Search Results for author:
Found 24 papers, 2 papers with code
Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method
In this paper, we focus on the task of UHD image deraining, and contribute the first large-scale UHD image deraining dataset, 4K-Rain13k, that contains 13, 000 image pairs at 4K resolution.
Manifold-based Incomplete Multi-view Clustering via Bi-Consistency Guidance
Moreover, to preserve the consistency information among multiple views, MIMB implements a biconsistency guidance strategy with reverse regularization of the consensus representation and proposes a manifold embedding measure for exploring the hidden structure of the recovered data.
Scene-Adaptive Person Search via Bilateral Modulations
In SEAS, a Background Modulation Network (BMN) is designed to encode the feature extracted from the detected bounding box into a multi-granularity embedding, which reduces the input of background noise from multiple levels with norm-aware.
Fast One-Stage Unsupervised Domain Adaptive Person Search
Unsupervised person search aims to localize a particular target person from a gallery set of scene images without annotations, which is extremely challenging due to the unexpected variations of the unlabeled domains.
DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement
To solve this issue, previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features, limiting the generalization and adaptability of the model.
IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater
In underwater environments, variations in suspended particle concentration and turbidity cause severe image degradation, posing significant challenges to image enhancement (IE) and object detection (OD) tasks.
Graph-Collaborated Auto-Encoder Hashing for Multi-view Binary Clustering
To address the above issues, we propose a hashing algorithm based on auto-encoders for multi-view binary clustering, which dynamically learns affinity graphs with low-rank constraints and adopts collaboratively learning between auto-encoders and affinity graphs to learn a unified binary code, called Graph-Collaborated Auto-Encoder Hashing for Multi-view Binary Clustering (GCAE).
Unsupervised Vehicle Re-identification with Progressive Adaptation
For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''.
Unsupervised Vehicle Re-Identification
Vehicle Re-Identification
Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification
In TCPM, triplet-center loss is introduced to ensure each part of vehicle features extracted has intra-class consistency and inter-class separability.
Attribute-guided Feature Learning Network for Vehicle Re-identification
Specially, an attribute-guided module is proposed in AGNet to generate the attribute mask which could inversely guide to select discriminative features for category classification.
Eliminating cross-camera bias for vehicle re-identification
Vehicle re-identification (reID) often requires recognize a target vehicle in large datasets captured from multi-cameras.
Graph-based Multi-view Binary Learning for Image Clustering
To address these problems, we propose a novel binary code algorithm for clustering, which adopts graph embedding to preserve the original data structure, called (Graph-based Multi-view Binary Learning) GMBL in this paper.
Kernelized Multiview Subspace Analysis by Self-weighted Learning
With the popularity of multimedia technology, information is always represented or transmitted from multiple views.
Jointly Adversarial Network to Wavelength Compensation and Dehazing of Underwater Images
Different from most of previous underwater image enhancement methods that compute light attenuation along object-camera path through hazy image formation model, we propose a novel jointly wavelength compensation and dehazing network (JWCDN) that takes into account the wavelength attenuation along surface-object path and the scattering along object-camera path simultaneously.
Purifying Real Images with an Attention-guided Style Transfer Network for Gaze Estimation
Different from the previous methods, this paper try to purify real image by extracting discriminative and robust features to convert outdoor real images to indoor synthetic images.
Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification
To address this problem, this paper proposes a domain adaptation framework for vehicle reID (DAVR), which narrows the cross-domain bias by fully exploiting the labeled data from the source domain to adapt the target domain.
Co-regularized Multi-view Sparse Reconstruction Embedding for Dimension Reduction
However, facing with features from multiple views, it's difficult for most dimension reduction methods to fully comprehended multi-view features and integrate compatible and complementary information from these features to construct low-dimensional subspace directly.
Mask-guided Style Transfer Network for Purifying Real Images
To solve this problem, the previous method learned a model to improve the realism of the synthetic images.
Self-Weighted Multiview Metric Learning by Maximizing the Cross Correlations
With the development of multimedia time, one sample can always be described from multiple views which contain compatible and complementary information.
Cross Domain Knowledge Transfer for Unsupervised Vehicle Re-identification
Vehicle re-identification (reID) is to identify a target vehicle in different cameras with non-overlapping views.
Purifying Naturalistic Images through a Real-time Style Transfer Semantics Network
To solve this problem, the previous method learned a model to improve the realism of the synthetic image.
Multi-feature Distance Metric Learning for Non-rigid 3D Shape Retrieval
To address these issue, a novel multi-feature distance metric learning method for non-rigid 3D shape retrieval is presented in this study, which can make full use of the complimentary geometric information from multiple shape features by utilizing the KL-divergences.
Auto-weighted Mutli-view Sparse Reconstructive Embedding
Therefore, it is essential to fully exploit the complementary information embedded in multiple views to enhance the performances of many tasks.
Guiding Intelligent Surveillance System by learning-by-synthesis gaze estimation
In an attempt to address this issue, previous method is to improve the realism of synthetic images by learning a model.
