Search Results for author:
Found 211 papers, 83 papers with code
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial Texts
Universal adversarial texts (UATs) refer to short pieces of text units that can largely affect the predictions of NLP models.
Monash-Summ@LongSumm 20 SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline
The Scholarly Document Processing (SDP) workshop is to encourage more efforts on natural language understanding of scientific task.
AMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation
Online knowledge distillation has attracted increasing interest recently, which jointly learns teacher and student models or an ensemble of student models simultaneously and collaboratively.
Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension
Then, we only fine-tune the lottery subnetwork, a small fraction of the whole parameters, on the annotated target domain data for adaptation.
Efficient and accurate neural field reconstruction using resistive memory
The GE harnesses the intrinsic stochasticity of resistive memory for efficient input encoding, while the PE achieves precise weight mapping through a Hardware-Aware Quantization (HAQ) circuit.
Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlooks
3D lane detection plays a crucial role in autonomous driving by extracting structural and traffic information from the road in 3D space to assist the self-driving car in rational, safe, and comfortable path planning and motion control.
SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions
The key idea of our SmartControl is to relax the visual condition on the areas that are conflicted with text prompts.
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
OmniColor: A Global Camera Pose Optimization Approach of LiDAR-360Camera Fusion for Colorizing Point Clouds
A Colored point cloud, as a simple and efficient 3D representation, has many advantages in various fields, including robotic navigation and scene reconstruction.
CurbNet: Curb Detection Framework Based on LiDAR Point Cloud Segmentation
Moreover, we propose an adaptive weighted loss function group, specifically formulated to counteract the imbalance in the distribution of curb point clouds relative to other categories.
CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models
Cognitive dynamics are pivotal to advance human understanding of the world.
Hi-Map: Hierarchical Factorized Radiance Field for High-Fidelity Monocular Dense Mapping
In this paper, we introduce Hi-Map, a novel monocular dense mapping approach based on Neural Radiance Field (NeRF).
A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model
Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem.
Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation
Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios.
U2-KWS: Unified Two-pass Open-vocabulary Keyword Spotting with Keyword Bias
Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest.
Random resistive memory-based deep extreme point learning machine for unified visual processing
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
KwaiAgents: Generalized Information-seeking Agent System with Large Language Models
Driven by curiosity, humans have continually sought to explore and understand the world around them, leading to the invention of various tools to satiate this inquisitiveness.
Generalized Label-Efficient 3D Scene Parsing via Hierarchical Feature Aligned Pre-Training and Region-Aware Fine-tuning
Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels.
TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
Understanding time is a pivotal aspect of human cognition, crucial in the broader framework of grasping the intricacies of the world.
GBD-TS: Goal-based Pedestrian Trajectory Prediction with Diffusion using Tree Sampling Algorithm
GBD combines goal prediction with the diffusion network.
Pruning random resistive memory for optimizing analogue AI
Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network.
MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document
To address this issue, we propose MTGER, a novel Multi-view Temporal Graph Enhanced Temporal Reasoning framework for temporal reasoning over time-involved documents.
Learning to Learn for Few-shot Continual Active Learning
Recent advances in CL are mostly confined to a supervised learning setting, especially in NLP domain.
Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection
Existing industrial anomaly detection (IAD) methods predict anomaly scores for both anomaly detection and localization.
Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Training
Monocular 3D object detection plays a crucial role in autonomous driving.
A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
Chain-of-thought reasoning, a cognitive process fundamental to human intelligence, has garnered significant attention in the realm of artificial intelligence and natural language processing.
Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition
In this paper, we circumvent this issue by presenting a joint framework for both unbounded recommendation of camera view and image composition (i. e., UNIC).
Rethinking Imitation-based Planner for Autonomous Driving
In recent years, imitation-based driving planners have reported considerable success.
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces
To evaluate our proposed MetaF2N, we have collected a real-world low-quality dataset with one or multiple faces in each image, and our MetaF2N achieves superior performance on both synthetic and real-world datasets.
Efficient Ray Sampling for Radiance Fields Reconstruction
Through this method, not only can the convergence of the network be accelerated, but the spatial geometry of a scene can also be perceived more accurately.
Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders
This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language processing.
Recent Advances in Hierarchical Multi-label Text Classification: A Survey
Hierarchical multi-label text classification aims to classify the input text into multiple labels, among which the labels are structured and hierarchical.
Multi Label Text Classification
Multi-Label Text Classification
+1
Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images
However, previous studies learned within a sequence of autonomous driving datasets, resulting in unsatisfactory blurring when rotating the car in the simulator.
Adaptive Control of Resource Flow to Optimize Construction Work and Cash Flow via Online Deep Reinforcement Learning
Therefore, this paper introducess a model and method to adaptive control the resource flows to optimize the work and cash flows of construction projects.
Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data
This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution.
Exploring & Exploiting High-Order Graph Structure for Sparse Knowledge Graph Completion
The proposed approach comprises two main components: a GNN-based predictor and a reasoning path distiller.
Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?
For Pretrained Language Models (PLMs), their susceptibility to noise has recently been linked to subword segmentation.
A Survey on Out-of-Distribution Evaluation of Neural NLP Models
Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models.
SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models
Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.
Automatic Localization and Detection Applicable to Robust Image Watermarking Resisting against Camera Shooting
Furthermore, the proposed scheme is not limited to any specific watermark embedding strategy, allowing for improvements in the watermark embedding and extraction procedure.
Binary stochasticity enabled highly efficient neuromorphic deep learning achieves better-than-software accuracy
We propose a binary stochastic learning algorithm that modifies all elementary neural network operations, by introducing (i) stochastic binarization of both the forwarding signals and the activation function derivatives, (ii) signed binarization of the backpropagating errors, and (iii) step-wised weight updates.
D2NT: A High-Performing Depth-to-Normal Translator
Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information.
FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving
Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving.
Human Guided Ground-truth Generation for Realistic Image Super-resolution
A human guided GT image dataset with both positive and negative samples is then constructed, and a loss function is proposed to train the Real-ISR models.
LCE-Calib: Automatic LiDAR-Frame/Event Camera Extrinsic Calibration With A Globally Optimal Solution
This paper proposes an automatic checkerboard-based approach to calibrate extrinsics between a LiDAR and a frame/event camera, where four contributions are presented.
Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast
The second is that we prevent over-discrimination between 3D segments/objects and encourage grouped foreground-to-background distinctions at the segment level with adaptive feature learning in a Siamese correspondence network, which adaptively learns feature correlations within and across point cloud views effectively.
An Efficient Approach to the Online Multi-Agent Path Finding Problem by Using Sustainable Information
The low-level solver, the Sustainable Reverse Safe Interval Path Planning algorithm (SRSIPP), is an efficient single-agent solver that uses previous planning context to reduce duplicate calculations.
Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography
Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling.
Ranked #1 on
Image Denoising
on ELD SonyA7S2 x200
GreenEyes: An Air Quality Evaluating Model based on WaveNet
Accompanying rapid industrialization, humans are suffering from serious air pollution problems.
Self-Supervised Image Restoration with Blurry and Noisy Pairs
By learning in a collaborative manner, the deblurring and denoising tasks in our method can benefit each other.
BigCilin: An Automatic Chinese Open-domain Knowledge Graph with Fine-grained Hypernym-Hyponym Relations
One is that it supports querying any Chinese named entity and browsing the extracted hypernym-hyponym paths surro-unding the query entity.
How Far are We from Robust Long Abstractive Summarization?
For long document abstractive models, we show that the constant strive for state-of-the-art ROUGE results can lead us to generate more relevant summaries but not factual ones.
Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia
In this paper, we propose Kuaipedia, a large-scale multi-modal encyclopedia consisting of items, aspects, and short videos lined to them, which was extracted from billions of videos of Kuaishou (Kwai), a well-known short-video platform in China.
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement
To annotate road network graphs effectively and efficiently, automatic algorithms for road network graph detection are demanded.
CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation
Due to the use of the DETR-like transformer network, CenterLineDet can handle complicated graph topology, such as lane intersections.
A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration
Generative adversarial networks (GANs) have drawn enormous attention due to the simple yet effective training mechanism and superior image generation quality.
Learning Diverse Tone Styles for Image Retouching
In particular, the style encoder predicts the target style representation of an input image, which serves as the conditional information in the RetouchNet for retouching, while the TSFlow maps the style representation vector into a Gaussian distribution in the forward pass.
VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion
In this paper, we solve the sparse KGC from these two motivations simultaneously and handle their respective drawbacks further, and propose a plug-and-play unified framework VEM$^2$L over sparse KGs.
Open-world Semantic Segmentation for LIDAR Point Clouds
Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e. g., autonomous driving, since it is closed-set and static.
An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics
The empirical analysis includes a study on the intrinsic characteristics of benchmark datasets, a multi-dimensional analysis of summarization models, and a review of the summarization evaluation metrics.
HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection
The same multi-word expressions may have different meanings in different sentences.
Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective
Meanwhile, diverse testing sets are also provided with different types of reflection and scenes.
Channel Self-Supervision for Online Knowledge Distillation
Recently, researchers have shown an increased interest in the online knowledge distillation.
RNGDet: Road Network Graph Detection by Transformer in Aerial Images
To provide a solution to these problems, we propose a novel approach based on transformer and imitation learning in this paper.
Why-So-Deep: Towards Boosting Previously Trained Models for Visual Place Recognition
We propose a novel approach for improving image retrieval based on previously trained models.
Distilled Dual-Encoder Model for Vision-Language Understanding
We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering.
Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency
In this paper, we observe that the reduced image retains relatively complete shape semantics but loses extensive texture information.
Open-set 3D Object Detection
The first step is solved by the finding that unknown objects are often classified as known objects with low confidence, and we show that the Euclidean distance sum based on metric learning is a better confidence score than the naive softmax probability to differentiate unknown objects from known objects.
csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps
To provide a solution to the aforementioned problems, in this letter, we propose a novel system termed csBoundary to automatically detect road boundaries at the city scale for HD map annotation.
Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence
This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation.
Neural Attention-Aware Hierarchical Topic Model
Neural topic models (NTMs) apply deep neural networks to topic modelling.
Leveraging Information Bottleneck for Scientific Document Summarization
This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle.
Decouple and Reconstruct: Mining Discriminative Features for Cross-domain Object Detection
In recent years, a great progress has been witnessed for cross-domain object detection.
Carl-Lead: Lidar-based End-to-End Autonomous Driving with Contrastive Deep Reinforcement Learning
We further use unsupervised contrastive representation learning as an auxiliary task to improve the sample efficiency.
Fine Grained Human Evaluation for English-to-Chinese Machine Translation: A Case Study on Scientific Text
Recent research suggests that neural machine translation (MT) in the news domain has reached human-level performance, but for other professional domains, it is far below the level.
Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms
Existing road pothole detection approaches can be classified as computer vision-based or machine learning-based.
Prototype-Guided Memory Replay for Continual Learning
Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge.
GEDIT: Geographic-Enhanced and Dependency-Guided Tagging for Joint POI and Accessibility Extraction at Baidu Maps
We approach this task as a sequence tagging problem, where the goal is to produce <POI name, accessibility label> pairs from unstructured text.
Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision
To diminish the effect of color inconsistency in image alignment, we introduce to use a global color mapping (GCM) module to generate an initial sRGB image given the input raw image, which can keep the spatial location of the pixels unchanged, and the target sRGB image is utilized to guide GCM for converting the color towards it.
DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks
Autonomous driving in multi-agent dynamic traffic scenarios is challenging: the behaviors of road users are uncertain and are hard to model explicitly, and the ego-vehicle should apply complicated negotiation skills with them, such as yielding, merging and taking turns, to achieve both safe and efficient driving in various settings.
Deep Metric Learning for Open World Semantic Segmentation
Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models.
SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection
In particular, SNE-RoadSeg, our previously proposed method based on a surface normal estimator (SNE) and a data-fusion DCNN (RoadSeg), has achieved impressive performance in freespace detection.
Federated Learning Meets Natural Language Processing: A Survey
Recent Natural Language Processing techniques rely on deep learning and large pre-trained language models.
CP-loss: Connectivity-preserving Loss for Road Curb Detection in Autonomous Driving with Aerial Images
To alleviate this issue, we detect road curbs offline using high-resolution aerial images in this paper.
Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
In this work, we present a general deep imitative reinforcement learning approach (DIRL), which successfully achieves agile autonomous racing using visual inputs.
Feature Mining: A Novel Training Strategy for Convolutional Neural Network
In this paper, we propose a novel training strategy for convolutional neural network(CNN) named Feature Mining, that aims to strengthen the network's learning of the local feature.
SCV-Stereo: Learning Stereo Matching from a Sparse Cost Volume
Convolutional neural network (CNN)-based stereo matching approaches generally require a dense cost volume (DCV) for disparity estimation.
Co-Teaching: An Ark to Unsupervised Stereo Matching
Stereo matching is a key component of autonomous driving perception.
Go Small and Similar: A Simple Output Decay Brings Better Performance
Regularization and data augmentation methods have been widely used and become increasingly indispensable in deep learning training.
Self-supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning
In this paper, we show that feature transformations within CNNs can also be regarded as supervisory signals to construct the self-supervised task, called \emph{internal pretext task}.
Self-supervision of Feature Transformation for Further Improving Supervised Learning
In this paper we find that features in CNNs can be also used for self-supervision.
White Paper Assistance: A Step Forward Beyond the Shortcut Learning
The promising performances of CNNs often overshadow the need to examine whether they are doing in the way we are actually interested.
DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension
Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC.
Ranked #4 on
Question Answering
on Molweni
Comparing Representations in Tracking for Event Camera-based SLAM
This paper investigates two typical image-type representations for event camera-based tracking: time surface (TS) and event map (EM).
Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation
To address this problem, we propose an interpretable end-to-end vision-based motion planning approach for autonomous driving, referred to as IVMP.
End-to-End Interactive Prediction and Planning with Optical Flow Distillation for Autonomous Driving
With the recent advancement of deep learning technology, data-driven approaches for autonomous car prediction and planning have achieved extraordinary performance.
3D Surfel Map-Aided Visual Relocalization with Learned Descriptors
In this paper, we introduce a method for visual relocalization using the geometric information from a 3D surfel map.
iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving
We find that the visual appearances between road areas and off-road areas are usually different in aerial images, so we propose a novel solution to detect road curbs off-line using aerial images.
Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving
So in this paper, we propose a new benchmark dataset, named \textit{Topo-boundary}, for offline topological road-boundary detection.
Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions
In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs).
FocusedDropout for Convolutional Neural Network
In convolutional neural network (CNN), dropout cannot work well because dropped information is not entirely obscured in convolutional layers where features are correlated spatially.
Greedy-Based Feature Selection for Efficient LiDAR SLAM
Modern LiDAR-SLAM (L-SLAM) systems have shown excellent results in large-scale, real-world scenarios.
YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs.
3D Object Detection From Stereo Images
Disparity Estimation
+3
PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching
Supervised learning with deep convolutional neural networks (DCNNs) has seen huge adoption in stereo matching.
Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network
In this paper, we propose a novel data augmentation strategy named Cut-Thumbnail, that aims to improve the shape bias of the network.
Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms
Therefore, in this paper, we first build a drivable area and road anomaly detection benchmark for ground mobile robots, evaluating the existing state-of-the-art single-modal and data-fusion semantic segmentation CNNs using six modalities of visual features.
Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars
To provide a solution to this problem, we propose a novel branched network G-CIL for the navigation policy learning.
Ground-aware Monocular 3D Object Detection for Autonomous Driving
We further verify the power of the proposed module with a neural network designed for monocular depth prediction.
Ranked #5 on
Monocular 3D Object Detection
on KITTI Cars Hard
AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention
We suggest that introducing an attention mechanism to infer the importance of different neighbors is critical for accurate trajectory prediction in scenes with varying crowd size.
Rethinking Road Surface 3D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation
This paper presents an efficient pothole detection algorithm based on road disparity map estimation and segmentation.
Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation
Therefore, this paper mainly explores an effective training data augmentation approach that can be employed to improve the overall DCNN performance, when additional images captured from different views are available.
Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance
To be specific, the reflection layer is firstly estimated due to that it generally is much simpler and is relatively easier to estimate.
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point
In this paper, we explore the limits of Microsoft Floating Point (MSFP), a new class of datatypes developed for production cloud-scale inferencing on custom hardware.
DiGNet: Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks
Traditional decision and planning frameworks for self-driving vehicles (SDVs) scale poorly in new scenarios, thus they require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable cases.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
Geometric Structure Aided Visual Inertial Localization
To take the advantages of both, in this work, we present a complete visual inertial localization system based on a hybrid map representation to reduce the computational cost and increase the positioning accuracy.
CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised Optical Flow Estimation
The interpretation of ego motion and scene change is a fundamental task for mobile robots.
Robust Odometry and Mapping for Multi-LiDAR Systems with Online Extrinsic Calibration
This paper proposes a system to achieve robust and simultaneous extrinsic calibration, odometry, and mapping for multiple LiDARs.
SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline
The Scholarly Document Processing (SDP) workshop is to encourage more efforts on natural language understanding of scientific task.
Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs
Few/Zero-shot learning is a big challenge of many classifications tasks, where a classifier is required to recognise instances of classes that have very few or even no training samples.
Wound and episode level readmission risk or weeks to readmit: Why do patients get readmitted? How long does it take for a patient to get readmitted?
On a combined wound & episode-level data set of patient's wound care information, our extended autoprognosis achieves a recall of 92 and a precision of 92 for the predicting a patient's re-admission risk.
Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation
We present a robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass.
Loop-box: Multi-Agent Direct SLAM Triggered by Single Loop Closure for Large-Scale Mapping
We develop a generic method for the keychallenging scenarios in multi-agent 3D mapping based on different camera systems.
MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving
To minimize the detrimental effect of extrinsic perturbation, we propagate an uncertainty prior on each point of input point clouds, and use this information to boost an approach for 3D geometric tasks.
HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction
Fully investigating the social interactions within the crowd is crucial for accurate pedestrian trajectory prediction.
Activate or Not: Learning Customized Activation
We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not.
Unpaired Learning of Deep Image Denoising
As for knowledge distillation, we first apply the learned noise models to clean images to synthesize a paired set of training images, and use the real noisy images and the corresponding denoising results in the first stage to form another paired set.
SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection
Freespace detection is an essential component of visual perception for self-driving cars.
Applying Surface Normal Information in Drivable Area and Road Anomaly Detection for Ground Mobile Robots
Our NIM can be deployed in existing convolutional neural networks (CNNs) to refine the segmentation performance.
ATG-PVD: Ticketing Parking Violations on A Drone
In this paper, we introduce a novel suspect-and-investigate framework, which can be easily embedded in a drone for automated parking violation detection (PVD).
We Learn Better Road Pothole Detection: from Attention Aggregation to Adversarial Domain Adaptation
The experimental results demonstrate that, firstly, the transformed disparity (or inverse depth) images become more informative; secondly, AA-UNet and AA-RTFNet, our best performing implementations, respectively outperform all other state-of-the-art single-modal and data-fusion networks for road pothole detection; and finally, the training set augmentation technique based on adversarial domain adaptation not only improves the accuracy of the state-of-the-art semantic segmentation networks, but also accelerates their convergence.
Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision
Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training.
SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression
Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains.
Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairs
We develop a pipeline that can automatically generate segmentation labels for drivable areas and road anomalies.
GMMLoc: Structure Consistent Visual Localization with Gaussian Mixture Models
Incorporating prior structure information into the visual state estimation could generally improve the localization performance.
6 nm super-resolution optical transmission and scattering spectroscopic imaging of carbon nanotubes using a nanometer-scale white light source
Optical hyperspectral imaging based on absorption and scattering of photons at the visible and adjacent frequencies denotes one of the most informative and inclusive characterization methods in material research.
Super-Resolution
Optics
Materials Science
Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator
To evaluate the performance of our proposed SNE, we created three large-scale synthetic datasets (easy, medium and hard) using 24 3D mesh models, each of which is used to generate 1800--2500 pairs of depth images (resolution: 480X640 pixels) and the corresponding ground-truth surface normal maps from different views.
Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments with Multimodal Sensor Fusion
All-day and all-weather navigation is a critical capability for autonomous driving, which requires proper reaction to varied environmental conditions and complex agent behaviors.
CoMoGCN: Coherent Motion Aware Trajectory Prediction with Graph Representation
Forecasting human trajectories is critical for tasks such as robot crowd navigation and autonomous driving.
VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban Environments
Traditional methods for autonomous driving are implemented with many building blocks from perception, planning and control, making them difficult to generalize to varied scenarios due to complex assumptions and interdependencies.
The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic: An Autonomous Logistic Vehicle for Contactless Goods Transportation
Moreover, many countries have imposed tough lockdown measures to reduce the virus transmission (e. g., retail, catering) during the pandemic, which causes inconveniences for human daily life.
Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure
Research into the area of multiparty dialog has grown considerably over recent years.
Ranked #7 on
Discourse Parsing
on Molweni
Deep Adaptive Inference Networks for Single Image Super-Resolution
Nonetheless, content and resource adaptive model is more preferred, and it is encouraging to apply simpler and efficient networks to the easier regions with less details and the scenarios with restricted efficiency constraints.
COVID-19 Docking Server: A meta server for docking small molecules, peptides and antibodies against potential targets of COVID-19
Motivation: The coronavirus disease 2019 (COVID-19) caused by a new type of coronavirus has been emerging from China and led to thousands of death globally since December 2019.
PointTrackNet: An End-to-End Network For 3-D Object Detection and Tracking From Point Clouds
Recent machine learning-based multi-object tracking (MOT) frameworks are becoming popular for 3-D point clouds.
Monocular Direct Sparse Localization in a Prior 3D Surfel Map
The tracked points with and without the global planar information involve both global and local constraints of frames to the system.
Leveraging Cross Feedback of User and Item Embeddings with Attention for Variational Autoencoder based Collaborative Filtering
Based on the ELBOs, we propose a VAE-based Bayesian MF framework.
High-speed Autonomous Drifting with Deep Reinforcement Learning
Drifting is a complicated task for autonomous vehicle control.
Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data
Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems.
Robust Lane Marking Detection Algorithm Using Drivable Area Segmentation and Extended SLT
In this paper, a robust lane detection algorithm is proposed, where the vertical road profile of the road is estimated using dynamic programming from the v-disparity map and, based on the estimated profile, the road area is segmented.
An Annotation Scheme of A Large-scale Multi-party Dialogues Dataset for Discourse Parsing and Machine Comprehension
In this paper, we propose the scheme for annotating large-scale multi-party chat dialogues for discourse parsing and machine comprehension.
Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification
Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context.
A Robust Pavement Mapping System Based on Normal-Constrained Stereo Visual Odometry
Pavement condition is crucial for civil infrastructure maintenance.
PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation
This linear model is then utilized to reduce the redundant information in the left and right road images.
Federated Transfer Reinforcement Learning for Autonomous Driving
Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles.
Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data
Under synthetic data evaluation, VAE-BPTF tended to recover the right number of latent factors and posterior parameter values.
Road Damage Detection Based on Unsupervised Disparity Map Segmentation
This paper presents a novel road damage detection algorithm based on unsupervised disparity map segmentation.
Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze
Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies.
Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data
The experimental results demonstrate that FIL is capable of increasing imitation learning of local robots in cloud robotic systems.
Pothole Detection Based on Disparity Transformation and Road Surface Modeling
Furthermore, the pothole detection accuracy is still far from satisfactory.
Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study
Detecting inaccurate smart meters and targeting them for replacement can save significant resources.
Utilizing Eye Gaze to Enhance the Generalization of Imitation Networks to Unseen Environments
Vision-based autonomous driving through imitation learning mimics the behaviors of human drivers by training on pairs of data of raw driver-view images and actions.
Learning How to Active Learn by Dreaming
Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.
Movable-Object-Aware Visual SLAM via Weakly Supervised Semantic Segmentation
Moving objects can greatly jeopardize the performance of a visual simultaneous localization and mapping (vSLAM) system which relies on the static-world assumption.
Key Ingredients of Self-Driving Cars
Over the past decade, many research articles have been published in the area of autonomous driving.
A Robust Roll Angle Estimation Algorithm Based on Gradient Descent
This paper presents a robust roll angle estimation algorithm, which is developed from our previously published work, where the roll angle was estimated from a dense disparity map by minimizing a global energy using golden section search algorithm.
Automatic Calibration of Multiple 3D LiDARs in Urban Environments
Multiple LiDARs have progressively emerged on autonomous vehicles for rendering a wide field of view and dense measurements.
A Novel Dual-Lidar Calibration Algorithm Using Planar Surfaces
Multiple lidars are prevalently used on mobile vehicles for rendering a broad view to enhance the performance of localization and perception systems.
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks.
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding
In this paper, we propose a novel road crack detection algorithm based on deep learning and adaptive image segmentation.
Gaze Training by Modulated Dropout Improves Imitation Learning
The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior.
Tightly Coupled 3D Lidar Inertial Odometry and Mapping
By sensor fusion, we can compensate the deficiencies of stand-alone sensors and provide more reliable estimations.
Real-Time Dense Stereo Embedded in A UAV for Road Inspection
This makes the damaged road areas more distinguishable from the road surface.
Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues
This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only.
RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes
In order to enable robust and accurate semantic segmentation for autonomous vehicles, we take the advantage of thermal images and fuse both the RGB and thermal information in a novel deep neural network.
Ranked #4 on
Thermal Image Segmentation
on KP day-night
Towards Time-Aware Distant Supervision for Relation Extraction
Time-DS is composed of a time series instance-popularity and two strategies.
Attribute Acquisition in Ontology based on Representation Learning of Hierarchical Classes and Attributes
This paper investigates an attention-based automatic paradigm called TransATT for attribute acquisition, by learning the representation of hierarchical classes and attributes in Chinese ontology.
Using DP Towards A Shortest Path Problem-Related Application
We apply the designed model and proposed an algorithm for detecting lanes by formulating it as the shortest path problem.
Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective
End-to-end visual-based imitation learning has been widely applied in autonomous driving.
PointIT: A Fast Tracking Framework Based on 3D Instance Segmentation
Finally, we extend the Sort algorithm with this instance framework to realize tracking in the 3D LiDAR point cloud data.
Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems
To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federated Reinforcement Learning (LFRL).
Learning Symmetry Consistent Deep CNNs for Face Completion
As for missing pixels on both of half-faces, we present a generative reconstruction subnet together with a perceptual symmetry loss to enforce symmetry consistency of recovered structures.
Ranked #1 on
Facial Inpainting
on VggFace2
Semi-Semantic Line-Cluster Assisted Monocular SLAM for Indoor Environments
In the back end, we optimize the map imposing the constraint that the line segments of the same cluster should be the same.
Point-cloud-based place recognition using CNN feature extraction
This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction.
Learning to Actively Learn Neural Machine Translation
Traditional active learning (AL) methods for machine translation (MT) rely on heuristics.
Neural Speech Synthesis with Transformer Network
Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long dependency using current recurrent neural networks (RNNs).
Ranked #9 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
Focal Loss in 3D Object Detection
Inspired by the recent use of focal loss in image-based object detection, we extend this hard-mining improvement of binary cross entropy to point-cloud-based object detection and conduct experiments to show its performance based on two different 3D detectors: 3D-FCN and VoxelNet.
Multiple Lane Detection Algorithm Based on Optimised Dense Disparity Map Estimation
Lane detection is very important for self-driving vehicles.
PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud
We take the spherical image, which is transformed from the 3D LiDAR point clouds, as input of the convolutional neural networks (CNNs) to predict the point-wise semantic map.
Real-Time Subpixel Fast Bilateral Stereo
Stereo vision technique has been widely used in robotic systems to acquire 3-D information.
Learning How to Actively Learn: A Deep Imitation Learning Approach
Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.
Fast Symbolic 3D Registration Solution
3D registration has always been performed invoking singular value decomposition (SVD) or eigenvalue decomposition (EIG) in real engineering practices.
Learning Warped Guidance for Blind Face Restoration
For better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided image of the same identity as input to our guided face restoration network (GFRNet).
Ranked #1 on
Image Super-Resolution
on WebFace - 8x upscaling
Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning
A video of our experimental results can be found at https://goo. gl/pWbpcF.
VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control
In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks.
Calculating Semantic Similarity between Academic Articles using Topic Event and Ontology
Determining semantic similarity between academic documents is crucial to many tasks such as plagiarism detection, automatic technical survey and semantic search.
Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning
Experiments show that our GAIL-based approach greatly improves the safety and efficiency of the behavior of mobile robots from pure behavior cloning.
Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning
In this paper we focus on developing a control algorithm for multi-terrain tracked robots with flippers using a reinforcement learning (RL) approach.
