Dual-perspective semantic-aware representation blending for multi-label image recognition with partial labels (2022-05-26T00:00:00.000000Z)

TL;DR

A dual-perspective semantic-aware representation blending (DSRB) that blends multi-granularity category-specific semantic representation across different images, from instance and prototype perspective respectively, to transfer information of known labels to complement unknown labels.

Authors

Liang Lin

22 papers

Tianshui Chen

10 papers

Tao Pu

6 papers

Hefeng Wu

6 papers

TL;DR

Authors

References64 items

Image emotion multi-label classification based on multi-graph learning

Spatial–Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation

Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

Mining Multi-Label Samples from Single Positive Labels

Large Loss Matters in Weakly Supervised Multi-Label Classification

Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations

Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels

Structured Semantic Transfer for Multi-Label Recognition with Partial Labels

GHRS: Graph-based Hybrid Recommendation System with Application to Movie Recommendation

Deep Co-Image-Label Hashing for Multi-Label Image Retrieval

Image classification with multi-view multi-instance metric learning

HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning

Deep Reinforcement Learning Framework for Category-Based Item Recommendation

Instance-weighted Central Similarity for Multi-label Image Retrieval

Learning Graph Convolutional Networks for Multi-Label Recognition and Applications

Deep-LIFT: Deep Label-Specific Feature Learning for Image Annotation

AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition

Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition

Relational Graph Learning for Grounded Video Description Generation

AdaHGNN: Adaptive Hypergraph Neural Networks for Multi-Label Image Classification

Computing Graph Neural Networks: A Survey from Algorithms to Accelerators

Asymmetric Loss For Multi-Label Classification

Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition

Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning

Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization

Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup

Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition

Interactive Multi-Label CNN Learning With Partial Labels

Hybrid Noise-Oriented Multilabel Learning

Physical-Virtual Collaboration Modeling for Intra- and Inter-Station Metro Ridership Prediction

Knowledge Graph Transfer Network for Few-Shot Recognition

Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition

Instance-Aware Representation Learning and Association for Online Multi-Person Tracking

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Deep Integration: A Multi-Label Architecture for Road Scene Recognition

Multi-Label Image Recognition With Graph Convolutional Networks

Learning a Deep ConvNet for Multi-Label Classification With Partial Labels

Learning deep similarity models with focus ranking for fabric image retrieval

Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition

mixup: Beyond Empirical Risk Minimization

Multi-label Image Recognition by Recurrently Discovering Attentional Regions

Focal Loss for Dense Object Detection

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

Multi-label convolutional neural network based pedestrian attribute classification

Learning Instance Correlation Functions for Multilabel Classification

Data-driven method for sketch-based 3D shape retrieval based on user similar draw-style recommendation

Instance-Aware Hashing for Multi-Label Image Retrieval

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Learning Deep Features for Discriminative Localization

Deep Residual Learning for Image Recognition

Learning Visual Features from Large Weakly Supervised Data

Adam: A Method for Stochastic Optimization

Context Recommendation Using Multi-label Classification

HCP: A Flexible CNN Framework for Multi-Label Image Classification

Microsoft COCO: Common Objects in Context

Multi-Label Image Categorization With Sparse Factor Representation

Technique of Image Retrieval Based on Multi-label Image Annotation

ImageNet: A large-scale hierarchical image database

A semantic learning for content-based image retrieval using analytical hierarchy process

Dynamic Mixup for Multi-Label Long-Tailed Food Ingredient Recognition

Quality Assessment for Omnidirectional Video: A Spatio-Temporal Distortion Modeling Approach

Hierarchical Ensemble of Background Models for PTZ-Based Video Surveillance

Multi-label Classification for Recommender Systems

Edinburgh Research Explorer The PASCAL Visual Object Classes (VOC) Challenge

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names