The Second Workshop on Human Identification in Multimedia (HIM'17)

Abstract

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 Interests

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

Organizers


Jiwen Lu

Tsinghua University

Nikolaos Boulgouris

Brunel University

Amit K. Roy-Chowdhury

University of California, Riverside


Submission


Paper Format & Page Limit: Same as regular paper

Submission: CMT *


*: Please choose "Human Identification in Multimedia"

Schedule:

(08:30 - 08:35) Opening Remarks

(08:35 - 09:20) Session I – Human Identification Applications (3 papers)

(08:35 - 08:50)ID 201: A Novel and Robust Face Clustering Method via Adaptive Difference Dictionary

      Jiaxiang Ren (Tongji University), Shengjie Zhao (Tongji University), Kai Yang (Tongji University) and Brian Zhao (Shanghai High School International Division)

(08:50 - 09:05)ID 101: A Robust Object Detection: Application to Detection of Visual Knives

      Himanshu Buckchash (Indian Institute of Technology Roorkee) and Balasubramanian Raman (Indian Institute of Technology Roorkee)

(09:05 - 09:20)ID 179: A Distance Transform Based TIP Point Detection Method for Neurons in Confocal Microscopy Images

      Weixun Chen (Hunan University), Min Liu (Hunan University) and Rong Gong (Hunan University)

(09:30 - 10:30) Session II – Face Analysis for Human Identification (4 papers)

(09:30 - 09:45)ID 24: Discriminative Metric Learning for Video-Based Kinship Verification

      Haibin Yan (Beijing University of Posts and Telecommunications)

(09:45 - 10:00)ID 83: Robust Single-Label Classification of Facial Attributes

      Ahmed Mohammed (Deakin University) and Atul Sajjanhar (Deakin University)

(10:00 - 10:15)ID 167: Facial Expression Recognition with Deep Age

      Zhaojie Luo (Kobe University), Jinhui Chen (Kobe University), Tetsuya Takiguchi (Kobe University) and Yasuo Ariki (Kobe University)

(10:15 - 10:30)ID 26: Domain Transfer Sparse Representation for Single-Sample Face Recognition

      Venice Erin Liong (Nanyang Technological University) and Haibin Yan (Beijing University of Posts and Telecommunications)

(10:30 – 11:00) Coffee Break

(11:00 – 11:35) Keynote Talk: Dr. Chen Change (Cavan) Loy, Chinese University of Hong Kong

(11:40 - 12:55) Session I – Video Analysis for Human Identification (5 papers)

(11:40 - 11:55) ID 5: Verification-Based Pairwise Gait Identification

      Suibing Tong (Shanghai Jiaotong University), Yuzhuo Fu (Shanghai Jiaotong University), and Hefei Ling (Huazhong University of Science and Technology)

(11:55 - 12:10) ID 199: Integration of Deep Features and Hand-Crafted Features for Person Re-identification

      Sutong Zheng (Beijing University of Posts and Telecommunications), Xiaoyu Li (Academy of Broadcasting Science), Aidong Men (Beijing University of Posts and Telecommunications), Xiaoqiang Guo (ABS), and Bo Yang (Beijing University of Posts and Telecommunications)

(12:10 - 12:25) ID 89: Video Object Graph: A Novel Semantic Level Representation for Videos

      Xin Feng (Chongqing University of Technology), Yuanyi Xue (NYU Tandon School of Engineering), and Yao Wang (NYU Tandon School of Engineering)

(12:25 - 12:40) ID 150: A Novel Object Tracker Designed Based on A Complementary Framework

      Shixiong Zhang (CHU HAI College of High Education) and Ah Chung Tsoi (CHU HAI College of High Education)

(12:40 - 12:55)ID 4: A Novel Framework for Video Summarization Based on Smooth Pursuit Information from Eye Tracker Data

      Md Musfequs Salehin (Charles Sturt University) and Manoranjan Paul (Charles Sturt University)

(12:55 – 13:00) Closing Remarks