IEEE 4th International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR 2021)

Program

The 3rd IEEE Workshop on Artificial Intelligence for Art Creation (AIART'21)

08:55-17:30

Workshop

Webpage: https://aiart2021.github.io/

25 Subsessions

Opening Remark08:55-09:00

Keynote 1: Stylized Cartoon and Animation09:00-09:30

Speaker: Ying-qing Xu

F1 01: AIBO - A Sicko Brainwave Opera09:30-09:45

Speaker: Ellen Pearlman

F1 02: Layout Structure Assisted Indoor Image Generation09:45-10:00

Speakers: Zhijie Qin, Wei Zhong, Fei Hu, Xinyan Yang, Long Ye, Qin Zhang

F1 03: Violent Scene Detection of Film Videos Based on Multi-task Learning of Temporal-spatial Features10:00-10:15

Speakers: Zhengxin Zheng, Wei Zhong, Long Ye, Li Fang, Qin Zhang

F1 04: MUSE: Textual Attributes Guided Portrait Painting Generation10:15-10:30

Speakers: Xiaodan Hu, Pengfei Yu, Kevin Knight, Heng Ji, Bo Li, Humphrey Shi

Keynote 2: Multimodal Emotion Recognition in Conversation10:30-11:00

Speaker: Qin Jin

F2 05: Text Style Transfer With Decorative Elements11:00-11:15

Speakers: Yuting Ma, Fan Tang, Weiming Dong, Changsheng Xu

F2 06: MemoMusic: A Personalized Music Recommendation Framework Based on Emotion and Memory11:15-11:30

Speakers: Luntian Mou, Jueying Li, Juehui Li, Feng Gao, Ramesh Jain, Baocai Yin

F2 07: Respective Volumetric Heatmap Autoencoder for Multi-person 3D Pose Estimation11:30-11:45

Speakers: Minghao Wang, Long Ye, Fei Hu, Li Fang, Wei Zhong, Qin Zhang

F2 08: Exploring the Application of AI-Generated Artworks for the Study of Aesthetic Processing11:45-12:00

Speakers: Vanessa Utz, Steve DiPaola

Keynote 3: Facial Action Unit Recognition under Non-full Annotation12:00-12:30

Speaker: Shangfei Wang

Lunch12:30-14:00

Keynote 4: Creating Real Emotions Artificially: Music & Beyond14:00-14:30

Speaker: Björn W. Schuller

F3 09: The Brain-Machine-Ratio Model for Designer and AI Collaboration14:30-14:45

Speakers: Ling Fan, Yifang Bao, Shuyu Gong, Sida Yan, Harry Jiannan Wang

F3 10: Rethinking of Intangible Cultural Heritage Teaching with Creative Promgramming in China14:45-15:00

Speakers: Peng Tan, Yi Ji, Yunqing Xu

F3 11: Design and Development of an Intelligent Pet-type Quadruped Robot15:00-15:15

Speakers: Feng Gao, Chengjia Lei, Xingguo Long, Jin Wang, Peiheng Song

F3 12: Smart Portable Musical Simulation System Based on Unified Temperament15:15-15:30

Speakers: Lin Gan, Li Lv, Cuicui Wang, Mu Zhang

F3 13: Culture-inspired Multi-modal Color Palette Generation and Colorization: A Chinese Youth Subculture Case15:30-15:45

Speakers: Yufan Li, Jinggang Zhuo, Ling Fan, Harry Jiannan Wang

Keynote 5: XAIArt: eXplainable Artificial Intelligence and the Arts15:45-16:15

Speaker: Nick Bryan-Kinns

F4 14: A Probabilistic and Random Method for the Generation of Bai Nationality Music Fragments16:15-16:30

Speakers: Pengcheng Shang, Shan. Ni, Li. Zhou

F4 15: The JinYue Database for Huqin Music Emotion, Scene and Imagery Recognition16:30-16:45

Speakers: Kejun Zhang, Xinda Wu, Ruiyuan Tang, Qiaoqiao Huang, Changyuan Yang, Hui Zhang

F4 16: Distinguishing the “strong/weak” in the 60 Jingfang Tones and Their Optimal Distribution16:45-17:00

Speaker: Gen-fang Chen

F4 17: Dance to Music: Generative Choreography with Music using Mixture Density Networks17:00-17:15

Speakers: Rongfeng Li, Meng Zhao, Xianlin Zhang, Xueming Li

F4 18: Music Emotion Recognition through Sparse Canonical Correlation Analysis17:15-17:30

Speakers: Hongwei Li, Hongjian Bo, Lin Ma, Lexiang Wang, Haifeng Li

Tutorial: Human-centric Media Understanding: Processing, Generation, Re-identification, and Prediction

09:00-11:30

Tutorial

Webpage: https://mipr2021.org/pages/tutorials/

6 Subsessions

Opening09:00-09:10

Speaker: Zheng Wang

Image Restoration and Generation for Human Analysis09:10-09:40

Speaker: Jing Xiao

Total Generate: Guided Generative Adversarial Networks for Generating Human Faces, Hands, Bodies and Natural Scenes09:40-10:10

Speaker: Hao Tang

Coffee Break10:10-10:30

New Trends of Person Re-ID System10:30-11:00

Speaker: Zheng Wang

Delving into Spatio-temporal Dependencies: Agent Behavior Forecasting in a Video Sequence11:00-11:30

Speaker: Yuke Li

Sponsors Lunch Session 3

12:10-12:50

Sponsor

NEC Corporation

Introduction of Research Activities related to Multimedia Information Processing

The Joint Workshop of the third IEEE Workshop on Fake Multimedia and first Workshop on Cross Modal Person Reidentification (Joint Workshops: FakeMM '21 & CM-PRID '21)

13:00-15:00

Workshop

Webpage: http://www.cs.albany.edu/~patrey/fakemm21/

Webpage: http://mipr.iiitd.edu.in/

6 Subsessions

Welcome Note13:00-13:02

Speaker: Pradeep Atrey

FakeMM 1: Detecting and Preventing Faked Mixed Reality13:02-13:22

Speakers: Fabian Kilger, Alexandre Kabil, Volker Tippmann, Gudrun Klinker, Marc-Oliver Pahl

FakeMM 2: An Introduction to the JPEG Fake Media Initiative13:22-13:42

Speakers: Frederik Temmermans, Deepayan Bhowmik, Fernando Pereira

FakeMM 3: Detection of AI-Synthesized Speech Using Cepstral& Bispectral Statistics13:42-14:02

Speakers: Arun Kumar Singh, Priyanka Singh

CM-PRID 1: Hardness Prediction for More Reliable Attribute-based Person Re-identification14:02-14:22

Speakers: Lucas Florin, Andreas Specker, Arne Schumann, Jürgen Beyerer

FakeMM Keynote: Digital Forensics and Anti-forensics for Deepfake Videos14:22-15:00

Speaker: Feng Ding

Tutorial: A Master’s Toolbox and Algorithms for Low-latency Live Streaming

15:10-17:10

Tutorial

Ali C. BegenTurkeyOzyegin UniversitySpeaker's Page

Abstarct:

Today, a glass-to-glass latency of 10-30 seconds is practically achievable in live streaming and such a range is acceptable in most cases. Yet, the increasing number of cord-cutters is putting pressure on streaming providers to offer low-latency (2-10 seconds) streaming, ...