Search Results for author:
Found 81 papers, 32 papers with code
Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition
Then, channel-dependent and temporal-dependent adjacency matrices corresponding to different channels and frames are calculated to capture the spatiotemporal dependencies between skeleton joints.
SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing
The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details.
How to Design Translation Prompts for ChatGPT: An Empirical Study
Machine translation relies heavily on the abilities of language understanding and generation.
Modeling of Interface Loads for EOD Suit Wearers
Explosive Ordnance Disposal (EOD) suits are widely used to protect human operators to execute emergency tasks such as bomb disposal and neutralization.
Financial Distress Prediction For Small And Medium Enterprises Using Machine Learning Techniques
As a result, there is a need to develop a productive prediction model for better order execution and adaptability to different datasets.
IMPORTANT-Net: Integrated MRI Multi-Parameter Reinforcement Fusion Generator with Attention Network for Synthesizing Absent Data
Then the multi-parameter fusion with attention module enables the interaction of the encoded information from different parameters through a set of algorithmic strategies, and applies different weights to the information through the attention mechanism after information fusion to obtain refined representation information.
Synthesis-based Imaging-Differentiation Representation Learning for Multi-Sequence 3D/4D MRI
Multi-sequence MRIs can be necessary for reliable diagnosis in clinical practice due to the complimentary information within sequences.
D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers
Second, the HKDL module can generate keypoint detectors in a hierarchical way, which is helpful for detecting keypoints with diverse levels of structures.
Wormhole MAML: Meta-Learning in Glued Parameter Space
In this paper, we introduce a novel variation of model-agnostic meta-learning, where an extra multiplicative parameter is introduced in the inner-loop adaptation.
1st Place Solution for YouTubeVOS Challenge 2022: Referring Video Object Segmentation
The task of referring video object segmentation aims to segment the object in the frames of a given video to which the referring expressions refer.
Referring Video Object Segmentation
Semantic Segmentation
+1
MFFN: Multi-view Feature Fusion Network for Camouflaged Object Detection
In addition, our MFFN exploits the dependence and interaction between views and channels.
Statistical Inference for Fisher Market Equilibrium
In resource allocation, it is crucial to quantify the variability of the resource received by the agents (such as blood banks and food banks) in addition to fairness and efficiency properties of the systems.
Progressive Self-Distillation for Ground-to-Aerial Perception Knowledge Transfer
In this paper, we introduce the ground-to-aerial perception knowledge transfer and propose a progressive semi-supervised learning framework that enables drone perception using only labeled data of ground viewpoint and unlabeled data of flying viewpoints.
Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
Such a strategy can generate the object boundaries in target domain (edge of target-domain object areas) with the correct labels.
Towards Autonomous Atlas-based Ultrasound Acquisitions in Presence of Articulated Motion
Robotic ultrasound (US) imaging aims at overcoming some of the limitations of free-hand US examinations, e. g. difficulty in guaranteeing intra- and inter-operator repeatability.
Learning to Coordinate for a Worker-Station Multi-robot System in Planar Coverage Tasks
In this paper, we focus on the multi-robot coverage path planning (mCPP) problem in large-scale planar areas with random dynamic interferers in the environment, where the robots have limited resources.
Composable Text Controls in Latent Space with ODEs
This paper proposes a new efficient approach for composable text operations in the compact latent space of text.
Ranked #2 on
Unsupervised Text Style Transfer
on Yelp
Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap
As a rising task, panoptic segmentation is faced with challenges in both semantic segmentation and instance segmentation.
VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation
The results demonstrate that proposed approach can effectively and accurately navigate the probe towards the longitudinal view of vessels.
Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering
With a multiscale sampling, RMI iterates the interaction of appearance-motion information at each scale and the question embeddings to build the multilevel question-guided visual representations.
Rumor Detection with Self-supervised Learning on Texts and Social Graph
At the core is to model the rumor characteristics inherent in rich information, such as propagation patterns in social network and semantic patterns in post content, and differentiate them from the truth.
Latent-Variable Advantage-Weighted Policy Optimization for Offline RL
Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions.
Bidding Agent Design in the LinkedIn Ad Marketplace
We establish a general optimization framework for the design of automated bidding agent in dynamic online marketplaces.
Finding Dynamics Preserving Adversarial Winning Tickets
Modern deep neural networks (DNNs) are vulnerable to adversarial attacks and adversarial training has been shown to be a promising method for improving the adversarial robustness of DNNs.
Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction
For this task, we observe that the overfitting is surprisingly severe between labeled and unlabeled frames within a training video although they are very similar in style and contents.
Robust Weakly Supervised Learning for COVID-19 Recognition Using Multi-Center CT Images
The multi-domain shift problem for the multi-center and multi-scanner studies is therefore nontrivial that is also crucial for a dependable recognition and critical for reproducible and objective diagnosis and prognosis.
Towards Panoptic 3D Parsing for Single Image in the Wild
Our proposed panoptic 3D parsing framework points to a promising direction in computer vision.
ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning
Inspired by the idea of dropout in neural networks, we introduce a network sampling strategy in the multi-party setting, which distributes different subnets of the central model to clients for updating, and the differentiable sampling rates allow each client to extract optimal local architecture from the supernet according to its private data distribution.
Abnormal Occupancy Grid Map Recognition using Attention Network
The occupancy grid map is a critical component of autonomous positioning and navigation in the mobile robotic system, as many other systems' performance depends heavily on it.
FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation
To better extract detail spatial information, we propose a two-stage Feature-Enhanced Attention Network (FEANet) for the RGB-T semantic segmentation task.
Ranked #8 on
Thermal Image Segmentation
on MFN Dataset
Relative Entropy Gradient Sampler for Unnormalized Distributions
We propose a relative entropy gradient sampler (REGS) for sampling from unnormalized distributions.
Temporal Pyramid Transformer with Multimodal Interaction for Video Question Answering
Targeting these issues, this paper proposes a novel Temporal Pyramid Transformer (TPT) model with multimodal interaction for VideoQA.
Learn2Agree: Fitting with Multiple Annotators without Objective Ground Truth
For such issues, we propose a novel Learning to Agreement (Learn2Agree) framework to tackle the challenge of learning from multiple annotators without objective ground truth.
A Dual Adversarial Calibration Framework for Automatic Fetal Brain Biometry
This paper presents a novel approach to automatic fetal brain biometry motivated by needs in low- and medium- income countries.
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
It simply encourages the variation of output caused by perturbations on different latent dimensions to be orthogonal, and the Jacobian with respect to the input is calculated to represent this variation.
1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition
In this technical report, we briefly introduce the solution of our team "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021.
Boosting Light-Weight Depth Estimation Via Knowledge Distillation
However, this KD process can be challenging and insufficient due to the large model capacity gap between the teacher and the student.
Multi-Party Dual Learning
The performance of machine learning algorithms heavily relies on the availability of a large amount of training data.
Towards Explainable Multi-Party Learning: A Contrastive Knowledge Sharing Framework
Since the existing naive model parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication, and analogy multi-party learning as a many-to-one knowledge sharing problem.
Principled Ultrasound Data Augmentation for Classification of Standard Planes
In this paper, we present an augmentation policy search method with the goal of improving model classification performance.
Significant Inverse Magnetocaloric Effect induced by Quantum Criticality
Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP.
Strongly Correlated Electrons
Factor-augmented Smoothing Model for Functional Data
We propose modeling raw functional data as a mixture of a smooth function and a highdimensional factor component.
Methodology Statistics Theory Statistics Theory
Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual Fusion
Video highlight detection plays an increasingly important role in social media content filtering, however, it remains highly challenging to develop automated video highlight detection methods because of the lack of temporal annotations (i. e., where the highlight moments are in long videos) for supervised learning.
Exploiting Learnable Joint Groups for Hand Pose Estimation
This is different from the previous methods where all the joints are considered holistically and share the same feature.
Generative Learning With Euler Particle Transport
The key task in training is the estimation of the density ratios or differences that determine the residual maps.
Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
Protective behavior exhibited by people with chronic pain (CP) during physical activities is the key to understanding their physical and emotional states.
Partial FC: Training 10 Million Identities on a Single Machine
The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks.
Ranked #2 on
Face Identification
on MegaFace
WeChat Neural Machine Translation Systems for WMT20
We participate in the WMT 2020 shared news translation task on Chinese to English.
Recognizing Micro-Expression in Video Clip with Adaptive Key-Frame Mining
As a spontaneous expression of emotion on face, micro-expression reveals the underlying emotion that cannot be controlled by human.
CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and possibly incomplete, which restricts its use for a high-quality surface recovery.
PP-YOLO: An Effective and Efficient Implementation of Object Detector
We mainly try to combine various existing tricks that almost not increase the number of model parameters and FLOPs, to achieve the goal of improving the accuracy of detector as much as possible while ensuring that the speed is almost unchanged.
Ranked #136 on
Object Detection
on COCO test-dev
Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement
In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled.
An Improved Analysis of Stochastic Gradient Descent with Momentum
Furthermore, the role of dynamic parameters has not been addressed.
Optimization and Control
Data-driven Efficient Solvers for Langevin Dynamics on Manifold in High Dimensions
To construct an efficient and stable approximation for the Langevin dynamics on $\mathcal{N}$, we leverage the corresponding Fokker-Planck equation on the manifold $\mathcal{N}$ in terms of the reaction coordinates $\mathsf{y}$.
Weakly Supervised Deep Learning for COVID-19 Infection Detection and Classification from CT Images
An outbreak of a novel coronavirus disease (i. e., COVID-19) has been recorded in Wuhan, China since late December 2019, which subsequently became pandemic around the world.
MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL).
Stochastic Flows and Geometric Optimization on the Orthogonal Group
We present a new class of stochastic, geometrically-driven optimization algorithms on the orthogonal group $O(d)$ and naturally reductive homogeneous manifolds obtained from the action of the rotation group $SO(d)$.
Self-Supervised Light Field Reconstruction Using Shearlet Transform and Cycle Consistency
Specifically, CycleST is composed of an encoder-decoder network and a residual learning strategy that restore the shearlet coefficients of densely-sampled EPIs using EPI reconstruction and cycle consistency losses.
Signal Processing Multimedia Image and Video Processing
DRST: Deep Residual Shearlet Transform for Densely Sampled Light Field Reconstruction
Specifically, for an input sparsely-sampled EPI, DRST employs a deep fully Convolutional Neural Network (CNN) to predict the residuals of the shearlet coefficients in shearlet domain in order to reconstruct a densely-sampled EPI in image domain.
Application of Deep Q-Network in Portfolio Management
This paper will introduce a strategy based on the classic Deep Reinforcement Learning algorithm, Deep Q-Network, for portfolio management in stock market.
Learning Implicit Generative Models with Theoretical Guarantees
We then solve the McKean-Vlasov equation numerically using the forward Euler iteration, where the forward Euler map depends on the density ratio (density difference) between the distribution at current iteration and the underlying target distribution.
Automated Testing for Deep Learning Systems with Differential Behavior Criteria
By observing differential behaviors from three pre-trained models during each testing iteration, the input image that triggered erroneous feedback was registered as a corner-case.
OpenArray v1.0: a simple operator library for the decoupling of ocean modeling and parallel computing
In this work, we design a simple computing library to bridge the gap and decouple the work of ocean modeling from parallel computing.
Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations
Our dataset consists of amino acid sequences, Q8 secondary structures, position specific scoring matrices, multiple sequence alignment co-evolutionary features, backbone atom distance matrices, torsion angles, and 3D coordinates.
Skew-Explore: Learn faster in continuous spaces with sparse rewards
In this work, we introduce an exploration approach based on maximizing the entropy of the visited states while learning a goal-conditioned policy.
Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction
In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction.
Intra-Ensemble in Neural Networks
In this work, we propose Intra-Ensemble, an end-to-end ensemble strategy with stochastic channel recombination operations to train several sub-networks simultaneously within one neural network.
Increasing Iterate Averaging for Solving Saddle-Point Problems
In particular, the increasing averages consistently outperform the uniform averages in all test problems by orders of magnitude.
Wasserstein-Wasserstein Auto-Encoders
To address the challenges in learning deep generative models (e. g., the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we propose a novel deep generative model, named Wasserstein-Wasserstein auto-encoders (WWAE).
Deep Generative Learning via Variational Gradient Flow
We propose a general framework to learn deep generative models via \textbf{V}ariational \textbf{Gr}adient Fl\textbf{ow} (VGrow) on probability spaces.
Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning
Deep reinforcement learning has recently been widely applied in robotics to study tasks such as locomotion and grasping, but its application to social human-robot interaction (HRI) remains a challenge.
Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance
This report demonstrates our solution for the Open Images 2018 Challenge.
Unity: A General Platform for Intelligent Agents
Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments.
NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction
In this paper, we propose a novel Convolutional Neural Network (CNN) structure for general-purpose multi-task learning (MTL), which enables automatic feature fusing at every layer from different tasks.
Ranked #53 on
Semantic Segmentation
on NYU Depth v2
Multi-Glimpse LSTM with Color-Depth Feature Fusion for Human Detection
In this paper, we propose a new Multi-Glimpse LSTM (MG-LSTM) network, in which multi-scale contextual information is sequentially integrated to promote the human detection performance.
Spoken English Intelligibility Remediation with PocketSphinx Alignment and Feature Extraction Improves Substantially over the State of the Art
We use automatic speech recognition to assess spoken English learner pronunciation based on the authentic intelligibility of the learners' spoken responses determined from support vector machine (SVM) classifier or deep learning neural network model predictions of transcription correctness.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Convex Geometry of the Generalized Matrix-Fractional Function
Generalized matrix-fractional (GMF) functions are a class of matrix support functions introduced by Burke and Hoheisel as a tool for unifying a range of seemingly divergent matrix optimization problems associated with inverse problems, regularization and learning.
Symmetric Non-Rigid Structure from Motion for Category-Specific Object Structure Estimation
This paper addresses the estimation of 3D structures of symmetric objects from multiple images of the same object category, e. g. different cars, seen from various viewpoints.
Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples
This is based on recent work on sparsity where faces are represented in terms of two dictionaries: a gallery dictionary consisting of one or more examples of each person, and a variation dictionary representing linear nuisance variables (e. g., different lighting conditions, different glasses).
Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation from Single and Multiple Images
By assuming an orthographic projection model, this paper addresses the estimation of 3D structures and camera projection using symmetry and/or Manhattan structure cues, which occur when the input is single- or multiple-image from the same category, e. g., multiple different cars.
Deep Gate Recurrent Neural Network
This paper introduces two recurrent neural network structures called Simple Gated Unit (SGU) and Deep Simple Gated Unit (DSGU), which are general structures for learning long term dependencies.
