ABSTRACT

The 1st Workshop on Multimodal AI for Social Good (MAISG) will be held in New Delhi 2020, in conjunction with IEEE, BigMM 2020. We invite the submission of papers on original and unpublished research on all aspects of multimodal AI for social good. MAISG’2020 introduces the tradition of leveraging AI for Social Good with multimodal practically deployable solutions and thus welcomes papers on all topics related to AI for social good pipelines & frameworks, with the expectation that all papers will include multimodal insight. MAISG’2020 recognizes that high-quality research on social impact domains often leads to papers along multiple dimensions. These are motivated by the following issues:

• Data collection may be difficult and may require innovative methods and validations, for instance, to address large scale data gathering in the field, eliminate bias and ensure fairness.

• Problem modeling is a time-intensive activity that requires significant collaborations with domain experts and needs to balance a variety of tradeoffs in decision making.

• Social impact may be realized through time-consuming field studies that typically compare a baseline with the application of novel algorithms in the real world, and the experimental design can be challenging and the evaluation may be multifaceted.

The goal of MAISG’2020 at BigMM 2020 is to highlight these technical challenges and opportunities and to showcase the social benefits of artificial intelligence for the greater good.

CALL FOR PAPERS

MAISG’2020 will be a half-day event and invites the submission of papers on original and unpublished research covering all aspects of multimodal AI for social good. All AI topics that can address computational sustainability and human well-being issues are appropriate, including machine learning, optimization, reasoning, vision, and robotics. Sustainability domains include:

• Natural resources, climate and the environment (for example, climate change, atmosphere, water, oceans, forest, land, soil, biodiversity, species)

• human well being (for example, climate change, atmosphere, water, oceans, forest, land, soil, biodiversity, species)

• socio-technical systems (for example, transportation systems, cities, buildings, data centers, food systems, smart grid, agriculture

Relevant topics for the workshop include, but are not limited to, the following:

• Applications (including practically deployable solutions) - Health, Crisis, Environment, Climate, Medical Imaging & Forensics

• Social Media - Fake News, Mental Health, Hate speech & Toxic comments

• Audio & Speech processing - Audio Speech Recognition, Visual Speech Recognition

• Multimodal classification - Socio-technical systems; Smart cities, Transport, Infrastructure.

• Video processing - Surgical imagery, Crisis, Surveillance

• Ethics & Fairness - Bias in Multimodal systems

• Latency sensitive analysis systems - Medical, First Responders

• Information Extraction and Data Mining, and Knowledge Graph for Multimodal analysis

• Multimodal Resources and Evaluation - Multimodal datasets for Health, Environment

• Multimodal Language Understanding and language generation - Conversational AI in social domain

• Visual behaviour analysis in social interaction on multimedia platforms

• Multimodal Dialogue Modelling for leveraging social interaction

• Low resource or endangered language-inclusive multimodal integration

Papers in all these areas describing Analytical engineering experiments or computationally-aided multimodal analysis as well as survey papers are welcome. In all relevant areas, we encourage authors to include a detailed description of the methodology, the analysis of the contribution of the proposal and in technologically-oriented papers, we encourage in-depth error analysis linked to multimodal information.

SUBMISSIONS

We welcome novel submissions in the mentioned categories. Maximum length of the papers can be 8 pages in a 2-column IEEE format excluding references. The authors will be provided with additional 2 pages for reference. For detailed guidelines and submission format, please refer http://bigmm2020.org/index.php/authors/submission-instructions

For submissions, please use the following link https://easychair.org/conferences/?conf=bigmm2020 , by selecting the appropriate track for the workshop.

MEMBERS OF THE ORGANIZING COMMITTEE

Ramit Sawhney - Tower Research

Cornelia Caragea - University of Illinois at Chicago

Roger Zimmerman - School of Computing, National University of Singapore

S. Indu - Delhi Technological University

Rahul Katarya - Delhi Technological University

Anil Singh Parihar - Delhi Technological University

MEMBERS OF THE PROGRAM COMMITTEE

Puneet Mathur - University of Maryland, College Park

Akash Kumar Gautam - MIDAS Labs, IIIT-Delhi