ACM Multimedia 2018

246 papers
ACM Multimedia 2018 featured 403 papers focusing on several emerging trends in multimedia research. A large portion of the work explored graph-based architectures, including graph knowledge propagation for zero-shot recognition and multi-hop aggregation for graph neural networks. Relational reasoning and structured scene graphs were also prominent, particularly for spatial reasoning and scene context-aware vision. In the generative domain, researchers addressed stylistic parity in music modeling and structured planning for long-form generation. The conference also highlighted advancements in efficient visual search through compact low-dimensional descriptors and large-scale image retrieval. Research topics included deep cognitive subspace clustering, supervised online hashing, and spatiotemporal networks for traffic prediction. Other areas of interest included visual sentiment analysis using mid-level semantic representations and adversarial attacks on deep neural networks. Prolific contributors to this edition included researchers such as Zheng-Jun Zha, Changsheng Xu, and Tat-Seng Chua, reflecting a broad interest in sequence-level image captioning and group activity recognition.

Top Research Directions

Research directions most represented by ACM Multimedia 2018 papers.

Composite Loss Functions for Perceptual Image Restoration 2
Dynamic Preference Modeling in Interactive Systems 2
Why Stacking Data Augmentations Degrades Performance 1
Reinforcement Learning for Adaptive Bitrate Streaming 1
Multi-Observer Gaze Aggregation for Collective Attention Mapping 1
Passive Estimation of Network Latency and Throughput 1
Adjective-Noun Pairs for Visual Sentiment Representation 1
Dynamic Adaptation of Rate Distortion Optimization 1
Jointly Learning Propensity and Outcome for Causal Inference 1
Multi-Objective Quality of Experience Optimization in Video Streaming 1
Marginal Likelihood Training for Partially Annotated Sequences 1
Discretizing Angular Spaces for Robust Orientation Estimation 1
Bridging the Performance Gap in Unsupervised Learning 1
Formal Structural Constraints in Creative Text Generation 1
Reconstructing Facial Expressions Under Head Mounted Display Occlusion 1

Top Authors

AuthorPapers
Zheng-Jun Zha9
Changsheng Xu7
Heng Tao Shen6
Jia Jia6
Qingming Huang6
Tat-Seng Chua6
Xian-Sheng Hua5
Fumin Shen4
Jingkuan Song4
Jitao Sang4
Meng Wang4
Rongrong Ji4
Shuicheng YAN4
Shuqiang Jiang4
Yongdong Zhang4
Yuxin Peng4
Axel Carlier3
Houqiang Li3
Jiaying Liu3
Jinhui Tang3

Impactful Papers

Papers from ACM Multimedia 2018 that shaped research clusters.

Foundational

Influential

Papers

Title
Session details: Vision-2 (Object & Scene Understanding)
Session details: Vision-3 (Applications in Multimedia)
Session details: Vision-4 (Representation Learning)
Shared Linear Encoder-based Gaussian Process Latent Variable Model for Visual Classification
SibNet: Sibling Convolutional Encoder for Video Captioning
SLIONS: A Karaoke Application to Enhance Foreign Language Learning
Social and Political Event Analysis based on Rich Media
Sparsely Grouped Multi-Task Generative Adversarial Networks for Facial Attribute Manipulation
Spotting and Aggregating Salient Regions for Video Captioning
Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector
StripNet: Towards Topology Consistent Strip Structure Segmentation
Structural inpainting
Structured Deep Learning for Pixel-level Understanding
Structure Guided Photorealistic Style Transfer
Style Separation and Synthesis via Generative Adversarial Networks
Supervised Online Hashing via Hadamard Codebook Learning
Support Neighbor Loss for Person Re-Identification
Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
Text-to-image Synthesis via Symmetrical Distillation Networks
ThoughtViz: Visualizing Human Thoughts Using Generative Adversarial Network
To Recognize Families In the Wild: A Machine Vision Tutorial
Tracking-assisted Weakly Supervised Online Visual Object Segmentation in Unconstrained Videos
Transforming Retailing Experiences with Artificial Intelligence
Trusted Guidance Pyramid Network for Human Parsing
Twitter Sentiment Analysis via Bi-sense Emoji Embedding and Attention-based LSTM
Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing
Unprecedented Usage of Pre-trained CNNs on Beauty Product
Unregularized Auto-Encoder with Generative Adversarial Networks for Image Generation
Unsupervised Learning of 3D Model Reconstruction from Hand-Drawn Sketches
USAR: An Interactive User-specific Aesthetic Ranking Framework for Images
User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Video-based Person Re-identification via Self-Paced Learning and Deep Reinforcement Learning Framework
Video Forecasting with Forward-Backward-Net: Delving Deeper into Spatiotemporal Consistency
Video-to-Video Translation with Global Temporal Consistency
Visual Domain Adaptation with Manifold Embedded Distribution Alignment
Visual Spatial Attention Network for Relationship Detection
VIVID: Virtual Environment for Visual Deep Learning
Watch, Think and Attend: End-to-End Video Classification via Dynamic Knowledge Evolution Modeling
Web-Based Configurable Image Annotations
Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval
What Dress Fits Me Best?: Fashion Recommendation on the Clothing Style for Personal Body Shape
When Deep Fool Meets Deep Prior: Adversarial Attack on Super-Resolution Network
When to Learn What: Deep Cognitive Subspace Clustering
WildFish: A Large Benchmark for Fish Recognition in the Wild
Your Attention is Unique: Detecting 360-Degree Video Saliency in Head-Mounted Display for Head Movement Prediction

« prev Page 5/5