Search Results for author:
Found 104 papers, 51 papers with code
Improving Embedding-based Large-scale Retrieval via Label Enhancement
Current embedding-based large-scale retrieval models are trained with 0-1 hard label that indicates whether a query is relevant to a document, ignoring rich information of the relevance degree.
Pseudo MIMO (pMIMO): An Energy and Spectral Efficient MIMO-OFDM System
The proposed system architecture and the dedicated signal processing methods enable the scheme to transmit a bigger number of parallel data streams than the number of receiving RF chains, achieving a spectral efficiency performance close to that of a fully digital (FD) MIMO system with the same number of antenna elements, each equipped with an RF chain.
Generative Nowcasting of Marine Fog Visibility in the Grand Banks area and Sable Island in Canada
Generative nowcasting of Vis time series for lead times of 30 and 60 minutes were performed using conditional generative adversarial networks (cGAN) regression at visibility thresholds of Vis < 1 km and < 10 km.
Real-Time Systems Optimization with Black-box Constraints and Hybrid Variables
When optimizing real-time systems, designers often face a challenging problem where the schedulability constraints are non-convex, non-continuous, or lack an analytical form to understand their properties.
A General and Scalable Method for Optimizing Real-Time Systems
In real-time systems optimization, designers often face a challenging problem posed by the non-convex and non-continuous schedulability conditions, which may even lack an analytical form to understand their properties.
Scout-Net: Prospective Personalized Estimation of CT Organ Doses from Scout Views
To optimize CT acquisitions before scanning, rapid prediction of patient-specific organ dose is needed prospectively, using available scout images.
MoMask: Generative Masked Modeling of 3D Human Motions
For the base-layer motion tokens, a Masked Transformer is designated to predict randomly masked motion tokens conditioned on text input at training stage.
Ranked #1 on
Motion Synthesis
on HumanML3D
VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis
Creating high-quality view synthesis is essential for immersive applications but continues to be problematic, particularly in indoor environments and for real-time deployment.
GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands.
Ranked #185 on
Image Classification
on ImageNet
In Search of Lost Online Test-time Adaptation: A Survey
In this paper, we present a comprehensive survey on online test-time adaptation (OTTA), a paradigm focused on adapting machine learning models to novel data distributions upon batch arrival.
Optimizing Logical Execution Time Model for Both Determinism and Low Latency
Therefore, fLET has the potential to significantly improve the end-to-end timing performance while keeping the benefits of deterministic behavior on timing and dataflow.
Understanding the Effects of Projectors in Knowledge Distillation
Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance.
MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient
Monocular 3D object detection is an inherently ill-posed problem, as it is challenging to predict accurate 3D localization from a single image.
Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers
Inspired by the channel shuffle design in ShuffleNetV2 \cite{ma2018shufflenet}, our module expands the feature channels of a tiny ViT and partitions the channels into two groups: the \textit{Attended} and \textit{Idle} groups.
No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages.
HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fields
For global consistency, we propose an efficient Sim(3)-based pose graph bundle adjustment (PGBA) approach to run online loop closing and mitigate the pose and scale drift.
Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection
The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process.
Enhancing AUV Autonomy With Model Predictive Path Integral Control
However, in order to ensure that the AUV is able to carry out its mission successfully, a control system capable of adapting to changing environmental conditions is required.
Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error
The prevalence of domain adaptive semantic segmentation has prompted concerns regarding source domain data leakage, where private information from the source domain could inadvertently be exposed in the target domain.
Zero-Shot Learning by Harnessing Adversarial Samples
To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS).
Event-based Human Pose Tracking by Spiking Spatiotemporal Transformer
Motivated by the above mentioned issues, we present in this paper a dedicated end-to-end sparse deep learning approach for event-based pose tracking: 1) to our knowledge this is the first time that 3D human pose tracking is obtained from events only, thus eliminating the need of accessing to any frame-based images as part of input; 2) our approach is based entirely upon the framework of Spiking Neural Networks (SNNs), which consists of Spike-Element-Wise (SEW) ResNet and a novel Spiking Spatiotemporal Transformer; 3) a large-scale synthetic dataset is constructed that features a broad and diverse set of annotated 3D human motions, as well as longer hours of event stream data, named SynEventHPD.
DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets
However, due to the sparse characteristics of point clouds, it is non-trivial to apply a standard transformer on sparse points.
Ranked #1 on
3D Object Detection
on nuScenes LiDAR only
Improved Feature Distillation via Projector Ensemble
Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features.
Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems
Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS).
Federated Zero-Shot Learning for Visual Recognition
We identify two key challenges in our FedZSL protocol: 1) the trained models are prone to be biased to the locally observed classes, thus failing to generalize to the unseen classes and/or seen classes appeared on other devices; 2) as each category in the training data comes from a single source, the central model is highly vulnerable to model replacement (backdoor) attacks.
Boosting Night-time Scene Parsing with Learnable Frequency
Based on this, we propose to exploit the image frequency distributions for night-time scene parsing.
Two Heads are Better than One: Robust Learning Meets Multi-branch Models
Compared to all methods that do not use additional data for training, our models achieve 67. 3% and 41. 5% robust accuracy on CIFAR-10 and CIFAR-100 (improving upon the state-of-the-art by +7. 23% and +9. 07%).
Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptation
A typical multi-source domain adaptation (MSDA) approach aims to transfer knowledge learned from a set of labeled source domains, to an unlabeled target domain.
GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning
To address this issue, we propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
Our approach is flexible, could be used for both text2motion and motion2text tasks.
Ranked #2 on
Motion Captioning
on KIT Motion-Language
Generating Diverse and Natural 3D Human Motions From Text
Automated generation of 3D human motions from text is a challenging problem.
Ranked #6 on
Motion Synthesis
on InterHuman
EndHiC: assemble large contigs into chromosomal-level scaffolds using the Hi-C links from contig ends
As the Hi-C links of two adjacent contigs concentrate only at the neighbor ends of the contigs, larger contig size will reduce the power to differentiate adjacent (signal) and non-adjacent (noise) contig linkages, leading to a higher rate of mis-assembly.
Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety.
3D Pose Estimation and Future Motion Prediction from 2D Images
This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences.
Action2video: Generating Videos of Human 3D Actions
Action2motion stochastically generates plausible 3D pose sequences of a prescribed action category, which are processed and rendered by motion2video to form 2D videos.
Neural Architecture Search via Ensemble-based Knowledge Distillation
Neural Architecture Search (NAS) automatically searches for well-performed network architectures from a given search space.
Sequential Diagnosis Prediction with Transformer and Ontological Representation
Sequential diagnosis prediction on the Electronic Health Record (EHR) has been proven crucial for predictive analytics in the medical domain.
Global Convolutional Neural Processes
Latent neural process, a member of NPF, is believed to be capable of modelling the uncertainty on certain points (local uncertainty) as well as the general function priors (global uncertainties).
Human Pose and Shape Estimation from Single Polarization Images
This paper focuses on a new problem of estimating human pose and shape from single polarization images.
EventHPE: Event-based 3D Human Pose and Shape Estimation
Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals.
Detailed Avatar Recovery from Single Image
In this paper, we propose a novel learning-based framework that combines the robustness of the parametric model with the flexibility of free-form 3D deformation.
Object Wake-up: 3D Object Rigging from a Single Image
A dataset of generic 3D objects with ground-truth annotated skeletons is collected.
Underwater inspection and intervention dataset
This paper presents a novel dataset for the development of visual navigation and simultaneous localisation and mapping (SLAM) algorithms as well as for underwater intervention tasks.
MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning
Hence, some recent works train healthcare representations by incorporating medical ontology, by self-supervised tasks like diagnosis prediction, but (1) the small-scale, monotonous ontology is insufficient for robust learning, and (2) critical contexts or dependencies underlying patient journeys are barely exploited to enhance ontology learning.
Self-supervised 3D Human Mesh Recovery from Noisy Point Clouds
However, Chamfer distance is quite sensitive to noise and outliers, thus could be unreliable to assign correspondences.
Mitigating Generation Shifts for Generalized Zero-Shot Learning
Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e. g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training.
CausalRec: Causal Inference for Visual Debiasing in Visually-Aware Recommendation
Existing visually-aware models make use of the visual features as a separate collaborative signal similarly to other features to directly predict the user's preference without considering a potential bias, which gives rise to a visually biased recommendation.
FedCM: Federated Learning with Client-level Momentum
Federated Learning is a distributed machine learning approach which enables model training without data sharing.
LiDAR-Aug: A General Rendering-Based Augmentation Framework for 3D Object Detection
Finally, we verify the proposed framework on the public KITTI dataset with different 3D object detectors.
QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval
The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field.
How Sensitive are Meta-Learners to Dataset Imbalance?
Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset.
Semantics Disentangling for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training.
Few-Shot Learning with Class Imbalance
Few-Shot Learning (FSL) algorithms are commonly trained through Meta-Learning (ML), which exposes models to batches of tasks sampled from a meta-dataset to mimic tasks seen during evaluation.
Class Imbalance in Few-Shot Learning
Few-shot learning aims to train models on a limited number of labeled samples from a support set in order to generalize to unseen samples from a query set.
Watch and Learn: Mapping Language and Noisy Real-world Videos with Self-supervision
In this paper, we teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations.
RADIATE: A Radar Dataset for Automotive Perception in Bad Weather
To the best of our knowledge, this is the first public radar dataset which provides high-resolution radar images on public roads with a large amount of road actors labelled.
BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes
Electronic health records (EHRs) are longitudinal records of a patient's interactions with healthcare systems.
Action2Motion: Conditioned Generation of 3D Human Motions
Action recognition is a relatively established task, where givenan input sequence of human motion, the goal is to predict its ac-tion category.
Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches
A voting strategy averages the probability distributions output from the classifiers and, given that some patches are more discriminative than others, a discrimination-based attention mechanism helps to weight each patch accordingly.
3D Human Shape Reconstruction from a Polarization Image
Inspired by the recent advances in human shape estimation from single color images, in this paper, we attempt at estimating human body shapes by leveraging the geometric cues from single polarization images.
Self-Attention Enhanced Patient Journey Understanding in Healthcare System
The key challenge of patient journey understanding is to design an effective encoding mechanism which can properly tackle the aforementioned multi-level structured patient journey data with temporal sequential visits and a set of medical codes.
Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping
Tracking and grasping a dynamic object with a random trajectory is even harder.
SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images
First, based on a generative human template, for every two frames having sufficient overlap, an initial pairwise alignment is performed; It is followed by a global non-rigid registration procedure, in which partial results from RGBD frames are collected into a unified 3D shape, under the guidance of correspondences from the pairwise alignment; Finally, the texture map of the reconstructed human model is optimized to deliver a clear and spatially consistent texture.
A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification
Deep convolutional neural networks generally perform well in underwater object recognition tasks on both optical and sonar images.
Polarization Human Shape and Pose Dataset
Polarization images are known to be able to capture polarized reflected lights that preserve rich geometric cues of an object, which has motivated its recent applications in reconstructing detailed surface normal of the objects of interest.
Estimation of genome size using k-mer frequencies from corrected long reads
We show that corrected third-generation data can be used to count k-mer frequencies and estimate genome size reliably, in replacement of using second-generation data.
ZSTAD: Zero-Shot Temporal Activity Detection
An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos.
Robot Calligraphy using Pseudospectral Optimal Control in Conjunction with a Novel Dynamic Brush Model
Chinese calligraphy is a unique art form with great artistic value but difficult to master.
Privacy-Preserving Image Classification in the Local Setting
To protect the image privacy, we propose to locally perturb the image representation before revealing to the data user.
Privacy-Preserving Boosting in the Local Setting
The privacy concern raises when such data leaves the hand of the owners and be further explored or mined.
Snoopy: Sniffing Your Smartwatch Passwords via Deep Sequence Learning
Demand for smartwatches has taken off in recent years with new models which can run independently from smartphones and provide more useful features, becoming first-class mobile platforms.
300 GHz Radar Object Recognition based on Deep Neural Networks and Transfer Learning
For high resolution scene mapping and object recognition, optical technologies such as cameras and LiDAR are the sensors of choice.
Robot Calligraphy using Pseudospectral Optimal Control in Conjunction with a Simulated Brush Model
Chinese calligraphy is a unique form of art that has great artistic value but is difficult to master.
Robotics
Temporal Self-Attention Network for Medical Concept Embedding
In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept.
A Multi-level Neural Network for Implicit Causality Detection in Web Texts
Mining causality from text is a complex and crucial natural language understanding task corresponding to the human cognition.
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
The framework directly regresses 3D bounding boxes for all instances in a point cloud, while simultaneously predicting a point-level mask for each instance.
Ranked #13 on
3D Instance Segmentation
on S3DIS
(mPrec metric)
Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
This paper presents a novel framework to recover detailed human body shapes from a single image.
Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning
Inspired by the cognitive process of humans and animals, Curriculum Learning (CL) trains a model by gradually increasing the difficulty of the training data.
Deep Reinforcement Learning for Autonomous Driving
To deal with these challenges, we first adopt the deep deterministic policy gradient (DDPG) algorithm, which has the capacity to handle complex state and action spaces in continuous domain.
Learning with Stochastic Guidance for Navigation
Due to the sparse rewards and high degree of environment variation, reinforcement learning approaches such as Deep Deterministic Policy Gradient (DDPG) are plagued by issues of high variance when applied in complex real world environments.
Robotics
Part-level Car Parsing and Reconstruction from Single Street View
As it is labor-intensive to annotate semantic parts on real street views, we propose a specific approach to implicitly transfer part features from synthesized images to real street views.
Distributionally Robust Semi-Supervised Learning for People-Centric Sensing
Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing.
Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
However, GRU based approaches are unable to consistently estimate 3D shapes given different permutations of the same set of input images as the recurrent unit is permutation variant.
Ranked #1 on
3D Reconstruction
on Data3D−R2N2
NeuRec: On Nonlinear Transformation for Personalized Ranking
Modeling user-item interaction patterns is an important task for personalized recommendations.
3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations
This is further confounded by the fact that shape information about encountered objects in the real world is often impaired by occlusions, noise and missing regions e. g. a robot manipulating an object will only be able to observe a partial view of the entire solid.
Multi-modality Sensor Data Classification with Selective Attention
Multimodal wearable sensor data classification plays an important role in ubiquitous computing and has a wide range of applications in scenarios from healthcare to entertainment.
Defo-Net: Learning Body Deformation using Generative Adversarial Networks
Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots.
Robotics
POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infrared Sensors
For vehicle autonomy, driver assistance and situational awareness, it is necessary to operate at day and night, and in all weather conditions.
Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning
In this paper, we propose the Gated Multimodal Embedding LSTM with Temporal Attention (GME-LSTM(A)) model that is composed of 2 modules.
Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling
In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other.
Ranked #56 on
Natural Language Inference
on SNLI
SMR: Medical Knowledge Graph Embedding for Safe Medicine Recommendation
To our best knowledge, SMR is the first to learn embeddings of a patient-disease-medicine graph for medicine recommendation in the world.
DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
This paper presents a novel end-to-end framework for monocular VO by using deep Recurrent Convolutional Neural Networks (RCNNs).
UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning
UnDeepVO is able to estimate the 6-DoF pose of a monocular camera and the depth of its view by using deep neural networks.
3D Object Reconstruction from a Single Depth View with Adversarial Learning
In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks.
Cascade and Parallel Convolutional Recurrent Neural Networks on EEG-based Intention Recognition for Brain Computer Interface
Brain-Computer Interface (BCI) is a system empowering humans to communicate with or control the outside world with exclusively brain intentions.
Human-Computer Interaction Neurons and Cognition
PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking
Electronic medical records contain multi-format electronic medical data that consist of an abundance of medical knowledge.
VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization
Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images.
Detailed Surface Geometry and Albedo Recovery from RGB-D Video Under Natural Illumination
In this paper we present a novel approach for depth map enhancement from an RGB-D video sequence.
VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem
In this paper we present an on-manifold sequence-to-sequence learning approach to motion estimation using visual and inertial sensors.
Safety Verification of Deep Neural Networks
Our method works directly with the network code and, in contrast to existing methods, can guarantee that adversarial examples, if they exist, are found for the given region and family of manipulations.
Uncovering Locally Discriminative Structure for Feature Analysis
We propose a method that utilizes both the manifold structure of data and local discriminant information.
Interactive Visual Hull Refinement for Specular and Transparent Object Surface Reconstruction
We discovered that these internal contours, which are results of convex parts on an object's surface, can lead to a tighter fit than the original visual hull.
Unsupervised Feature Analysis with Class Margin Optimization
In this paper, we propose an unsupervised feature selection method seeking a feature coefficient matrix to select the most distinctive features.
Compound Rank-k Projections for Bilinear Analysis
In many real-world applications, data are represented by matrices or high-order tensors.
