Search Results for author:
Found 281 papers, 114 papers with code
Selective Kernel Networks
A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches.
Ranked #98 on
Image Classification
on CIFAR-100
(using extra training data)
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 #93 on
Object Detection
on COCO test-dev
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 #26 on
Object Detection
on COCO-O
Qwen Technical Report
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans.
Ranked #3 on
Multi-Label Text Classification
on CC3M-TagMask
DSFD: Dual Shot Face Detector
In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively.
Ranked #1 on
Face Detection
on FDDB
Shape Robust Text Detection with Progressive Scale Expansion Network
To address these problems, we propose a novel Progressive Scale Expansion Network (PSENet), designed as a segmentation-based detector with multiple predictions for each text instance.
Ranked #12 on
Scene Text Detection
on ICDAR 2017 MLT
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features.
Ranked #739 on
Image Classification
on ImageNet
2017 Robotic Instrument Segmentation Challenge
In mainstream computer vision and machine learning, public datasets such as ImageNet, COCO and KITTI have helped drive enormous improvements by enabling researchers to understand the strengths and limitations of different algorithms via performance comparison.
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.
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
Semantic Segmentation
on UAVid
LSKNet: A Foundation Lightweight Backbone for Remote Sensing
While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios.
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.
FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
We present a novel deep end-to-end trainable Face Super-Resolution Network (FSRNet), which makes full use of the geometry prior, i. e., facial landmark heatmaps and parsing maps, to super-resolve very low-resolution (LR) face images without well-aligned requirement.
Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models
This finding inspired us to omit the encoder at certain adjacent time-steps and reuse cyclically the encoder features in the previous time-steps for the decoder.
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 #37 on
Object Detection
on COCO minival
Image Super-Resolution via Deep Recursive Residual Network
Specifically, residual learning is adopted, both in global and local manners, to mitigate the difficulty of training very deep networks; recursive learning is used to control the model parameters while increasing the depth.
Ranked #10 on
Video Super-Resolution
on MSU Video Upscalers: Quality Enhancement
(VMAF metric)
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.
Ranked #1 on
2D Object Detection
on SARDet-100K
(using extra training data)
MemNet: A Persistent Memory Network for Image Restoration
We apply MemNet to three image restoration tasks, i. e., image denosing, super-resolution and JPEG deblocking.
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.
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.
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.
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.
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.
Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification
To alleviate this shortcoming, we consider employing the recently proposed Graph Convolutional Network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information.
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries.
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.
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.
SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution
Recent image guided DSR approaches mainly focus on spatial domain to rebuild depth structure.
PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student.
Ranked #1 on
Prompt Engineering
on Oxford-IIIT Pet Dataset
Deepfake Generation and Detection: A Benchmark and Survey
In addition to the advancements in deepfake generation, corresponding detection technologies need to continuously evolve to regulate the potential misuse of deepfakes, such as for privacy invasion and phishing attacks.
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
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation
Standard automatic metrics, e. g. BLEU, are not reliable for document-level MT evaluation.
Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
Specifically, a shadow image is fed into the first generator which produces a shadow detection mask.
Ranked #3 on
RGB Salient Object Detection
on ISTD
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.
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation
Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs.
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.
Ranked #3 on
3D Place Recognition
on Oxford RobotCar Dataset
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.
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.
Ranked #7 on
Text-based Image Editing
on PIE-Bench
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.
Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
In contrast, human vision is able to predict poses by exploiting geometric constraints of joint inter-connectivity.
Ranked #15 on
Pose Estimation
on MPII Human Pose
Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?
Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images.
ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems
This paper introduces a new database of voice recordings with the goal of supporting research on vulnerabilities and protection of voice-controlled systems (VCSs).
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.
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.
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.
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.
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).
Enhancing Large Language Model with Self-Controlled Memory Framework
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.
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.
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.
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.
Robust Outlier Rejection for 3D Registration with Variational Bayes
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
RotationDrag: Point-based Image Editing with Rotated Diffusion Features
Our method tracks handle points more precisely by utilizing the feature map of the rotated images, thus ensuring precise optimization and high image fidelity.
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.
SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks
Single image super resolution is a very important computer vision task, with a wide range of applications.
Ranked #34 on
Image Super-Resolution
on BSD100 - 4x upscaling
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.
Mixed Link Networks
Basing on the analysis by revealing the equivalence of modern networks, we find that both ResNet and DenseNet are essentially derived from the same "dense topology", yet they only differ in the form of connection -- addition (dubbed "inner link") vs. concatenation (dubbed "outer link").
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.
VIPTR: A Vision Permutable Extractor for Fast and Efficient Scene Text Recognition
In this work, we propose the VIsion Permutable extractor for fast and efficient scene Text Recognition (VIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR.
Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
However, these models struggle to effectively suppress the generation of undesired content, which is explicitly requested to be omitted from the generated image in the prompt.
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.
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.
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.
Fine-Grained Visual Prompting
Previous works have suggested that incorporating visual prompts, such as colorful boxes or circles, can improve the ability of models to recognize objects of interest.
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.
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.
AutoOptLib: Tailoring Metaheuristic Optimizers via Automated Algorithm Design
In response, this paper proposes AutoOptLib, the first platform for accessible automated design of metaheuristic optimizers.
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.
FinPT: Financial Risk Prediction with Profile Tuning on Pretrained Foundation Models
To tackle these issues, we propose FinPT and FinBench: the former is a novel approach for financial risk prediction that conduct Profile Tuning on large pretrained foundation models, and the latter is a set of high-quality datasets on financial risks such as default, fraud, and churn.
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.
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.
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.
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.
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.
SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation
In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?"
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).
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.
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.
Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation
The merits of the proposed MCTL are four-fold: 1) the concept of manifold criterion (MC) is first proposed as a measure validating the distribution matching across domains, and domain adaptation is achieved if the MC is satisfied; 2) the proposed MC can well guide the generation of the intermediate domain sharing similar distribution with the target domain, by minimizing the local domain discrepancy; 3) a global generative discrepancy metric (GGDM) is presented, such that both the global and local discrepancy can be effectively and positively reduced; 4) a simplified version of MCTL called MCTL-S is presented under a perfect domain generation assumption for more generic learning scenario.
Densely Connected Bidirectional LSTM with Applications to Sentence Classification
Deep neural networks have recently been shown to achieve highly competitive performance in many computer vision tasks due to their abilities of exploring in a much larger hypothesis space.
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.
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.
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
We propose Knowledgeable Prefix Tuning (KnowPrefix-Tuning), a two-stage tuning framework, bypassing the retrieval process in a knowledge-grounded conversation system by injecting prior knowledge into the lightweight knowledge prefix.
LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection
Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps).
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.
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.
Creative Birds: Self-Supervised Single-View 3D Style Transfer
Our focus lies primarily on birds, a popular subject in 3D reconstruction, for which no existing single-view 3D transfer methods have been developed. The method we propose seeks to generate a 3D mesh shape and texture of a bird from two single-view images.
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
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.
MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extraction
Cross-lingual open information extraction aims to extract structured information from raw text across multiple languages.
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.
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.
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.
TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer
To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects.
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.
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.
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.
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.
Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
Log parsing, which entails transforming raw log messages into structured templates, constitutes a critical phase in the automation of log analytics.
Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift
Theoretically, we find that Dropout would shift the variance of a specific neural unit when we transfer the state of that network from train to test.
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.
Divide and Conquer: Hybrid Pre-training for Person Search
To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data.
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.
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.
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.
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.
Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch
Nowadays, class-mismatch problem has drawn intensive attention in Semi-Supervised Learning (SSL), where the classes of labeled data are assumed to be only a subset of the classes of unlabeled data.
Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity.
Greedy Graph Searching for Vascular Tracking in Angiographic Image Sequences
The vascular branch was described using a vascular centerline extraction method with multi-probability fusion-based topology optimization.
Walk-Steered Convolution for Graph Classification
As an analogy to a standard convolution kernel on image, Gaussian models implicitly coordinate those unordered vertices/nodes and edges in a local receptive field after projecting to the gradient space of Gaussian parameters.
Provable Convex Co-clustering of Tensors
Our convex co-clustering (CoCo) estimator enjoys stability guarantees and its computational and storage costs are polynomial in the size of the data.
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition
To encode dynamic graphs, the constructed multi-scale local graph convolution filters, consisting of matrices of local receptive fields and signal mappings, are recursively performed on structured graph data of temporal and spatial domain.
Ranked #1 on
Skeleton Based Action Recognition
on Florence 3D
Adversarial Metric Learning
In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs.
Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
Unsupervised Image-to-Image Translation achieves spectacularly advanced developments nowadays.
Action-Attending Graphic Neural Network
The motion analysis of human skeletons is crucial for human action recognition, which is one of the most active topics in computer vision.
Spectral Filter Tracking
Visual object tracking is a challenging computer vision task with numerous real-world applications.
Discriminative Block-Diagonal Representation Learning for Image Recognition
In particular, the elaborate BDLRR is formulated as a joint optimization problem of shrinking the unfavorable representation from off-block-diagonal elements and strengthening the compact block-diagonal representation under the semi-supervised framework of low-rank representation.
LightRNN: Memory and Computation-Efficient Recurrent Neural Networks
Based on the 2-Component shared embedding, we design a new RNN algorithm and evaluate it using the language modeling task on several benchmark datasets.
Tensor Graphical Model: Non-convex Optimization and Statistical Inference
We consider the estimation and inference of graphical models that characterize the dependency structure of high-dimensional tensor-valued data.
A survey of sparse representation: algorithms and applications
The main purpose of this article is to provide a comprehensive study and an updated review on sparse representation and to supply a guidance for researchers.
Inventory Control Involving Unknown Demand of Discrete Nonperishable Items - Analysis of a Newsvendor-based Policy
Inventory control with unknown demand distribution is considered, with emphasis placed on the case involving discrete nonperishable items.
Stochastic Behavior of the Nonnegative Least Mean Fourth Algorithm for Stationary Gaussian Inputs and Slow Learning
Some system identification problems impose nonnegativity constraints on the parameters to estimate due to inherent physical characteristics of the unknown system.
Sparse Deep Stacking Network for Image Classification
Luckily, a simplified neural network module (SNNM) has been proposed to directly learn the discriminative dictionaries for avoiding the expensive inference.
Feature Engineering for Map Matching of Low-Sampling-Rate GPS Trajectories in Road Network
Map matching of GPS trajectories from a sequence of noisy observations serves the purpose of recovering the original routes in a road network.
Feature Selection in Conditional Random Fields for Map Matching of GPS Trajectories
Map matching of the GPS trajectory serves the purpose of recovering the original route on a road network from a sequence of noisy GPS observations.
Unsupervised Pretraining Encourages Moderate-Sparseness
It is well known that direct training of deep neural networks will generally lead to poor results.
Nuclear Norm based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes
Compared with the current regression methods, the proposed Nuclear Norm based Matrix Regression (NMR) model is more robust for alleviating the effect of illumination, and more intuitive and powerful for removing the structural noise caused by occlusion.
When Work Matters: Transforming Classical Network Structures to Graph CNN
In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem.
Ranked #3 on
Graph Classification
on IMDb-B
Person Search via A Mask-Guided Two-Stream CNN Model
In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification~(re-ID).
Triple Attention Mixed Link Network for Single Image Super Resolution
Single image super resolution is of great importance as a low-level computer vision task.
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition
In a Co-LSTM unit, each sub-memory unit stores individual motion information, while this Co-LSTM unit selectively integrates and stores inter-related motion information between multiple interacting persons from multiple sub-memory units via the cell gate and co-memory cell, respectively.
Ranked #1 on
Human Interaction Recognition
on UT
Regularized Robust Coding for Face Recognition
Recently the sparse representation based classification (SRC) has been proposed for robust face recognition (FR).
Gaussian-Induced Convolution for Graphs
In this work, we propose a Gaussian-induced convolution (GIC) framework to conduct local convolution filtering on irregular graphs.
Ranked #3 on
Graph Classification
on PTC
Large Margin Discriminant Dimensionality Reduction in Prediction Space
We argue that the intermediate mapping, e. g. boosting predictor, is preserving the discriminant aspects of the data and by controlling the dimension of this mapping it is possible to achieve discriminant low dimensional representations for the data.
Occluded Pedestrian Detection Through Guided Attention in CNNs
In this paper, we aim to propose a simple and compact method based on the FasterRCNN architecture for occluded pedestrian detection.
Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation
In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks.
Ranked #76 on
Semantic Segmentation
on NYU Depth v2
Context-Dependent Diffusion Network for Visual Relationship Detection
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images.
Learning with Inadequate and Incorrect Supervision
To address label insufficiency, we use a graph to bridge the data points so that the label information can be propagated from the scarce labeled examples to unlabeled examples along the graph edges.
Sparse Tensor Additive Regression
Tensors are becoming prevalent in modern applications such as medical imaging and digital marketing.
A Regularization Approach for Instance-Based Superset Label Learning
As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms.
Ensemble Teaching for Hybrid Label Propagation
More importantly, HyDEnT conducts propagation under the guidance of an ensemble of teachers.
Online Adaptation through Meta-Learning for Stereo Depth Estimation
Our proposal is evaluated on the wellestablished KITTI dataset, where we show that our online method is competitive withstate of the art algorithms trained in a batch setting.
Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation
In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation.
Ranked #51 on
Semantic Segmentation
on NYU Depth v2
SHALE: An Efficient Algorithm for Allocation of Guaranteed Display Advertising
Motivated by the problem of optimizing allocation in guaranteed display advertising, we develop an efficient, lightweight method of generating a compact {\em allocation plan} that can be used to guide ad server decisions.
Data Structures and Algorithms
Robust Classification with Sparse Representation Fusion on Diverse Data Subsets
It performs Sparse Representation Fusion based on the Diverse Subset of training samples (SRFDS), which reduces the impact of randomness of the sample set and enhances the robustness of classification results.
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 #18 on
Fine-Grained Image Classification
on NABirds
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Visual Categorization
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.
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).
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Spatial Transformer Point Convolution
In this paper, we propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Aspect-Based Sentiment Analysis
Aspect Category Sentiment Analysis
+1
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.
Ranked #1 on
Traffic Prediction
on SZ-Taxi
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.
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.
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.
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.
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.
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.
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.
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.
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
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.
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.
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.
A Survey of Knowledge Enhanced Pre-trained Models
Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) 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.
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.
Scribble-Supervised Semantic Segmentation Inference
In this paper, we propose a progressive segmentation inference (PSI) framework to tackle with scribble-supervised semantic segmentation.
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.
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.
Neural BRDFs: Representation and Operations
Bidirectional reflectance distribution functions (BRDFs) are pervasively used in computer graphics to produce realistic physically-based appearance.
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.
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.
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.
Learn Interpretable Word Embeddings Efficiently with von Mises-Fisher Distribution
Results show that our model can outperform the dominant models consistently in these tasks.
