Search Results for author:
Found 118 papers, 35 papers with code
Latent Augmentation For Better Graph Self-Supervised Learning
A novel graph decoder named Wiener Graph Deconvolutional Network is correspondingly designed to perform information reconstruction from augmented latent representations.
Deep Learning Eliminates Massive Dust Storms from Images of Tianwen-1
Inspired by the haze formation process on Earth, we formulate a similar visual degradation process on clean images and synthesize dusty images sharing a similar feature distribution with realistic dusty images.
Semi-Supervised Hierarchical Graph Classification
We study the node classification problem in the hierarchical graph where a 'node' is a graph instance.
Rethinking Graph Neural Networks for Anomaly Detection
Graph Neural Networks (GNNs) are widely applied for graph anomaly detection.
MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation
Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions.
Fast and Provably Convergent Algorithms for Gromov-Wasserstein in Graph Learning
In this paper, we study the design and analysis of a class of efficient algorithms for computing the Gromov-Wasserstein (GW) distance tailored to large-scale graph learning tasks.
Pyramid Grafting Network for One-Stage High Resolution Saliency Detection
An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically, guided by different source feature during decoding process.
Video Demoireing with Relation-Based Temporal Consistency
Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.
ELECRec: Training Sequential Recommenders as Discriminators
A generator, as an auxiliary model, is trained jointly with the discriminator to sample plausible alternative next items and will be thrown out after training.
Improving Contrastive Learning with Model Augmentation
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
ConTinTin: Continual Learning from Task Instructions
This work defines a new learning paradigm ConTinTin (Continual Learning from Task Instructions), in which a system should learn a sequence of new tasks one by one, each task is explained by a piece of textual instruction.
Robust facial expression recognition with global‑local joint representation learning
In the proposed method, (1) the topological structure information and texture feature of regions of interest (ROIs) are modeled as graphs and processed with graph convolutional network (GCN) to remain the topological features.
Styleverse: Towards Identity Stylization across Heterogeneous Domains
We propose a new challenging task namely IDentity Stylization (IDS) across heterogeneous domains.
A Machine Learning Paradigm for Studying Pictorial Realism: Are Constable's Clouds More Real than His Contemporaries?
European artists have sought to create life-like images since the Renaissance.
Intent Contrastive Learning for Sequential Recommendation
Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering.
RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems
Robust machine learning is an increasingly important topic that focuses on developing models resilient to various forms of imperfect data.
Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution
The distribution gap between training datasets and data encountered in production is well acknowledged.
Deconvolutional Networks on Graph Data
In this paper, we consider an inverse problem in graph learning domain -- ``given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal?"
Receptive Field Broadening and Boosting for Salient Object Detection
Moreover, Unlike multi-path parallel training, MHB randomly selects one branch each time for gradient back propagation in a boosting way.
Deconfounded Causal Collaborative Filtering
Experiments on real-world e-commerce datasets show that our method is able to deconfound unobserved confounders to achieve better recommendation performance.
Transformer-based Dual Relation Graph for Multi-label Image Recognition
Different from these researches, in this paper, we propose a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i. e., structural relation graph and semantic relation graph.
Universal Face Restoration With Memorized Modulation
Blind face restoration (BFR) is a challenging problem because of the uncertainty of the degradation patterns.
Video Forgery Detection Using Multiple Cues on Fusion of EfficientNet and Swin Transformer
The first is that capturing the general clue of artifacts is difficult.
Self-supervised Learning for Sequential Recommendation with Model Augmentation
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
Modeling Dynamic Attributes for Next Basket Recommendation
However, properly integrating them into user interest models is challenging since attribute dynamics can be diverse such as time-interval aware, periodic patterns (etc.
Heterogeneous Relational Complement for Vehicle Re-identification
The crucial problem in vehicle re-identification is to find the same vehicle identity when reviewing this object from cross-view cameras, which sets a higher demand for learning viewpoint-invariant representations.
Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing
In this paper, firstly, we propose a new complementary feature enhanced framework, in which the complementary features are learned by several complementary subtasks and then together serve to boost the performance of the primary task.
RGB-D Salient Object Detection with Ubiquitous Target Awareness
To construct our framework as well as achieving accurate salient detection results, we propose a Ubiquitous Target Awareness (UTA) network to solve three important challenges in RGB-D SOD task: 1) a depth awareness module to excavate depth information and to mine ambiguous regions via adaptive depth-error weights, 2) a spatial-aware cross-modal interaction and a channel-aware cross-level interaction, exploiting the low-level boundary cues and amplifying high-level salient channels, and 3) a gated multi-scale predictor module to perceive the object saliency in different contextual scales.
Pose-guided Inter- and Intra-part Relational Transformer for Occluded Person Re-Identification
Therefore, we propose a Pose-guided inter-and intra-part relational transformer (Pirt) for occluded person Re-Id, which builds part-aware long-term correlations by introducing transformers.
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image.
Ranked #5 on
Out-of-Distribution Detection
on CIFAR-10
Contrastive Self-supervised Sequential Recommendation with Robust Augmentation
In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues.
Mixture of Linear Models Co-supervised by Deep Neural Networks
Our main idea is a mixture of discriminative models that is trained with the guidance from a DNN.
Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
Given an image, we employ an Hourglass Network to infer all the keypoints from different persons indiscriminately as well as the guiding offsets connecting the adjacent keypoints belonging to the same persons.
Ranked #4 on
Pose Estimation
on CrowdPose
Graph-Based High-Order Relation Discovery for Fine-Grained Recognition
Fine-grained object recognition aims to learn effective features that can identify the subtle differences between visually similar objects.
Ranked #17 on
Fine-Grained Image Classification
on CUB-200-2011
FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains
In this work, we propose a novel two-stage framework named FaceInpainter to implement controllable Identity-Guided Face Inpainting (IGFI) under heterogeneous domains.
Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection
Cross-domain weakly supervised object detection aims to adapt object-level knowledge from a fully labeled source domain dataset (i. e. with object bounding boxes) to train object detectors for target domains that are weakly labeled (i. e. with image-level tags).
Ranked #3 on
Weakly Supervised Object Detection
on Clipart1k
Exploring Driving-aware Salient Object Detection via Knowledge Transfer
In this network, we construct an attentionbased knowledge transfer module to make up the knowledge difference.
Epsilon Consistent Mixup: Structural Regularization with an Adaptive Consistency-Interpolation Tradeoff
In this paper we propose $\epsilon$-Consistent Mixup ($\epsilon$mu).
Functional and spatial rewiring jointly generate convergent-divergent units in self-organizing networks
The prominence of minimizing wiring distance in the dynamic evolution of the network determines the extent to which the core is encapsulated from the rest of the network, i. e., the context-sensitivity of its computations.
Structural Similarity of Boundary Conditions and an Efficient Local Search Algorithm for Goal Conflict Identification
By taking experiments on a set of cases, we show that LOGION effectively exploits the structural similarity of BCs.
Mask-GVAE: Blind Denoising Graphs via Partition
We present Mask-GVAE, a variational generative model for blind denoising large discrete graphs, in which "blind denoising" means we don't require any supervision from clean graphs.
Graph Autoencoders with Deconvolutional Networks
Recent studies have indicated that Graph Convolutional Networks (GCNs) act as a \emph{low pass} filter in spectral domain and encode smoothed node representations.
Teaching deep learning causal effects improves predictive performance
Specifically, we first describe a Causal-Temporal Structure for temporal EHR data; then based on this structure, we estimate sequential ITE along the timeline, using sequential Propensity Score Matching (PSM); and finally, we propose a knowledge-guided neural network methodology to incorporate estimated ITE.
Learning Open Set Network with Discriminative Reciprocal Points
In this process, one of the key challenges is to reduce the risk of generalizing the inherent characteristics of numerous unknown samples learned from a small amount of known data.
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood.
Ranked #2 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Dialogue State Tracking
Multi-domain Dialogue State Tracking
TUTA: Tree-based Transformers for Generally Structured Table Pre-training
First, we devise a unified tree-based structure, called a bi-dimensional coordinate tree, to describe both the spatial and hierarchical information of generally structured tables.
Dirichlet Graph Variational Autoencoder
In this work, we present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors.
DanceIt: Music-inspired Dancing Video Synthesis
To explore the relationship between music and dance movements, we propose a cross-modal alignment module that focuses on dancing video clips, accompanied on pre-designed music, to learn a system that can judge the consistency between the visual features of pose sequences and the acoustic features of music.
Intrinsic Relationship Reasoning for Small Object Detection
In this paper, we propose a novel context reasoning approach for small object detection which models and infers the intrinsic semantic and spatial layout relationships between objects.
Cooperative Bi-path Metric for Few-shot Learning
Given base classes with sufficient labeled samples, the target of few-shot classification is to recognize unlabeled samples of novel classes with only a few labeled samples.
Permutation-based tests for discontinuities in event studies
Under a high-level condition that the observed data can be coupled by a collection of conditionally independent variables, we establish the asymptotic validity of the permutation test, allowing the sizes of the local subsamples to be either be fixed or grow to infinity.
SEKD: Self-Evolving Keypoint Detection and Description
Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks.
Is Depth Really Necessary for Salient Object Detection?
To solve this, many recent RGBD-based networks are proposed by adopting the depth map as an independent input and fuse the features with RGB information.
Ranked #1 on
RGB-D Salient Object Detection
on RGBD135
Semi-Supervised Cervical Dysplasia Classification With Learnable Graph Convolutional Network
In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance.
Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously.
Adversarial Attack on Community Detection by Hiding Individuals
It has been demonstrated that adversarial graphs, i. e., graphs with imperceptible perturbations added, can cause deep graph models to fail on node/graph classification tasks.
Single Image Dehazing Using Ranking Convolutional Neural Network
To obtain effective features for single image dehazing, this paper presents a novel Ranking Convolutional Neural Network (Ranking-CNN).
Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss
Through these two attentions, we use the Purificatory Mechanism to impose strict weights with different regions of the whole salient objects and purify results from hard-to-distinguish regions, thus accurately predicting the locations and details of salient objects.
Zooming into Face Forensics: A Pixel-level Analysis
The stunning progress in face manipulation methods has made it possible to synthesize realistic fake face images, which poses potential threats to our society.
Deep Variable-Block Chain with Adaptive Variable Selection
In this paper, we propose a framework that imposes on blocks of variables a chain structure obtained by step-wise greedy search so that the DNN architecture can leverage the constructed grid.
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one.
Ranked #8 on
Multi-Person Pose Estimation
on COCO test-dev
Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems
We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems.
Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space.
Word embedding re-examined: is the symmetrical factorization optimal?
Such linear transformation will result in these good properties.
Near-Zero-Cost Differentially Private Deep Learning with Teacher Ensembles
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
Exploring Reciprocal Attention for Salient Object Detection by Cooperative Learning
Typically, objects with the same semantics are not always prominent in images containing different backgrounds.
Distortion-adaptive Salient Object Detection in 360$^\circ$ Omnidirectional Images
Moreover, benchmarking results of the proposed baseline approach and other methods on 360$^\circ$ SOD dataset show the proposed dataset is very challenging, which also validate the usefulness of the proposed dataset and approach to boost the development of SOD on 360$^\circ$ omnidirectional scenes.
Learning Local Feature Descriptor with Motion Attribute for Vision-based Localization
For better performance, the features used for open-loop localization are required to be short-term globally static, and the ones used for re-localization or loop closure detection need to be long-term static.
Cartoon Face Recognition: A Benchmark Dataset
Recent years have witnessed increasing attention in cartoon media, powered by the strong demands of industrial applications.
Combining Reinforcement Learning and Configuration Checking for Maximum k-plex Problem
Based on the BLP and DTCC, we develop a local search algorithm named BDCC and improve it by a hyperheuristic strategy.
Private Deep Learning with Teacher Ensembles
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information.
Predicting Path Failure In Time-Evolving Graphs
Through experiments on a real-world telecommunication network and a traffic network in California, we demonstrate the superiority of LRGCN to other competing methods in path failure prediction, and prove the effectiveness of SAPE on path representation.
Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets
A multiscale shared convolution structure is adopted in the discriminator network to further supervise training the generator.
Reinforcement Learning Based Emotional Editing Constraint Conversation Generation
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers.
Semi-Supervised Graph Classification: A Hierarchical Graph Perspective
We study the node classification problem in the hierarchical graph where a `node' is a graph instance, e. g., a user group in the above example.
Ranked #10 on
Graph Classification
on D&D
Image Quality Assessment for Omnidirectional Cross-reference Stitching
Along with the development of virtual reality (VR), omnidirectional images play an important role in producing multimedia content with immersive experience.
Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency
In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model.
Ultrafast Video Attention Prediction with Coupled Knowledge Distillation
To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net.
Harmonic Unpaired Image-to-image Translation
The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the presence of artifacts and degenerated transformations.
Selectivity or Invariance: Boundary-aware Salient Object Detection
In this network, the feature selectivity at boundaries is enhanced by incorporating a boundary localization stream, while the feature invariance at interiors is guaranteed with a complex interior perception stream.
Visual Attention on the Sun: What Do Existing Models Actually Predict?
Visual attention prediction is a classic problem that seems to be well addressed in the deep learning era.
Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation
In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively.
Complementary Segmentation of Primary Video Objects with Reversible Flows
Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities.
Model-guided Multi-path Knowledge Aggregation for Aerial Saliency Prediction
After that, the visual saliency knowledge encoded in the most representative paths is selected and aggregated to improve the capability of MM-Net in predicting spatial saliency in aerial scenarios.
Coordinating Disaster Emergency Response with Heuristic Reinforcement Learning
To improve the efficiency of the emergency response in the immediate aftermath of a disaster, we propose a heuristic multi-agent reinforcement learning scheduling algorithm, named as ResQ, which can effectively schedule the rapid deployment of volunteers to rescue victims in dynamic settings.
Forecasting People's Needs in Hurricane Events from Social Network
Our proposed sequence to sequence method forecast people's needs more successfully than either of the other models.
Lifted Proximal Operator Machines
LPOM is block multi-convex in all layer-wise weights and activations.
Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification
In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet.
AirDialogue: An Environment for Goal-Oriented Dialogue Research
However, current datasets are limited in size, and the environment for training agents and evaluating progress is relatively unsophisticated.
A Fast Globally Linearly Convergent Algorithm for the Computation of Wasserstein Barycenters
When the support points of the barycenter are pre-specified, this problem can be modeled as a linear programming (LP) problem whose size can be extremely large.
ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild
A system to model the emotional expressions based on bodily movements, named ARBEE (Automated Recognition of Bodily Expression of Emotion), has also been developed and evaluated.
Hierarchical Deep Co-segmentation of Primary Objects in Aerial Videos
Primary object segmentation plays an important role in understanding videos generated by unmanned aerial vehicles.
Learning a Saliency Evaluation Metric Using Crowdsourced Perceptual Judgments
Due to the effectiveness of the learned metric, it also can be used to facilitate the development of new models for fixation prediction.
Collaborative Annotation of Semantic Objects in Images with Multi-granularity Supervisions
In this paper, we propose a human-agent collaborative annotation approach that can efficiently generate per-pixel masks of semantic objects in tagged images with multi-granularity supervisions.
Image Co-segmentation via Multi-scale Local Shape Transfer
Image co-segmentation is a challenging task in computer vision that aims to segment all pixels of the objects from a predefined semantic category.
Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion
Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms.
Aggregated Wasserstein Metric and State Registration for Hidden Markov Models
This distance quantifies the dissimilarity of GMM-HMMs by measuring both the difference between the two marginal GMMs and that between the two transition matrices.
Look, Perceive and Segment: Finding the Salient Objects in Images via Two-Stream Fixation-Semantic CNNs
Toward this end, this paper proposes two-stream fixation-semantic CNNs, whose architecture is inspired by the fact that salient objects in complex images can be unambiguously annotated by selecting the pre-segmented semantic objects that receive the highest fixation density in eye-tracking experiments.
Primary Video Object Segmentation via Complementary CNNs and Neighborhood Reversible Flow
By applying CCNN on each video frame, the spatial foregroundness and backgroundness maps can be initialized, which are then propagated between various frames so as to segment primary video objects and suppress distractors.
Embedding 3D Geometric Features for Rigid Object Part Segmentation
One stream, named AppNet, is to extract 2D appearance features from the input image.
Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering
The new clustering method is easy to use and consistently outperforms other methods on a variety of data sets.
What Is and What Is Not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors
Finding what is and what is not a salient object can be helpful in developing better features and models in salient object detection (SOD).
Detecting Masked Faces in the Wild With LLE-CNNs
Detecting masked faces (i. e., faces with occlusions) is a challenging task due to two main reasons: 1)the absence of large datasets of masked faces, and 2)the absence of facial cues from the masked regions.
CT Image Reconstruction in a Low Dimensional Manifold
In this paper, we propose a CT image reconstruction method based on the prior knowledge of the low-dimensional manifold of CT image.
Manifold Based Low-rank Regularization for Image Restoration and Semi-supervised Learning
Low-rank structures play important role in recent advances of many problems in image science and data science.
Probabilistic Multigraph Modeling for Improving the Quality of Crowdsourced Affective Data
We proposed a probabilistic approach to joint modeling of participants' reliability and humans' regularity in crowdsourced affective studies.
AutoScaler: Scale-Attention Networks for Visual Correspondence
We propose AutoScaler, a scale-attention network to explicitly optimize this trade-off in visual correspondence tasks.
A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection
Based on this dataset, this paper proposes an unsupervised baseline approach for video-based SOD by using saliency-guided stacked autoencoders.
A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration
We refer to such HMMs as Gaussian mixture model-HMM (GMM-HMM).
Modeling Photographic Composition via Triangles
The capacity of automatically modeling photographic composition is valuable for many real-world machine vision applications such as digital photography, image retrieval, image understanding, and image aesthetics assessment.
Storm Detection by Visual Learning Using Satellite Images
In our system, we extract and summarize important visual storm evidence from satellite image sequences in the way that meteorologists interpret the images.
A Data-Driven Metric for Comprehensive Evaluation of Saliency Models
To address this problem, we propose a data-driven metric for comprehensive evaluation of saliency models.
Fast Discrete Distribution Clustering Using Wasserstein Barycenter with Sparse Support
In a variety of research areas, the weighted bag of vectors and the histogram are widely used descriptors for complex objects.
Gaussian Mixture Models with Component Means Constrained in Pre-selected Subspaces
This motivates us to find a subspace by applying weighted principal component analysis to the modes of a kernel density and the class means.
Proposition m\'ethodologique pour la d\'etection automatique de Community Manager. \'Etude multilingue sur un corpus relatif \`a la Junk Food
Dans cet article, nous pr{\'e}sentons une m{\'e}thodologie pour l{'}identification de messages suspect{\'e}s d{'}{\^e}tre produits par des Community Managers {\`a} des fins commerciales d{\'e}guis{\'e}es dans des documents du Web 2. 0.
Semantic Object Segmentation via Detection in Weakly Labeled Video
Semantic object segmentation in video is an important step for large-scale multimedia analysis.
Salient Object Detection: A Benchmark
We extensively compare, qualitatively and quantitatively, 40 state-of-the-art models (28 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over 6 challenging datasets for the purpose of benchmarking salient object detection and segmentation methods.
Salient Object Detection: A Survey
Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision.
