ACM Multimedia

7,758 papers2,320 directions
ACM Multimedia is a research venue established in 1993 that focuses on the intersection of multimedia systems and artificial intelligence. With over 10,800 papers published through 2025, it serves as a central hub for research involving multiple data modalities, including text, image, video, and audio. The venue is characterized by its emphasis on how machine learning models can process, synthesize, and interpret complex multimodal information. Research at ACM Multimedia covers a broad spectrum of AI-driven topics. Key areas of investigation include dynamic gating for multimodal feature fusion, the development of multimodal foundation models, and the scaling of generative models for high-resolution visual synthesis. The venue also publishes work on affective computing, such as bridging the affective gap in computer vision and using continuous dimensional models. Recent contributions explore efficiency through lightweight adapters for frozen backbones and neural video compression for real-time deployment. The venue addresses diverse applications ranging from social media analysis, such as detecting toxicity in memes and fake news, to specialized fields like medical imaging and marketing strategy co-creation. Prolific contributors to the venue include researchers such as Tat-Seng Chua, Xian-Sheng Hua, Meng Wang, and Shuicheng Yan. Through its focus on structural and perceptual alignment, spectral-decomposed prompting, and spatial-spectral fusion, ACM Multimedia facilitates the development of tools and methodologies for change detection and immersive content generation.

Papers by Year

2026 4
2025 1,231
2024 1,176
2023 899
2022 696
2021 572
2020 497
2019 294
2018 246
2017 209
2016 187
2015 177
2014 160
2013 145
2012 193
2011 203
2010 192
2009 140
2008 101
2007 89
2006 92
2005 83
2004 69
2003 41
2002 34
2001 28
2000 24
1998 7
1997 13
1996 7
1995 10
1994 6
1993 7

Top Research Directions

Research directions most represented by papers from this venue.

The Cross Modal Representation Gap 20
Exploiting Temporal Redundancy in Video Neural Networks 18
The Decoupling of Visual Perception and Logical Reasoning 13
Composite Loss Functions for Perceptual Image Restoration 12
Cross-Modal Attention Fusion for Heterogeneous Data Integration 11
Hierarchical Temporal Modeling for Long Video Understanding 11
Compressing Large Foundation Models via Knowledge Distillation 11
Visual Grounding and Hallucination in Vision Language Models 11
The Mechanics of Synergistic Information in Multimodal Fusion 11
3D Gaussian Splatting for Photorealistic Scene Representation 10
Shared Representation Learning via Simultaneous Multi-Task Training 10
Aligning Global Semantics with Local Spatial Precision 10
Adversarial Training for Domain Invariant Representations 10
3D Convolutions for Spatiotemporal Feature Learning 10
Asymmetric Spatiotemporal Decoupling for Video Models 10

Top Authors

AuthorPapers
Tat-Seng Chua120
Xian-Sheng Hua97
Meng Wang95
Changsheng Xu92
Qingming Huang87
Shuicheng YAN86
Heng Tao Shen75
Liqiang Nie70
Zheng-Jun Zha70
Yu-Gang Jiang65
Rongrong Ji63
Jinhui Tang61
Yang Yang60
Mohan Kankanhalli59
Nicu Sebe59
Richang Hong56
Wenwu Zhu56
Tao Mei55
Yongdong Zhang55
Roger Zimmermann54

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Progressive Cross-modal Knowledge Distillation for Human Action Recognition2022
Progressive Limb-Aware Virtual Try-On2022
Progressive Spatial-temporal Collaborative Network for Video Frame Interpolation2022
Progressive Tree-Structured Prototype Network for End-to-End Image Captioning2022
Progressive Unsupervised Learning of Local Descriptors2022
Prompt-based Zero-shot Video Moment Retrieval2022
Prompting for Multi-Modal Tracking2022
Prototype-based Selective Knowledge Distillation for Zero-Shot Sketch Based Image Retrieval2022
Proxy Probing Decoder for Weakly Supervised Object Localization: A Baseline Investigation2022
Purifier: Plug-and-play Backdoor Mitigation for Pre-trained Models Via Anomaly Activation Suppression2022
Pursuing Knowledge Consistency: Supervised Hierarchical Contrastive Learning for Facial Action Unit Recognition2022
PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis2022
Pyramidal Transformer with Conv-Patchify for Person Re-identification2022
PYSKL: Towards Good Practices for Skeleton Action Recognition2022
QoE-aware Download Control and Bitrate Adaptation for Short Video Streaming2022
QoEVMA'22: 2nd Workshop on Quality of Experience (QoE) in Visual Multimedia Applications2022
Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity2022
Query-driven Generative Network for Document Information Extraction in the Wild2022
Query Prior Matters: A MRC Framework for Multimodal Named Entity Recognition2022
Rail Detection: An Efficient Row-based Network and a New Benchmark2022
Rate-Distortion-Guided Learning Approach with Cross-Projection Information for V-PCC Fast CU Decision2022
Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition2022
Real-time Semantic Segmentation with Parallel Multiple Views Feature Augmentation2022
Real-time Streaming Video Denoising with Bidirectional Buffers2022
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors2022
Recipe-oriented Food Logging for Nutritional Management2022
ReCoRo: Region-Controllable Robust Light Enhancement with User-Specified Imprecise Masks2022
Recurrent Meta-Learning against Generalized Cold-start Problem in CTR Prediction2022
Reducing the Vision and Language Bias for Temporal Sentence Grounding2022
RefCrowd: Grounding the Target in Crowd with Referring Expressions2022
Reflecting on Experiences for Response Generation2022
ReFormer: The Relational Transformer for Image Captioning2022
ReFu: Refine and Fuse the Unobserved View for Detail-Preserving Single-Image 3D Human Reconstruction2022
Relational Representation Learning in Visually-Rich Documents2022
Relation-enhanced Negative Sampling for Multimodal Knowledge Graph Completion2022
Relative Alignment Network for Source-Free Multimodal Video Domain Adaptation2022
ReLyMe: Improving Lyric-to-Melody Generation by Incorporating Lyric-Melody Relationships2022
REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfer2022
Repainting and Imitating Learning for Lane Detection2022
Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis2022
Reproducibility Companion Paper: Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies2022
RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization2022
Restoration of Analog Videos Using Swin-UNet2022
Rethinking Open-World Object Detection in Autonomous Driving Scenarios2022
Rethinking Optical Flow Methods for Micro-Expression Spotting2022
Rethinking Super-Resolution as Text-Guided Details Generation2022
Rethinking the Mechanism of the Pattern Pruning and the Circle Importance Hypothesis2022
Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective2022
Rethinking the Reference-based Distinctive Image Captioning2022
Rethinking the Vulnerability of DNN Watermarking: Are Watermarks Robust against Naturalness-aware Perturbations?2022

« prev Page 76/156 next »