IEEE Trans. Multimedia

4,610 papers1,225 directions
IEEE Transactions on Multimedia serves as a venue for research at the intersection of multimedia systems and artificial intelligence. The publication covers a broad range of topics related to multimedia intelligence, focusing on how machine learning techniques are applied to process, analyze, and interpret complex data. Research often explores the integration of general knowledge into image representation learning and the development of multimodal network learning for applications such as social-aware recommendation systems. The venue publishes work on various computer vision tasks, including fine-grained recognition, pedestrian detection, and salient object detection. Specific technical directions represented in the literature include the use of multi-receptive-field networks for image super-resolution, sequential visual search using recurrent attention models, and methods for mitigating redundancy in multi-head attention mechanisms. Additionally, research addresses structural challenges in deep learning, such as internal ensembling through multi-exit architectures and boundary optimization techniques to overcome shrinking bias. Contributions to the venue frequently involve weakly supervised discovery of object parts and the resolution of local visual ambiguities through global context. Prolific contributors to this body of work include researchers such as Shuicheng Yan, Wenwu Zhu, Meng Wang, and Jiashi Feng. The venue’s output reflects a consistent focus on advancing spatial recurrent neural networks and dense connection strategies to improve the accuracy and efficiency of multimedia processing and distraction diagnosis in salient object detection.

Papers by Year

2026 374
2025 710
2024 770
2023 760
2022 424
2021 376
2020 278
2019 225
2018 219
2017 183
2016 158
2015 126
2014 115
2013 120
2012 99
2011 74
2010 46
2009 68
2008 66
2007 68
2006 46
2005 38
2004 28
2003 10
2002 17
2001 10
2000 3
1999 5

Top Research Directions

Research directions most represented by papers from this venue.

The Cross Modal Representation Gap 11
Robust Identity Representation for Person Re-identification 9
Exploiting Temporal Redundancy in Video Neural Networks 9
Adversarial Training for Domain Invariant Representations 8
Overcoming the Deaf Response in Multimodal AI 8
The Perceptual Misalignment of Image Quality Metrics 7
Generalizing Deep Learning Methods Beyond Image Classification 7
Mitigating Error Propagation in Pseudo Labeling 7
Asymmetric Spatiotemporal Decoupling for Video Models 6
Cross-Modal Attention Fusion for Heterogeneous Data Integration 6
Hierarchical Temporal Modeling for Long Video Understanding 6
The Hyperparameter Tuning Burden in Specialized Machine Learning Models 6
Resolving Kinematic Ambiguity in Skeleton Based Action Recognition 5
Learning from Incomplete Multi-View Data 5
Hierarchical Feature Fusion across Network Depths 5

Top Authors

AuthorPapers
Changsheng Xu96
Meng Wang49
Richang Hong46
Xinbo Gao43
Yongdong Zhang43
Qingming Huang42
Shiqi Wang38
Guangtao Zhai37
Houqiang Li37
Shuicheng YAN37
Anan Liu35
Xian-Sheng Hua35
Yi Yang35
Liqiang Nie34
Wengang Zhou34
Yao Zhao32
Xuelong Li30
Zheng-Jun Zha30
Tat-Seng Chua28
Weisi Lin28

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Spatiotemporal Dilated Convolution With Uncertain Matching for Video-Based Crowd Estimation2022
Spatio-Temporal Pain Estimation Network With Measuring Pseudo Heart Rate Gain2022
Spatiotemporal Saliency Representation Learning for Video Action Recognition2022
SPGNet: Serial and Parallel Group Network2022
SPG-VTON: Semantic Prediction Guidance for Multi-Pose Virtual Try-on2022
SRDRL: A Blind Super-Resolution Framework With Degradation Reconstruction Loss2022
Structured Attention Network for Referring Image Segmentation2022
Style Normalization and Restitution for Domain Generalization and Adaptation2022
Suppressing Biased Samples for Robust VQA2022
TANet: Target Attention Network for Video Bit-Depth Enhancement2022
TaoHighlight: Commodity-Aware Multi-Modal Video Highlight Detection in E-Commerce2022
Targeted Attack of Deep Hashing Via Prototype-Supervised Adversarial Networks2022
Tear the Image Into Strips for Style Transfer2022
Temporal Cross-Layer Correlation Mining for Action Recognition2022
Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection2022
TERA: Screen-to-Camera Image Code With Transparency, Efficiency, Robustness and Adaptability2022
The Model May Fit You: User-Generalized Cross-Modal Retrieval2022
ToF and Stereo Data Fusion Using Dynamic Search Range Stereo Matching2022
Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes2022
Toward Rendering-Latency Reduction for Composable Web Services via Priority-Based Object Caching2022
Towards Analysis-Friendly Face Representation With Scalable Feature and Texture Compression2022
Towards Fast and Robust Real Image Denoising With Attentive Neural Network and PID Controller2022
Towards Multi-Domain Face Synthesis Via Domain-Invariant Representations and Multi-Level Feature Parts2022
Tripartite Graph Regularized Latent Low-Rank Representation for Fashion Compatibility Prediction2022
TWGAN: Twin Discriminator Generative Adversarial Networks2022
Two Exposure Fusion Using Prior-Aware Generative Adversarial Network2022
Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection2022
Underwater Image Enhancement With Lightweight Cascaded Network2022
Underwater Image Quality Assessment: Subjective and Objective Methods2022
Unmanned Aircraft System Aided Adaptive Video Streaming: A Joint Optimization Approach2022
Unpaired Image Captioning With semantic-Constrained Self-Learning2022
Unreliable-to-Reliable Instance Translation for Semi-Supervised Pedestrian Detection2022
Unsupervised Image and Text Fusion for Travel Information Enhancement2022
Unsupervised Image-to-Image Translation via Pre-Trained StyleGAN2 Network2022
Video-Based Point Cloud Compression Artifact Removal2022
Video Frame Interpolation via Generalized Deformable Convolution2022
Video Quality Assessment With Serial Dependence Modeling2022
View-Invariant Human Action Recognition Via View Transformation Network (VTN)2022
Voxel Structure-Based Mesh Reconstruction From a 3D Point Cloud2022
V-SVR+: Support Vector Regression With Variational Privileged Information2022
WAFP-Net: Weighted Attention Fusion Based Progressive Residual Learning for Depth Map Super-Resolution2022
Weakly-Supervised Facial Expression Recognition in the Wild With Noisy Data2022
Weakly Supervised Temporal Adjacent Network for Language Grounding2022
Zero-Shot Learning Based on Quality-Verifying Adversarial Network2022
Zero-Shot Single-Microphone Sound Classification and Localization in a Building Via the Synthesis of Unseen Features2022
Zero-Shot Video Event Detection With High-Order Semantic Concept Discovery and Matching2022
Zwei: A Self-Play Reinforcement Learning Framework for Video Transmission Services2022
3D Face Reconstruction From A Single Image Assisted by 2D Face Images in the Wild2021
3D Pose Estimation Based on Reinforce Learning for 2D Image-Based 3D Model Retrieval2021
3D Skeletal Gesture Recognition via Discriminative Coding on Time-Warping Invariant Riemannian Trajectories2021

« prev Page 52/93 next »