Human Identities are an important information source in many high-level multimedia analysis tasks such as video summarization, semantic retrieval, interaction indexing, and scene understanding. The aim of this workshop is to bring together researchers in computer vision and multimedia to share ideas and propose solutions on how to address the many open issues in human identification, and present new datasets that introduce new challenges in the field. Human identification in multimedia is one relatively new problem in multimedia analysis and, recently, it has attracted the attention of many researchers in the field. Human Identification is significant to many multimedia related applications such as video surveillance, video search, human-computer interaction, and video summarization. Recent advances in feature representations, modeling, and inference techniques have led to a significant progress in the field. The proposed workshop aims to explore recent progress in human identification with multimedia data by taking stock of the past five years of work in this field and evaluating different algorithms. The proposed workshop will help the community to understand the challenges and opportunities of human identification in multimedia techniques for the next few years.
Topics of interest include, but are not limited to:
Multimedia feature representation
1.Image feature representation
2.Video feature representation
3.Audio feature representation
4.Multiview feature representation
5.Multimodal feature representation
Statistical learning for human identification
1.Sparse learning for human identification
2.Dictionary learning for human identification
3.Manifold learning for human identification
4.Metric learning for human identification
5.Deep learning for human identification
Applications
1.Video surveillance
2.Multimedia search
3.Video summarization
4.Benchmark datasets
5.Comparative evaluations
Paper Format & Page Limit: Same as regular paper
Submission: CMT *
*: Please choose "The Third Workshop on Human Identification in Multimedia"
Paper submission deadline: 1 April 2019
Decision notification: 22 April 2019
Camera ready: 29 April 2019
Workshop day: 12 July 2019
|
13:30 |
Introduction |
|
13:35 |
Invited Talk: Person Re-identification ( Weishi Zheng ) |
|
14:25 |
Similarity Preserved Camera-to-camera Gan For Person Re-identification |
|
14:40 |
Collaborative Representation Guided Graph Learning For Visual Classification |
|
15:00 |
Coffee Break - Meeting room Foyer |
|
15:30 |
Dual-cycle Deep Reinforcement Learning For Stabilizing Face Tracking |
|
15:45 |
Multi-task Learning For Pedestrian Body Parts Detection And Multi-attribute Classification |
|
16:00 |
Context Attention Module For Human Hand Detection |
|
16:15 |
Toward Robust Online Adaptive Visual Tracking Via Pyramidal Features Extraction |
|
16:30 |
Improving Human Pose Estimation With Self-attention Generative Adversarial Networks |
|
16:45 |
Unsupervised Domain Adaptation For Disguised Face Recognition |
|
17:00 |
Sports Highlights Generation Using Decomposed Audio Information |
|
17:15 |
New Benchmark Datasets And A Character Identification System On TV Series |
|
17:30 |
Conclusions |
