Search Results for author:
Found 48 papers, 21 papers with code
SeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape Estimation
In this paper, we attempt to not only consider the appearance of a hand but incorporate the temporal movement information of a hand in motion into the learning framework for better 3D hand pose estimation performance, which leads to the necessity of a large scale dataset with sequential RGB hand images.
Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective Adaptation
Medical image segmentation poses challenges due to domain gaps, data modality variations, and dependency on domain knowledge or experts, especially for low- and middle-income countries (LMICs).
NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model
Given a language description of the hand and contact, NL2Contact generates realistic and faithful 3D hand-object contacts.
TextGaze: Gaze-Controllable Face Generation with Natural Language
Our work first introduces a text-of-gaze dataset containing over 90k text descriptions spanning a dense distribution of gaze and head poses.
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation.
What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation
GazeDPTR shows state-of-the-art performance on the IVGaze dataset.
MoST: Motion Style Transformer between Diverse Action Contents
While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents.
NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interaction
Despite remarkable progress that has been achieved in this field, existing methods still fail to synthesize the hand-object interaction photo-realistically, suffering from degraded rendering quality caused by the heavy mutual occlusions between the hand and the object, and inaccurate hand-object pose estimation.
Multi-Modal Gaze Following in Conversational Scenarios
We then use the identity information to enhance scene images and propose a gaze candidate estimation network.
BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation
Our new instance embedding loss provides a learning signal on the entire area of the image with bounding box annotations, achieving globally consistent and disentangled instance representation.
Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images
We propose a novel transformer-based framework that reconstructs two high fidelity hands from multi-view RGB images.
Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation
With the rapid development of deep learning technology in the past decade, appearance-based gaze estimation has attracted great attention from both computer vision and human-computer interaction research communities.
High-Fidelity Eye Animatable Neural Radiance Fields for Human Face
In this paper, we aim to learn a face NeRF model that is sensitive to eye movements from multi-view images.
DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation
However, extending such models to multi-frame human pose estimation is non-trivial due to the presence of the additional temporal dimension in videos.
Clothes Grasping and Unfolding Based on RGB-D Semantic Segmentation
These methods often utilize physics engines to synthesize depth images to reduce the cost of real labeled data collection.
HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation
In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation.
Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video
On the other hand, the temporal difference has the ability to encode representative motion information which can potentially be valuable for pose estimation but has not been fully exploited.
Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation
The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task.
GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields
We propose GazeNeRF, a 3D-aware method for the task of gaze redirection.
S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning
In this paper, we propose a novel semi-supervised framework that allows us to learn contact from monocular images.
Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning
To tackle the learning of whole-body motion, long-range temporal dynamics, and person-to-person interactions, we design a global and local attention mechanism, where, global body motions and local joint motions pay attention to each other.
Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution
Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality.
Ranked #6 on
hand-object pose
on DexYCB
Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping
We propose a novel optimization framework that crops a given image based on user description and aesthetics.
Contrastive Vicinal Space for Unsupervised Domain Adaptation
In the contrastive space, inter-domain discrepancy is mitigated by constraining instances to have contrastive views and labels, and the consensus space reduces the confusion between intra-domain categories.
Ranked #1 on
Unsupervised Domain Adaptation
on PACS
Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration
Recent developments in stochastic approaches based on deep learning have achieved sub-second runtimes for DiffIR with competitive registration accuracy, offering a fast alternative to conventional iterative methods.
Learning a Model-Driven Variational Network for Deformable Image Registration
We then propose two neural layers (i. e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i. e. generalized denoising layer).
Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders
Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored.
FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image.
Ranked #7 on
6D Pose Estimation using RGBD
on REAL275
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
However, most of the studies were based on direct adaptation from the source domain to the target domain and have suffered from large domain discrepancies.
Ranked #8 on
Domain Adaptation
on Office-31
Combining Task Predictors via Enhancing Joint Predictability
Predictor combination aims to improve a (target) predictor of a learning task based on the (reference) predictors of potentially relevant tasks, without having access to the internals of individual predictors.
SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation
In this paper, we attempt to not only consider the appearance of a hand but incorporate the temporal movement information of a hand in motion into the learning framework for better 3D hand pose estimation performance, which leads to the necessity of a large scale dataset with sequential RGB hand images.
Class-Attentive Diffusion Network for Semi-Supervised Classification
In contrast to the existing diffusion methods with a transition matrix determined solely by the graph structure, CAD considers both the node features and the graph structure with the design of our class-attentive transition matrix that utilizes a classifier.
Implications of Human Irrationality for Reinforcement Learning
Recent work in the behavioural sciences has begun to overturn the long-held belief that human decision making is irrational, suboptimal and subject to biases.
VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning
We show that our method can be applied to classification tasks on multiple different datasets -- including one that is a real-world dataset with heavy data imbalance -- significantly outperforming the state of the art.
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation.
Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video
We propose a self-supervised visual learning method by predicting the variable playback speeds of a video.
Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
(iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework.
Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture.
Joint Manifold Diffusion for Combining Predictions on Decoupled Observations
We present a new predictor combination algorithm that improves a given task predictor based on potentially relevant reference predictors.
RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments
We first record a novel dataset of varied gaze and head pose images in a natural environment, addressing the issue of ground truth annotation by measuring head pose using a motion capture system and eye gaze using mobile eyetracking glasses.
Ranked #1 on
Gaze Estimation
on RT-GENE
Context-aware Deep Feature Compression for High-speed Visual Tracking
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.
Ranked #15 on
Visual Object Tracking
on VOT2017/18
Attentional Correlation Filter Network for Adaptive Visual Tracking
We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency.
DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self
This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot.
MAGAN: Margin Adaptation for Generative Adversarial Networks
We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function.
Visual Tracking Using Attention-Modulated Disintegration and Integration
In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types.
Kinematic Structure Correspondences via Hypergraph Matching
In this paper, we present a novel framework for finding the kinematic structure correspondence between two objects in videos via hypergraph matching.
Unsupervised Learning of Complex Articulated Kinematic Structures Combining Motion and Skeleton Information
The iterative merge process is guided by a skeleton distance function which is generated from a novel object boundary generation method from sparse points.
Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture
In contrast to prior forest-based methods, which take dense pixels as input, classify them independently and then estimate joint positions afterwards; our method can be considered as a structured coarse-to-fine search, starting from the centre of mass of a point cloud until locating all the skeletal joints.
