Search Results for author:
Found 219 papers, 83 papers with code
Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning
In the past few years, we have witnessed the great progress of image super-resolution (SR) thanks to the power of deep learning.
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate answers.
Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?
Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images.
QURG: Question Rewriting Guided Context-Dependent Text-to-SQL Semantic Parsing
Context-dependent Text-to-SQL aims to translate multi-turn natural language questions into SQL queries.
Self-Supervised 3D Scene Flow Estimation Guided by Superpoints
In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds.
Refined Response Distillation for Class-Incremental Player Detection
Furthermore, we present the NBA-IOD and Volleyball-IOD datasets as the benchmark and investigate the IOD tasks of the players systematically.
Group Equivariant BEV for 3D Object Detection
Experimental results demonstrate that GeqBevNet can extract more rotational equivariant features in the 3D object detection of the actual road scene and improve the performance of object orientation prediction.
A Partial Order for Strictly Positive Coalitional Games and a Link from Risk Aversion to Cooperation
We deal with coalitional games possessing strictly positive values.
Partition-based Stability of Coalitional Games
For the resulting strong, medium, and weak stability concepts, the first is core-compatible in that the traditional core exactly contains those allocations that are associated through this strong stability concept with the all-consolidated partition consisting of only the grand coalition.
Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations
Motivated by the important role of ID, in this paper, we propose a novel deep representation learning approach with autoencoder, which incorporates regularization of the global and local ID constraints into the reconstruction of data representations.
Multi-scale Geometry-aware Transformer for 3D Point Cloud Classification
At first, the MGT divides point cloud data into patches with multiple scales.
Curricular Object Manipulation in LiDAR-based Object Detection
For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages.
Robust Outlier Rejection for 3D Registration with Variational Bayes
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.
3D-Aware Multi-Class Image-to-Image Translation with NeRFs
In the second step, based on the well-trained multi-class 3D-aware GAN architecture, that preserves view-consistency, we construct a 3D-aware I2I translation system.
A Survey of Historical Learning: Learning Models with Learning History
The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models.
Large Selective Kernel Network for Remote Sensing Object Detection
To the best of our knowledge, this is the first time that large and selective kernel mechanisms have been explored in the field of remote sensing object detection.
Ranked #1 on
Object Detection In Aerial Images
on DOTA
Non-aligned supervision for Real Image Dehazing
In particular, we explore a non-alignment setting by utilizing a clear reference image that is not aligned with the hazy input image to supervise the dehazing network through a multi-scale reference loss that compares the features of the two images.
Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN
In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation.
Heterogeneous Social Event Detection via Hyperbolic Graph Representations
This model addresses the heterogeneity of social media, and, with this graph, the information in social media can be used to capture structural information based on the properties of hyperbolic space.
Graph Matching Optimization Network for Point Cloud Registration
Point Cloud Registration is a fundamental and challenging problem in 3D computer vision.
Structure Flow-Guided Network for Real Depth Super-Resolution
Specifically, our framework consists of a cross-modality flow-guided upsampling network (CFUNet) and a flow-enhanced pyramid edge attention network (PEANet).
Recurrent Structure Attention Guidance for Depth Super-Resolution
Second, instead of the coarse concatenation guidance, we propose a recurrent structure attention block, which iteratively utilizes the latest depth estimation and the image features to jointly select clear patterns and boundaries, aiming at providing refined guidance for accurate depth recovery.
HanoiT: Enhancing Context-aware Translation via Selective Context
Context-aware neural machine translation aims to use the document-level context to improve translation quality.
State of the Art and Potentialities of Graph-level Learning
Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures.
Multilingual Entity and Relation Extraction from Unified to Language-specific Training
In this paper, we propose a two-stage multilingual training method and a joint model called Multilingual Entity and Relation Extraction framework (mERE) to mitigate language interference across languages.
Clothed Human Performance Capture With a Double-Layer Neural Radiance Fields
Previous methods capture the performance of full humans with a personalized template or recover the garments from a single frame with static human poses.
Revisiting the P3P Problem
One of the classical multi-view geometry problems is the so called P3P problem, where the absolute pose of a calibrated camera is determined from three 2D-to-3D correspondences.
Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network
Recently, great progress has been made in single-image super-resolution (SISR) based on deep learning technology.
Robust Consensus Clustering and its Applications for Advertising Forecasting
Consensus clustering aggregates partitions in order to find a better fit by reconciling clustering results from different sources/executions.
Do not Waste Money on Advertising Spend: Bid Recommendation via Concavity Changes
In computational advertising, a challenging problem is how to recommend the bid for advertisers to achieve the best return on investment (ROI) given budget constraint.
Demystifying Advertising Campaign Bid Recommendation: A Constraint target CPA Goal Optimization
In cost-per-click (CPC) or cost-per-impression (CPM) advertising campaigns, advertisers always run the risk of spending the budget without getting enough conversions.
Mining User-aware Multi-relations for Fake News Detection in Large Scale Online Social Networks
In this paper, we construct a dual-layer graph (i. e., the news layer and the user layer) to extract multiple relations of news and users in social networks to derive rich information for detecting fake news.
GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator
Inspired by the idea of Generative Adversarial Networks (GANs), we propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator, unifying the ability of language understanding and generation in a single model.
One-Stage Cascade Refinement Networks for Infrared Small Target Detection
Finally, we present a new research benchmark for infrared small target detection, consisting of the SIRST-V2 dataset of real-world, high-resolution single-frame targets, the normalized contrast evaluation metric, and the DeepInfrared toolkit for detection.
Feature Aggregation and Propagation Network for Camouflaged Object Detection
In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection.
A Dataset with Multibeam Forward-Looking Sonar for Underwater Object Detection
There are several challenges to the research on underwater object detection with MFLS.
Curriculum Temperature for Knowledge Distillation
In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature.
DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion
Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation.
High-Resolution Boundary Detection for Medical Image Segmentation with Piece-Wise Two-Sample T-Test Augmented Loss
Deep learning methods have contributed substantially to the rapid advancement of medical image segmentation, the quality of which relies on the suitable design of loss functions.
LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation
To this end, we first propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages.
DAGAD: Data Augmentation for Graph Anomaly Detection
To bridge the gaps, this paper devises a novel Data Augmentation-based Graph Anomaly Detection (DAGAD) framework for attributed graphs, equipped with three specially designed modules: 1) an information fusion module employing graph neural network encoders to learn representations, 2) a graph data augmentation module that fertilizes the training set with generated samples, and 3) an imbalance-tailored learning module to discriminate the distributions of the minority (anomalous) and majority (normal) classes.
CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation
Specifically, the target sequence is first translated into the source language and then tagged by a source NER model.
SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval
In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks.
Spatio-Temporal Relation Learning for Video Anomaly Detection
Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly.
Grouped Adaptive Loss Weighting for Person Search
A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates.
Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking
The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization.
LogLG: Weakly Supervised Log Anomaly Detection via Log-Event Graph Construction
Experiments on five benchmarks validate the effectiveness of LogLG for detecting anomalies on unlabeled log data and demonstrate that LogLG, as the state-of-the-art weakly supervised method, achieves significant performance improvements compared to existing methods.
GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation
Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation.
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth.
3D Siamese Transformer Network for Single Object Tracking on Point Clouds
Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area.
UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation
Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable.
HLT-MT: High-resource Language-specific Training for Multilingual Neural Machine Translation
Nonetheless, multilingual training is plagued by language interference degeneration in shared parameters because of the negative interference among different translation directions, especially on high-resource languages.
GCN-based Multi-task Representation Learning for Anomaly Detection in Attributed Networks
Anomaly detection in attributed networks has received a considerable attention in recent years due to its applications in a wide range of domains such as finance, network security, and medicine.
Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution
Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction.
Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels
To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of DNNs in the early stage of learning to correct noisy labels.
Graph-level Neural Networks: Current Progress and Future Directions
To frame this survey, we propose a systematic taxonomy covering GLNNs upon deep neural networks, graph neural networks, and graph pooling.
Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality
Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy.
Ranked #33 on
Object Detection
on COCO minival
Bi-level Alignment for Cross-Domain Crowd Counting
The main challenge for this task is to achieve high-quality manual annotations on a large amount of training data.
Hyperspectral Image Classification With Contrastive Graph Convolutional Network
To enhance the feature representation ability, in this paper, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations, which is termed Contrastive Graph Convolutional Network (ConGCN), for HSI classification.
Semantics-Guided Moving Object Segmentation with 3D LiDAR
Instead of segmenting the moving objects directly, the network conducts single-scan-based semantic segmentation and multiple-scan-based moving object segmentation in turn.
Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architectures
Knowledge-aware methods have boosted a range of natural language processing applications over the last decades.
CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution
Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features.
Towards Explainable Meta-Learning for DDoS Detection
With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more.
OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation
To this end, some deep convolutional neural networks (CNNs) have been developed to learn discriminative feature by designing properly margin-based losses, which perform well on easy samples but fail on hard samples.
Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product.
Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks
Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion
To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery.
RecursiveMix: Mixed Learning with History
In semantic segmentation, RM also surpasses the baseline and CutMix by 1. 9 and 1. 1 mIoU points under UperNet on ADE20K, respectively.
Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information
Therefore, it is helpful to leverage additional information, e. g., the locations and dates for data shooting, which can be easily accessible but rarely exploited.
Reliable Inlier Evaluation for Unsupervised Point Cloud Registration
In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration.
Webly-Supervised Fine-Grained Recognition with Partial Label Learning
The task of webly-supervised fne-grained recognition is to boost recognition accuracy of classifying subordinate categories (e. g., different bird species)by utilizing freely available but noisy web data. As the label noises signifcantly hurt the network training, it is desirable to distinguish and eliminate noisy images.
PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation
While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable.
SMDT: Selective Memory-Augmented Neural Document Translation
Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation.
Synthesizing Tensor Transformations for Visual Self-attention
Self-attention shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning.
A Proposal-Based Paradigm for Self-Supervised Sound Source Localization in Videos
Humans can easily recognize where and how the sound is produced via watching a scene and listening to corresponding audio cues.
Relative Pose From a Calibrated and an Uncalibrated Smartphone Image
In this paper, we propose a new minimal and a non-minimal solver for estimating the relative camera pose together with the unknown focal length of the second camera.
CVNet: Contour Vibration Network for Building Extraction
The classic active contour model raises a great promising solution to polygon-based object extraction with the progress of deep learning recently.
TransLog: A Unified Transformer-based Framework for Log Anomaly Detection
Therefore, we propose a unified Transformer-based framework for log anomaly detection (\ourmethod{}), which is comprised of the pretraining and adapter-based tuning stage.
A$^2$-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval
Specifically, based on the captured visual representations by attention, we develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors from the appearance-specific visual representations without attribute annotations.
Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation
In this setting, we embed an additional pair of “latent-latent” to reduce the domain gap between the source and different latent domains, allowing the model to adapt well on multiple target domains simultaneously.
Universal Semi-Supervised Learning
Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i. e., class set) and feature distribution (i. e., feature domain) are different between labeled dataset and unlabeled dataset.
Fast and Light-Weight Network for Single Frame Structured Illumination Microscopy Super-Resolution
In our SF-SIM, we propose a noise estimator which can effectively suppress the noise in the image and enable our method to work under the low light and short exposure environment, without the need for stacking multiple frames for non-local denoising.
Keypoint Message Passing for Video-based Person Re-Identification
Video-based person re-identification (re-ID) is an important technique in visual surveillance systems which aims to match video snippets of people captured by different cameras.
Representation Learning
Video-Based Person Re-Identification
Fine-Grained Image Analysis with Deep Learning: A Survey
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications.
3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
The Siamese shape-aware feature learning network can capture 3D shape information of the object to learn the discriminative features of the object so that the potential target from the background in sparse point clouds can be identified.
Neural BRDFs: Representation and Operations
Bidirectional reflectance distribution functions (BRDFs) are pervasively used in computer graphics to produce realistic physically-based appearance.
Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task
This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation.
Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioning
In detail, considering that the heterogeneous gap between modalities always leads to the supervision difficulty of using the global embedding directly, CPRC turns to transform both the raw image and corresponding generated sentence into the shared semantic space, and measure the generated sentence from two aspects: 1) Prediction consistency.
A Survey of Knowledge Enhanced Pre-trained Models
Pre-trained models learn informative representations on large-scale training data through a self-supervised or supervised learning method, which has achieved promising performance in natural language processing (NLP), computer vision (CV), and cross-modal fields after fine-tuning.
Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation
Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm.
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations.
FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation
Specifically, FBSNet employs a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch.
Learning Fair Face Representation With Progressive Cross Transformer
To mitigate racial bias and meantime preserve robust FR, we abstract face identity-related representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition.
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Monocular depth estimation aims at predicting depth from a single image or video.
Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration
By modeling the point cloud registration process as a Markov decision process (MDP), we develop a latent dynamic model of point clouds, consisting of a transformation network and evaluation network.
Multilingual Agreement for Multilingual Neural Machine Translation
Although multilingual neural machine translation (MNMT) enables multiple language translations, the training process is based on independent multilingual objectives.
RigNet: Repetitive Image Guided Network for Depth Completion
However, blurry guidance in the image and unclear structure in the depth still impede the performance of the image guided frameworks.
Ranked #2 on
Depth Completion
on KITTI Depth Completion
Graph Jigsaw Learning for Cartoon Face Recognition
To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner.
Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection
Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions.
A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection.
dFDA-VeD: A Dynamic Future Demand Aware Vehicle Dispatching System
As the process should be socially and economically profitable, the task of vehicle dispatching is highly challenging, specially due to the time-varying travel demands and traffic conditions.
Smart-Start Decoding for Neural Machine Translation
Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left.
Attention-oriented Brain Storm Optimization for Multimodal Optimization Problems
Rather than converge to a single global optimum, the proposed method can guide the search procedure to converge to multiple "salient" solutions.
Robotic Brain Storm Optimization: A Multi-target Collaborative Searching Paradigm for Swarm Robotics
Swarm intelligence optimization algorithms can be adopted in swarm robotics for target searching tasks in a 2-D or 3-D space by treating the target signal strength as fitness values.
A Comprehensive Survey on Community Detection with Deep Learning
A community reveals the features and connections of its members that are different from those in other communities in a network.
DONet: Dual-Octave Network for Fast MR Image Reconstruction
In this paper, we propose the Dual-Octave Network (DONet), which is capable of learning multi-scale spatial-frequency features from both the real and imaginary components of MR data, for fast parallel MR image reconstruction.
Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks
Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.
SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
In order to reduce the number of annotated labels, we propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net, where we train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points.
Learning Normal Dynamics in Videos with Meta Prototype Network
Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection.
Contrastive Embedding for Generalized Zero-Shot Learning
To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework.
JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
In this work, we treat the mask occlusion as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task.
Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition
(i) To learn more robust and discriminative features, we desire to adaptively fuse the contextual features from different layers.
MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones.
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation
Standard automatic metrics, e. g. BLEU, are not reliable for document-level MT evaluation.
Spatial-Temporal Tensor Graph Convolutional Network for Traffic Prediction
We further extend graph convolution into tensor space and propose a tensor graph convolution network to extract more discriminating features from spatial-temporal graph data.
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs).
Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
In this paper, we develop an efficient point cloud learning network (EPC-Net) to form a global descriptor for visual place recognition, which can obtain good performance and reduce computation memory and inference time.
Pyramid Point Cloud Transformer for Large-Scale Place Recognition
In order to obtain discriminative global descriptors, we construct a pyramid VLAD module to aggregate the multi-scale feature maps of point clouds into the global descriptors.
Wasserstein Coupled Graph Learning for Cross-Modal Retrieval
Then, a Wasserstein coupled dictionary, containing multiple pairs of counterpart graph keys with each key corresponding to one modality, is constructed for further feature learning.
Superpoint Network for Point Cloud Oversegmentation
Specifically, in our clustering network, we first jointly learn a soft point-superpoint association map from the coordinate and feature spaces of point clouds, where each point is assigned to the superpoint with a learned weight.
Scribble-Supervised Semantic Segmentation Inference
In this paper, we propose a progressive segmentation inference (PSI) framework to tackle with scribble-supervised semantic segmentation.
Graph Deformer Network
In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.
XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders
Multilingual machine translation enables a single model to translate between different languages.
Globally Optimal Relative Pose Estimation with Gravity Prior
Smartphones, tablets and camera systems used, e. g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately.
They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning
Semi-Supervised Learning (SSL) with mismatched classes deals with the problem that the classes-of-interests in the limited labeled data is only a subset of the classes in massive unlabeled data.
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality.
Ranked #57 on
Object Detection
on COCO test-dev
Aspect Based Sentiment Analysis with Self-Attention and Gated Convolutional Networks
Therefore, to solve the problems above, we build a new model based on gating mechanism, combined with convolutional neural networks (CNN) and self-attention mechanism.
Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising
To cope with this issue, this paper presents a multi-level wavelet residual network (MWRN) architecture as well as a progressive training (PTMWRN) scheme to improve image denoising performance.
Interest-Behaviour Multiplicative Network for Resource-limited Recommendation
In this paper, we aim to mine the cue of user preferences in resource-limited recommendation tasks, for which purpose we specifically build a large used car transaction dataset possessing resource-limitation characteristics.
Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification
Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification.
Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph.
Frontier Detection and Reachability Analysis for Efficient 2D Graph-SLAM Based Active Exploration
We propose an integrated approach to active exploration by exploiting the Cartographer method as the base SLAM module for submap creation and performing efficient frontier detection in the geometrically co-aligned submaps induced by graph optimization.
Spatial Transformer Point Convolution
In this paper, we propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds.
Learning Adaptive Embedding Considering Incremental Class
To this end, we propose a Class-Incremental Learning without Forgetting (CILF) framework, which aims to learn adaptive embedding for processing novel class detection and model update in a unified framework.
ICS-Assist: Intelligent Customer Inquiry Resolution Recommendation in Online Customer Service for Large E-Commerce Businesses
Existing solution recommendation methods for online customer service are unable to determine the best solutions at runtime, leading to poor satisfaction of end customers.
Localizing Anomalies from Weakly-Labeled Videos
In addition, in order to fully utilize the spatial context information, the immediate semantics are directly derived from the segment representations.
Anomaly Detection In Surveillance Videos
Video Anomaly Detection
Instance-Aware Graph Convolutional Network for Multi-Label Classification
For label diffusion of instance-awareness in graph convolution, rather than using the statistical label correlation alone, an image-dependent label correlation matrix (LCM), fusing both the statistical LCM and an individual one of each image instance, is constructed for graph inference on labels to inject adaptive information of label-awareness into the learned features of the model.
S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification
Open set classification (OSC) tackles the problem of determining whether the data are in-class or out-of-class during inference, when only provided with a set of in-class examples at training time.
Graph Wasserstein Correlation Analysis for Movie Retrieval
Spectral graph filtering is introduced to encode graph signals, which are then embedded as probability distributions in a Wasserstein space, called graph Wasserstein metric learning.
Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation
In this paper, we propose a cascaded non-local neural network for point cloud segmentation.
Progressive Point Cloud Deconvolution Generation Network
Starting from the low-resolution point clouds, with the bilateral interpolation and max-pooling operations, the deconvolution network can progressively output high-resolution local and global feature maps.
Improving Neural Machine Translation with Soft Template Prediction
Although neural machine translation (NMT) has achieved significant progress in recent years, most previous NMT models only depend on the source text to generate translation.
Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species.
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.
Ranked #106 on
Object Detection
on COCO test-dev
Deep Learning for Community Detection: Progress, Challenges and Opportunities
As communities represent similar opinions, similar functions, similar purposes, etc., community detection is an important and extremely useful tool in both scientific inquiry and data analytics.
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image.
Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method
With the rapidly growing number of security-sensitive systems that use voice as the primary input, it becomes increasingly important to address these systems' potential vulnerability to replay attacks.
Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
Meanwhile, we propose a M-bit Inputs and N-bit Weights Network (MINW-Net) trained by AQE, a quantized neural network with 1-3 bits weights and activations.
Network Cooperation with Progressive Disambiguation for Partial Label Learning
Partial Label Learning (PLL) aims to train a classifier when each training instance is associated with a set of candidate labels, among which only one is correct but is not accessible during the training phase.
Graph Inference Learning for Semi-supervised Classification
In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures.
LiDAR Iris for Loop-Closure Detection
In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection.
Curvilinear Distance Metric Learning
To address this issue, we first reveal that the traditional linear distance metric is equivalent to the cumulative arc length between the data pair's nearest points on the learned straight measurer lines.
Dual-Attention Graph Convolutional Network
Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification.
AIM 2019 Challenge on Image Demoireing: Methods and Results
A new dataset, called LCDMoire was created for this challenge, and consists of 10, 200 synthetically generated image pairs (moire and clean ground truth).
Trident Segmentation CNN: A Spatiotemporal Transformation CNN for Punctate White Matter Lesions Segmentation in Preterm Neonates
In this paper, a novel spatiotemporal transformation deep learning method called Trident Segmentation CNN (TS-CNN) is proposed to segment PWML in MR images.
Multi-scale Dynamic Feature Encoding Network for Image Demoireing
The prevalence of digital sensors, such as digital cameras and mobile phones, simplifies the acquisition of photos.
Low-Resource Response Generation with Template Prior
Since the paired data now is no longer enough to train a neural generation model, we consider leveraging the large scale of unpaired data that are much easier to obtain, and propose response generation with both paired and unpaired data.
Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network
In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance.
Learn Interpretable Word Embeddings Efficiently with von Mises-Fisher Distribution
Results show that our model can outperform the dominant models consistently in these tasks.
Cross-X Learning for Fine-Grained Visual Categorization
Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.
Ranked #15 on
Fine-Grained Image Classification
on NABirds
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Visual Categorization
Image Formation Model Guided Deep Image Super-Resolution
We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution.
Refined-Segmentation R-CNN: A Two-stage Convolutional Neural Network for Punctate White Matter Lesion Segmentation in Preterm Infants
In this paper, we construct an efficient two-stage PWML semantic segmentation network based on the characteristics of the lesion, called refined segmentation R-CNN (RS RCNN).
