Search Results for author:
Found 68 papers, 24 papers with code
An Asymmetric Modeling for Action Assessment
However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e. g., between persons and objects); and this limitation undermines their ability to assess actions containing asymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions.
CoCPF: Coordinate-based Continuous Projection Field for Ill-Posed Inverse Problem in Imaging
As a result, CoCPF can accurately estimate the internal measurements between SV projections (i. e., DV sinograms), producing high-quality CT images after re-projection.
VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation
Text-to-3D generation aims to create 3D assets from text-to-image diffusion models.
Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
While existing methods simply align the person appearance to the target pose, they are prone to overfitting due to the lack of a high-level semantic understanding on the source person image.
Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion
We introduce a two-stage pipeline to effectively train our network: Stage I utilizes inter-speech contrastive learning to model fine-grained emotion and intra-speech disentanglement learning to better separate emotion and content.
MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer.
Ranked #2 on
Universal Domain Adaptation
on Office-31
GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification
Class imbalance is the phenomenon that some classes have much fewer instances than others, which is ubiquitous in real-world graph-structured scenarios.
HomoGCL: Rethinking Homophily in Graph Contrastive Learning
Contrastive learning (CL) has become the de-facto learning paradigm in self-supervised learning on graphs, which generally follows the "augmenting-contrasting" learning scheme.
One-step Bipartite Graph Cut: A Normalized Formulation and Its Application to Scalable Subspace Clustering
The bipartite graph structure has shown its promising ability in facilitating the subspace clustering and spectral clustering algorithms for large-scale datasets.
CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution
Medical image arbitrary-scale super-resolution (MIASSR) has recently gained widespread attention, aiming to super sample medical volumes at arbitrary scales via a single model.
Weakly Supervised Semantic Segmentation of Echocardiography Videos via Multi-level Features Selection
To improve the generalization of our model to different echocardiography images, we propose Pseudo-Segmentation Penalty loss function.
Ranked #2 on
LV Segmentation
on Echonet-Dynamic
Adaptively-weighted Integral Space for Fast Multiview Clustering
In view of this, we propose an Adaptively-weighted Integral Space for Fast Multiview Clustering (AIMC) with nearly linear complexity.
Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
Deep clustering has shown its promising capability in joint representation learning and clustering via deep neural networks.
Vision Transformer for Contrastive Clustering
Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning.
DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks
In view of this, this paper presents a Deep Clustering via Ensembles (DeepCluE) approach, which bridges the gap between deep clustering and ensemble clustering by harnessing the power of multiple layers in deep neural networks.
Strongly Augmented Contrastive Clustering
In this paper, we present an end-to-end deep clustering approach termed Strongly Augmented Contrastive Clustering (SACC), which extends the conventional two-augmentation-view paradigm to multiple views and jointly leverages strong and weak augmentations for strengthened deep clustering.
Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity
Then, a set of diversified base clusterings for different view groups are obtained via fast graph partitioning, which are further formulated into a unified bipartite graph for final clustering in the late-stage fusion.
G$^3$SR: Global Graph Guided Session-based Recommendation
G$^3$SR decomposes the session-based recommendation workflow into two steps.
Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations
Extensive experiments show that our method can significantly outperform state-of-the-art adversarially robust FSIC methods on two standard benchmarks.
Modeling 3D Layout for Group Re-Identification
To the best of our knowledge, 3DT is the first work to address GReID with 3D perspective, and the City1M is the currently largest dataset.
BCFNet: A Balanced Collaborative Filtering Network with Attention Mechanism
Representation learning tries to learn a common low dimensional space for the representations of users and items.
Predictive Feature Learning for Future Segmentation Prediction
In the latent feature learned by the autoencoder, global structures are enhanced and local details are suppressed so that it is more predictive.
Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos
However, most existing works focus only on video dynamic information (i. e., motion information) but ignore the specific postures that an athlete is performing in a video, which is important for action assessment in long videos.
Ranked #2 on
Action Quality Assessment
on Rhythmic Gymnastic
Adaptive Interaction Modeling via Graph Operations Search
We propose to search the network structures with differentiable architecture search mechanism, which learns to construct adaptive structures for different videos to facilitate adaptive interaction modeling.
Exploiting Monolingual Data at Scale for Neural Machine Translation
In this work, we study how to use both the source-side and target-side monolingual data for NMT, and propose an effective strategy leveraging both of them.
Ranked #1 on
Machine Translation
on WMT2016 English-German
(SacreBLEU metric, using extra
training data)
Machine Translation With Weakly Paired Documents
1) We provide a simple approach to mine implicitly bilingual sentence pairs from document pairs which can then be used as supervised training signals.
Contour Loss: Boundary-Aware Learning for Salient Object Segmentation
Yet the Contour Loss emphasizes on the local saliency.
Learnable Parameter Similarity
Most of the existing approaches focus on specific visual tasks while ignoring the relations between them.
A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
In this paper, we design a teacher-student learning framework to learn an occlusion-robust model from the full-body person domain to the occluded person domain.
Depth Growing for Neural Machine Translation
While very deep neural networks have shown effectiveness for computer vision and text classification applications, how to increase the network depth of neural machine translation (NMT) models for better translation quality remains a challenging problem.
Ranked #11 on
Machine Translation
on WMT2014 English-French
EdMot: An Edge Enhancement Approach for Motif-aware Community Detection
Based on the new edge set, the original connectivity structure of the input network is enhanced to generate a rewired network, whereby the motif-based higher-order structure is leveraged and the hypergraph fragmentation issue is well addressed.
Ranked #1 on
Community Detection
on Cora
Social and Information Networks Physics and Society 97R40
Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
Learning a Re-ID model with bag-level annotation is called the weakly supervised Re-ID problem.
Ranked #2 on
Person Re-Identification
on SYSU-30k
Unsupervised Person Re-identification by Soft Multilabel Learning
To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID.
Ranked #84 on
Person Re-Identification
on DukeMTMC-reID
Ultra-Scalable Spectral Clustering and Ensemble Clustering
Experiments on various large-scale datasets have demonstrated the scalability and robustness of our algorithms.
Ranked #3 on
Image/Document Clustering
on pendigits
Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification
With the discovered underlying person structure, the RLD method builds a bridge between the global and local feature representation and thus improves the capacity of feature representation for person re-ID.
DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System
To solve this problem, many methods have been studied, which can be generally categorized into two types, i. e., representation learning-based CF methods and matching function learning-based CF methods.
Spatial-Temporal Person Re-identification
In this paper, we propose a novel two-stream spatial-temporal person ReID (st-ReID) framework that mines both visual semantic information and spatial-temporal information.
Ranked #1 on
Person Re-Identification
on Market-1501
(using extra training data)
M2M-GAN: Many-to-Many Generative Adversarial Transfer Learning for Person Re-Identification
Cross-domain transfer learning (CDTL) is an extremely challenging task for the person re-identification (ReID).
Enhanced Ensemble Clustering via Fast Propagation of Cluster-wise Similarities
Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information.
Learning to Teach with Dynamic Loss Functions
Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher).
Deep Bilinear Learning for RGB-D Action Recognition
In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition.
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter
Many previous works have discussed the relationship between error propagation and the \emph{accuracy drop} (i. e., the left part of the translated sentence is often better than its right part in left-to-right decoding models) problem.
A Study of Reinforcement Learning for Neural Machine Translation
Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system.
Early action prediction by soft regression
Our formulation of soft regression framework 1) overcomes a usual assumption in existing early action prediction systems that the progress level of on-going sequence is given in the testing stage; and 2) presents a theoretical framework to better resolve the ambiguity and uncertainty of subsequences at early performing stage.
Ranked #82 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Interleaved Structured Sparse Convolutional Neural Networks
In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels.
IGCV$2$: Interleaved Structured Sparse Convolutional Neural Networks
In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels.
Occluded Person Re-identification
Person re-identification (re-id) suffers from a serious occlusion problem when applied to crowded public places.
Dimensionality's Blessing: Clustering Images by Underlying Distribution
Many high dimensional vector distances tend to a constant.
Learning View-Specific Deep Networks for Person Re-Identification
In recent years, a growing body of research has focused on the problem of person re-identification (re-id).
Adversarial Attribute-Image Person Re-identification
While attributes have been widely used for person re-identification (Re-ID) which aims at matching the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image matching task.
Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyond
The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research.
Deep Growing Learning
A bottleneck of SSL is the overfitting problem when training over the limited labeled data, especially on a complex model like a deep neural network.
RGB-Infrared Cross-Modality Person Re-Identification
To that end, matching RGB images with infrared images is required, which are heterogeneous with very different visual characteristics.
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos
We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos.
Adversarial Neural Machine Translation
The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human.
Robust Depth-based Person Re-identification
More specifically, we exploit depth voxel covariance descriptor and further propose a locally rotation invariant depth shape descriptor called Eigen-depth feature to describe pedestrian body shape.
Person Re-Identification by Camera Correlation Aware Feature Augmentation
The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion.
Jointly learning heterogeneous features for rgb-d activity recognition
The proposed model formed in a unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to exploit latent shared features across different feature channels, 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces, and 3) transferring feature-specific intermediate transforms (i-transforms) for learning fusion of heterogeneous features across datasets.
Ranked #8 on
Skeleton Based Action Recognition
on SYSU 3D
Ensemble-driven support vector clustering: From ensemble learning to automatic parameter estimation
Support vector clustering (SVC) is a versatile clustering technique that is able to identify clusters of arbitrary shapes by exploiting the kernel trick.
Robust Ensemble Clustering Using Probability Trajectories
To address these two limitations, in this paper, we propose a novel ensemble clustering approach based on sparse graph representation and probability trajectory analysis.
Locally Weighted Ensemble Clustering
Although some efforts have been made to (globally) evaluate and weight the base clusterings, yet these methods tend to view each base clustering as an individual and neglect the local diversity of clusters inside the same base clustering.
Partial Person Re-Identification
We address a new partial person re-identification (re-id) problem, where only a partial observation of a person is available for matching across different non-overlapping camera views.
Deep Ranking for Person Re-identification via Joint Representation Learning
This paper proposes a novel approach to person re-identification, a fundamental task in distributed multi-camera surveillance systems.
Learning Contour-Fragment-based Shape Model with And-Or Tree Representation
This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree.
Data-Driven Scene Understanding with Adaptively Retrieved Exemplars
In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i. e. the assigned labels of the target and the references).
Discriminatively Trained And-Or Graph Models for Object Shape Detection
In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images.
Complex Background Subtraction by Pursuing Dynamic Spatio-Temporal Models
Although it has been widely discussed in video surveillance, background subtraction is still an open problem in the context of complex scenarios, e. g., dynamic backgrounds, illumination variations, and indistinct foreground objects.
Combining Multiple Clusterings via Crowd Agreement Estimation and Multi-Granularity Link Analysis
We present the normalized crowd agreement index (NCAI) to evaluate the quality of base clusterings in an unsupervised manner and thus weight the base clusterings in accordance with their clustering validity.
