration and Segregation
Mimicking the experimental protocol, our model reproduces the characteristics of congruent and opposite neurons, and demonstrates that in each module, the sisters of congruent and opposite neurons can jointly achieve optimal multisensory information integration and segregation.
Saliency Detection via Cellular Automata
In this paper, we introduce Cellular Automata--a dynamic evolution model to intuitively detect the salient object.
Attractor Dynamics with Synaptic Depression
Neuronal connection weights exhibit short-term depression (STD).
