Search Results for author:
Found 101 papers, 26 papers with code
Learn From Neighbour: A Curriculum That Train Low Weighted Samples By Imitating
Training hard examples aggravates the distribution shifting and damages the training.
3D Human Mesh Estimation from Virtual Markers
The advanced motion capture systems solve the problem by placing dense physical markers on the body surface, which allows to extract realistic meshes from their non-rigid motions.
Ranked #3 on
3D Human Pose Estimation
on 3DPW
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.
Proactive Multi-Camera Collaboration For 3D Human Pose Estimation
This paper presents a multi-agent reinforcement learning (MARL) scheme for proactive Multi-Camera Collaboration in 3D Human Pose Estimation in dynamic human crowds.
UniHCP: A Unified Model for Human-Centric Perceptions
When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e. g., 69. 8 mIoU on CIHP for human parsing, 86. 18 mA on PA-100K for attribute prediction, 90. 3 mAP on Market1501 for ReID, and 85. 8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.
Saliency Guided Contrastive Learning on Scene Images
Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images.
Towards Explainable Visual Anomaly Detection
Anomaly detection and localization of visual data, including images and videos, are of great significance in both machine learning academia and applied real-world scenarios.
Making Reconstruction-based Method Great Again for Video Anomaly Detection
With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction.
GFPose: Learning 3D Human Pose Prior with Gradient Fields
During the denoising process, GFPose implicitly incorporates pose priors in gradients and unifies various discriminative and generative tasks in an elegant framework.
Ranked #1 on
Monocular 3D Human Pose Estimation
on Human3.6M
MotionBERT: Unified Pretraining for Human Motion Analysis
We present MotionBERT, a unified pretraining framework, to tackle different sub-tasks of human motion analysis including 3D pose estimation, skeleton-based action recognition, and mesh recovery.
Ranked #1 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement
As an important upstream task for many medical applications, supervised landmark localization still requires non-negligible annotation costs to achieve desirable performance.
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes.
Ranked #6 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked.
3D Multi-Person Pose Estimation (absolute)
3D Pose Estimation
GaitTAKE: Gait Recognition by Temporal Attention and Keypoint-guided Embedding
Gait recognition, which refers to the recognition or identification of a person based on their body shape and walking styles, derived from video data captured from a distance, is widely used in crime prevention, forensic identification, and social security.
Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains
While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain.
Domain Invariant Model with Graph Convolutional Network for Mammogram Classification
To resolve this problem, we propose a novel framework, namely Domain Invariant Model with Graph Convolutional Network (DIM-GCN), which only exploits invariant disease-related features from multiple domains.
Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition
Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects.
EventFormer: AU Event Transformer for Facial Action Unit Event Detection
Facial action units (AUs) play an indispensable role in human emotion analysis.
Adaptive Trajectory Prediction via Transferable GNN
To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for practical pedestrian trajectory prediction across different domains.
GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning
we formulate the dynamic grasping problem as a 'move-and-grasp' game, where the robot is to pick up the object on the mover and the adversarial mover is to find a path to escape it.
MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks
Trained with the canonicalization operations and the derived regularizations, our method learns to factorize a skeleton sequence into three independent semantic subspaces, i. e., motion, structure, and view angle.
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
The pretrain-finetune paradigm is a classical pipeline in visual learning.
SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
Next we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features.
ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind
With ToM, each agent is capable of inferring the mental states and intentions of others according to its (local) observation.
Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
In this paper, we propose a symmetry enhanced attention network (SEAN) for acute ischemic infarct segmentation.
Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition
Finally, to implement this contextual posterior, we introduce a Transformer that takes the object's information as a reference and locates correlated contextual factors.
Improving the Transferability of Supervised Pretraining with an MLP Projector
The pretrain-finetune paradigm is a classical pipeline in visual learning.
MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning
In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning.
ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot
One-stage long-tailed recognition methods improve the overall performance in a "seesaw" manner, i. e., either sacrifice the head's accuracy for better tail classification or elevate the head's accuracy even higher but ignore the tail.
Ranked #7 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Which Invariance Should We Transfer? A Causal Minimax Learning Approach
When this condition fails, we surprisingly find with an example that this whole stable set, although can fully exploit stable information, is not the optimal one to transfer.
Rethinking Adam: A Twofold Exponential Moving Average Approach
The intuition is that gradient with momentum contains more accurate directional information and therefore its second moment estimation is a more favorable option for learning rate scaling than that of the raw gradient.
Towards Distraction-Robust Active Visual Tracking
In active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance.
Towards Unified Surgical Skill Assessment
In this paper, a unified multi-path framework for automatic surgical skill assessment is proposed, which takes care of multiple composing aspects of surgical skills, including surgical tool usage, intraoperative event pattern, and other skill proxies.
Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection
In this paper, we propose an Anatomy-aware Graph convolutional Network (AGN), which is tailored for mammogram mass detection and endows existing detection methods with multi-view reasoning ability.
Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment
Radar has long been a common sensor on autonomous vehicles for obstacle ranging and speed estimation.
Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking
To address such common challenges in most of the existing trackers, in this paper, a tracklet booster algorithm is proposed, which can be built upon any other tracker.
Multi-Target Multi-Camera Tracking of Vehicles using Metadata-Aided Re-ID and Trajectory-Based Camera Link Model
In this paper, we propose a novel framework for multi-target multi-camera tracking (MTMCT) of vehicles based on metadata-aided re-identification (MA-ReID) and the trajectory-based camera link model (TCLM).
Causal Hidden Markov Model for Time Series Disease Forecasting
We propose a causal hidden Markov model to achieve robust prediction of irreversible disease at an early stage, which is safety-critical and vital for medical treatment in early stages.
Context Modeling in 3D Human Pose Estimation: A Unified Perspective
By comparing the two methods, we found that the end-to-end training scheme in GNN and the limb length constraints in PSM are two complementary factors to improve results.
Ranked #41 on
3D Human Pose Estimation
on MPI-INF-3DHP
RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization
Finally, we propose a method to evaluate the object detection performance of the RODNet.
Forecasting Irreversible Disease via Progression Learning
In order to account for the degree of progression of the disease, we propose a temporal generative model to accurately generate the future image and compare it with the current one to get a residual image.
Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices
We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3. 48% absolute improvement in the sensitivity of FPs@0. 5), significantly surpassing the baseline method by up to 6. 06% (in MAP@0. 5) which adopts 2D convolution for 3D context modeling.
Ranked #4 on
Medical Object Detection
on DeepLesion
An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation
The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for images under different augmentations.
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks
Maximum target coverage by adjusting the orientation of distributed sensors is an important problem in directional sensor networks (DSNs).
Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification
Mammogram benign or malignant classification with only image-level labels is challenging due to the absence of lesion annotations.
Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusion
In the experiments on the binary instrument segmentation task of the 2017 MICCAI EndoVis Robotic Instrument Segmentation Challenge dataset, the proposed method achieves 0. 71 IoU and 0. 81 Dice score without using a single manual annotation, which is promising to show the potential of unsupervised learning for surgical tool segmentation.
Surgical Skill Assessment on In-Vivo Clinical Data via the Clearness of Operating Field
Then an objective and automated framework based on neural network is proposed to predict surgical skills through the proxy of COF.
Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model
In this paper, we propose an effective and reliable MTMCT framework for vehicles, which consists of a traffic-aware single camera tracking (TSCT) algorithm, a trajectory-based camera link model (CLM) for vehicle re-identification (ReID), and a hierarchical clustering algorithm to obtain the cross camera vehicle trajectories.
Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space
Specifically, with a variable the splitting term, two estimators are introduced and split apart, i. e. one is for feature selection (the sparse estimator) and the other is for prediction (the dense estimator).
Augmented Bi-path Network for Few-shot Learning
Finally, the model learns to compare global and local features separately, i. e., in two paths, before merging the similarities.
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
In this paper, we propose a novel information-theoretic approach, namely \textbf{T}otal \textbf{C}orrelation \textbf{G}ain \textbf{M}aximization (TCGM), for semi-supervised multi-modal learning, which is endowed with promising properties: (i) it can utilize effectively the information across different modalities of unlabeled data points to facilitate training classifiers of each modality (ii) it has theoretical guarantee to identify Bayesian classifiers, i. e., the ground truth posteriors of all modalities.
Context-Aware Refinement Network Incorporating Structural Connectivity Prior for Brain Midline Delineation
Nevertheless, there are still great challenges with brain midline delineation, such as the largely deformed midline caused by the mass effect and the possible morphological failure that the predicted midline is not a connected curve.
IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency
Meanwhile, the spatial attention, which focuses on the foreground within the bounding boxes, is generated from the given instance masks and applied to the extracted embedding features.
MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation
Cross view feature fusion is the key to address the occlusion problem in human pose estimation.
RODNet: Radar Object Detection Using Cross-Modal Supervision
Radar is usually more robust than the camera in severe driving scenarios, e. g., weak/strong lighting and bad weather.
Segmentation-based Method combined with Dynamic Programming for Brain Midline Delineation
The midline related pathological image features are crucial for evaluating the severity of brain compression caused by stroke or traumatic brain injury (TBI).
Self-Directed Online Machine Learning for Topology Optimization
A small number of training data is generated dynamically based on the DNN's prediction of the optimum.
A Generative Adversarial Network for AI-Aided Chair Design
We present a method for improving human design of chairs.
Pose-Assisted Multi-Camera Collaboration for Active Object Tracking
In the system, each camera is equipped with two controllers and a switcher: The vision-based controller tracks targets based on observed images.
On Computation and Generalization of Generative Adversarial Imitation Learning
Generative Adversarial Imitation Learning (GAIL) is a powerful and practical approach for learning sequential decision-making policies.
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
To the best of our knowledge, L_DMI is the first loss function that is provably robust to instance-independent label noise, regardless of noise pattern, and it can be applied to any existing classification neural networks straightforwardly without any auxiliary information.
Ranked #33 on
Image Classification
on Clothing1M
(using extra training data)
MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors.
Ranked #8 on
Medical Object Detection
on DeepLesion
L_DMI: An Information-theoretic Noise-robust Loss Function
\emph{To the best of our knowledge, $\mathcal{L}_{DMI}$ is the first loss function that is provably robust to instance-independent label noise, regardless of noise pattern, and it can be applied to any existing classification neural networks straightforwardly without any auxiliary information}.
Ranked #33 on
Image Classification
on Clothing1M
Multi-level Domain Adaptive learning for Cross-Domain Detection
In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment.
Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds
Furthermore, we devise an accurate data-crowds forecaster that employs both the data and the crowdsourced labels to forecast the ground truth.
SSoC: Learning Spontaneous and Self-Organizing Communication for Multi-Agent Collaboration
By treating the communication behaviour as an explicit action, SSoC learns to organize communication in an effective and efficient way.
AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active Tracking
In AD-VAT, both the tracker and the target are approximated by end-to-end neural networks, and are trained via RL in a dueling/competitive manner: i. e., the tracker intends to lockup the target, while the target tries to escape from the tracker.
$S^{2}$-LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning
This paper proposes a novel Stochastic Split Linearized Bregman Iteration ($S^{2}$-LBI) algorithm to efficiently train the deep network.
Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
Specifically, the model encodes multiple agents' past trajectories and the scene context into a Multi-Agent Tensor, then applies convolutional fusion to capture multiagent interactions while retaining the spatial structure of agents and the scene context.
Efficient Model-Free Reinforcement Learning Using Gaussian Process
Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy.
CRAVES: Controlling Robotic Arm with a Vision-based Economic System
We also construct a vision-based control system for task accomplishment, for which we train a reinforcement learning agent in a virtual environment and apply it to the real-world.
Exploit the Connectivity: Multi-Object Tracking with TrackletNet
Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision.
Ranked #19 on
Multi-Object Tracking
on MOT16
HAPPIER: Hierarchical Polyphonic Music Generative RNN
Generating polyphonic music with coherent global structure is a major challenge for automatic composition algorithms.
Video Object Segmentation by Learning Location-Sensitive Embeddings
We address the problem of video object segmentation which outputs the masks of a target object throughout a video given only a bounding box in the first frame.
End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning
We further propose an environment augmentation technique and a customized reward function, which are crucial for successful training.
Integrating Feature and Image Pyramid: A Lung Nodule Detector Learned in Curriculum Fashion
Meanwhile, our sampling strategy halves the training time of the proposal network on LUNA16.
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
To solve this task, $L_{1}$ regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in $L_{1}$ regularization may cause the underfitting of training data.
A Large-scale Attribute Dataset for Zero-shot Learning
In classical ZSL algorithms, attributes are introduced as the intermediate semantic representation to realize the knowledge transfer from seen classes to unseen classes.
Joint Learning for Pulmonary Nodule Segmentation, Attributes and Malignancy Prediction
Refer to the literature of lung nodule classification, many studies adopt Convolutional Neural Networks (CNN) to directly predict the malignancy of lung nodules with original thoracic Computed Tomography (CT) and nodule location.
Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning
Many tasks in artificial intelligence require the collaboration of multiple agents.
RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
The evaluator predicts perceptual score by extracting feature representations from the distorted and restored patches to measure GoR.
Zero-shot Learning via Shared-Reconstruction-Graph Pursuit
With the learned SRG, each unseen class prototype (cluster center) in the image feature space can be synthesized by the linear combination of other class prototypes, so that testing instances can be classified based on the distance to these synthesized prototypes.
AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
Significant progress has been achieved in Computer Vision by leveraging large-scale image datasets.
End-to-end Active Object Tracking via Reinforcement Learning
We study active object tracking, where a tracker takes as input the visual observation (i. e., frame sequence) and produces the camera control signal (e. g., move forward, turn left, etc.).
Collaborative Deep Reinforcement Learning for Joint Object Search
We examine the problem of joint top-down active search of multiple objects under interaction, e. g., person riding a bicycle, cups held by the table, etc..
An Attention-Driven Approach of No-Reference Image Quality Assessment
The model learning is implemented by a reinforcement strategy, in which the rewards of both tasks guide the learning of the optimal sampling policy to acquire the "task-informative" image regions so that the predictions can be made accurately and efficiently (in terms of the sampling steps).
Multi-Task Learning
No-Reference Image Quality Assessment
+1
Zero-Shot Learning posed as a Missing Data Problem
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem.
Face Detection with End-to-End Integration of a ConvNet and a 3D Model
The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e. g., faster R-CNN) for face detection: (i) One is to eliminate the heuristic design of prede- fined anchor boxes in the region proposals network (RPN) by exploit- ing a 3D mean face model.
Ranked #7 on
Face Detection
on Annotated Faces in the Wild
Mining 3D Key-Pose-Motifs for Action Recognition
Recognizing an action from a sequence of 3D skeletal poses is a challenging task.
Maximal Sparsity with Deep Networks?
The iterations of many sparse estimation algorithms are comprised of a fixed linear filter cascaded with a thresholding nonlinearity, which collectively resemble a typical neural network layer.
A Novel Method to Study Bottom-up Visual Saliency and its Neural Mechanism
In this study, we propose a novel method to measure bottom-up saliency maps of natural images.
Exploiting Object Similarity in 3D Reconstruction
Despite recent progress, reconstructing outdoor scenes in 3D from movable platforms remains a highly difficult endeavour.
Background Subtraction via Generalized Fused Lasso Foreground Modeling
Background Subtraction (BS) is one of the key steps in video analysis.
Stable Feature Selection from Brain sMRI
Neuroimage analysis usually involves learning thousands or even millions of variables using only a limited number of samples.
Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels
In this paper, we propose a more principled way to identify annotation outliers by formulating the subjective visual property prediction task as a unified robust learning to rank problem, tackling both the outlier detection and learning to rank jointly.
Representing Data by a Mixture of Activated Simplices
We show that under this restriction, building a model with simplices amounts to constructing a convex hull inside the sphere whose boundary facets is close to the data.
Predictive Encoding of Contextual Relationships for Perceptual Inference, Interpolation and Prediction
We propose a new neurally-inspired model that can learn to encode the global relationship context of visual events across time and space and to use the contextual information to modulate the analysis by synthesis process in a predictive coding framework.
Robust Estimation of 3D Human Poses from a Single Image
We address the challenges in three ways: (i) We represent a 3D pose as a linear combination of a sparse set of bases learned from 3D human skeletons.
Ranked #25 on
3D Human Pose Estimation
on HumanEva-I
What Object Motion Reveals about Shape with Unknown BRDF and Lighting
Under orthographic projection, we prove that three differential motions suffice to yield an invariant that relates shape to image derivatives, regardless of BRDF and illumination.
Weakly Supervised Learning for Attribute Localization in Outdoor Scenes
We evaluate the proposed method by (i) showing the improvement of attribute recognition accuracy; and (ii) comparing the average precision of localizing attributes to the scene parts.
An Approach to Pose-Based Action Recognition
We start by improving a state of the art method for estimating human joint locations from videos.
