ICME

4,586 papers662 directions
The International Conference on Multimedia and Expo (ICME) is a research venue focused on the intersection of multimedia systems and artificial intelligence. Active since 2001, the conference has published over 5,700 papers, serving as a platform for technical developments in signal processing, computer vision, and machine learning. Its scope encompasses the creation, analysis, and transmission of diverse media types, including video, audio, and images. Research at ICME frequently addresses challenges in deep learning and generative modeling. Key areas of focus include video understanding through temporal sampling and action recognition, as well as image restoration and synthesis. Recent publications highlight advancements in neural compression, the sparsification of transformers, and techniques for long-tailed learning. The venue also features work on specialized applications such as deepfake detection, gait emotion recognition, and non-line-of-sight imaging, reflecting a broad interest in both foundational and applied machine learning. The venue facilitates the exploration of distributed deep learning, active object tracking, and data-free quantization. Prolific contributors to the conference include researchers such as Qingming Huang, Wen Gao, Guangtao Zhai, and Hanqing Lu. By integrating visual context and multi-modal data, ICME contributes to the development of models for complex scenarios, ranging from audio style transfer to omni-dimensional video compression for latent diffusion models.

Papers by Year

2026 2
2025 579
2024 429
2023 335
2022 275
2021 301
2020 167
2019 237
2018 126
2017 170
2016 91
2015 99
2014 135
2013 112
2012 86
2011 137
2010 108
2009 187
2008 145
2007 235
2006 196
2005 117
2004 148
2003 136
2002 7
2001 70

Top Research Directions

Research directions most represented by papers from this venue.

The Cross Modal Representation Gap 6
Generalizing Deep Learning Methods Beyond Image Classification 5
Overcoming the Computational Cost of Transformer Architectures 5
Synthetic Anomalies and Distillation for Robust Anomaly Detection 4
Preserving Tiny Features Against Spatial Resolution Degradation 4
Gated Fusion for Adaptive Feature Integration 4
Hierarchical Feature Fusion across Network Depths 4
Generalizing Deepfake Detection to Unseen Forgery Methods 4
Unified Representations via Multimodal Feature Fusion 4
Low-Rank Weight Decomposition for Efficient Model Adaptation 4
Scaling Visual Attention Beyond Quadratic Complexity 4
Cross Dataset Validation for Robust Model Generalization 4
The Performance Ceiling of Pre-trained Feature Dependency 3
Joint Classification and Metric Learning for Robust Embeddings 3
Resolving Kinematic Ambiguity in Skeleton Based Action Recognition 3

Top Authors

AuthorPapers
Qingming Huang49
Changsheng Xu41
Guangtao Zhai39
Ruimin Hu37
Houqiang Li33
Xian-Sheng Hua33
Mohan Kankanhalli30
Jinqiao Wang28
Siwei Ma28
Xiongkuo Min28
Shuqiang Jiang26
Xing Xu26
Alberto Del Bimbo25
Kiyoharu Aizawa22
Lizhuang Ma22
Tiejun Huang22
Qionghai Dai21
Wei-Ying Ma21
Xiaoyan Sun20
Yonghong Tian20

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
FFNet-M: Feature Fusion Network with Masks for Multimodal Facial Expression Recognition2021
FGF-GAN: A Lightweight Generative Adversarial Network for Pansharpening via Fast Guided Filter2021
Fine-Grained Image Retrieval Via Multiple Part-Level Feature Ensemble2021
Flexible Knowledge Distillation with an Evolutional Network Population2021
Gait Identification Based on Human Skeleton with Pairwise Graph Convolutional Network2021
Geometric Transformation-Based Network Ensemble for Open-Set Recognition2021
Global-to-Local Dynamic Feature Aggregation for Unsupervised Person Re-Identification2021
Graph Attention Neural Network for Image Restoration2021
Graph Convolutional Hourglass Networks for Skeleton-Based Action Recognition2021
Graph-in-Graph Contrastive Learning for Semi-Supervised Adaptation2021
GSS: Graph-Based Subspace Learning with Shots Initialization for few-shot Recognition2021
GSVNET: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video2021
Halder: Hierarchical Attention-Guided Learning with Detail-Refinement for Multi-Exposure Image Fusion2021
Hardware-Aware Low-Light Image Enhancement via One-Shot Neural Architecture Search with Shrinkage Sampling2021
Hazy Re-ID: An Interference Suppression Model for Domain Adaptation Person Re-Identification Under Inclement Weather Condition2021
Heatmap-Aware Pyramid Face Hallucination2021
Heterogeneous Federated Learning Through Multi-Branch Network2021
Hierarchical Representation Network With Auxiliary Tasks For Video Captioning2021
Hierarchical Transformer: Unsupervised Representation Learning for Skeleton-Based Human Action Recognition2021
High-Quality Face Sketch Synthesis via Geometric Normalization and Regularization2021
HRDNet: High-Resolution Detection Network for Small Objects2021
Image Captioning with Inherent Sentiment2021
Image Demoiréing with a Dual-Domain Distilling Network2021
Improved Lightcnn with Attention Modules for Asv Spoofing Detection2021
Improving Convolutional Networks with Boosting Attention Convolutions2021
Improving Facial Attribute Recognition by Group and Graph Learning2021
Incorporating Multimodal Cues for Advertorial Discovery2021
Infrared and Visible Image Fusion Based on Modal Feature Fusion Network and Dual Visual Decision2021
Inharmonious Region Localization2021
Input-Output Balanced Framework for Long-Tailed Lidar Semantic Segmentation2021
Interpret the Predictions of Deep Networks via Re-Label Distillation2021
Intra-Class Uncertainty Loss Function For Classification2021
IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation2021
ISTA-NET++: Flexible Deep Unfolding Network for Compressive Sensing2021
Key Facial Components Guided Micro-Expression Recognition Based on First & Second-Order Motion2021
Knowledge Transfer Based Fine-Grained Visual Classification2021
Label-Free Regional Consistency for Image-to-Image Translation2021
Label-Specific Alignment with Adversarial Multi-View Representation2021
Lavs: A Lightweight Audio-Visual Saliency Prediction Model2021
Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition2021
Learning a Tree-Structured Channel-Wise Refinement Network for Efficient Image Deraining2021
Learning Connected Attentions for Convolutional Neural Networks2021
Learning Content and Context with Language Bias for Visual Question Answering2021
Learning Controlled Semantic Embedding for Cross-Modal Retrieval2021
Learning Efficient Rotation Representation for Point Cloud via Local-Global Aggregation2021
Learning Factorized Cross-View Fusion for Multi-View Crowd Counting2021
Learning Homogeneous and Heterogeneous Co-Occurrences for Unsupervised Cross-Modal Retrieval2021
Learning Long Term Style Preserving Blind Video Temporal Consistency2021
Learning Multiple Semantic Knowledge For Cross-Domain Unsupervised Vehicle Re-Identification2021
Learning Outfit Compatibility with Graph Attention Network and Visual-Semantic Embedding2021

« prev Page 35/92 next »