The First International Workshop on Video Question Answering and Image Question Answering

Video and Image Question Answering (VIQA): building a bridge between visual content analysis and reasoning on textual data.

Organized in conjunction with ICPR2020 The 25th International Conference on Pattern Recognition, Milan, Italy, January 10-15, 2021

VIQA2020 will be held virtually as an half-day joint workshop with CBIR2020 and TAILOR2020 on January, 10th 2021, 12.00-16.00 (CET Time): reach us at VTIUR 2020!

The Deadline has been extended to October 17th, 2020!

Please note that papers rejected at ICPR 2020 main conference and fitting VIQA topics can be submitted here. Authors should address reviewers' concerns and provide the ICPR reviews as supplementary material.

Image Question Answering and Video Question Answering are two tasks involving the realization of models able to analyze the visual content of an image or a video, and produce a meaningful answer to visual content-related questions. These tasks both involve spatial, frame-level reasoning. Moreover, Video Question Answering also requires temporal, video-level reasoning which further raises the difficulty of the task. Solving these tasks would represent the ability to train models able to jointly analyze and reason on visual contents and textual contents at a human-level: the obtained models would be able to learn to isolate and pinpoint objects of interest in video (or image), and to identify and reason about their interactions in both the spatial and temporal domains. Image and Video Question Answering thus represent a challenging, but fundamental task in both Computer Vision and Natural Language Processing communities.

Topics of interest are mainly related to Visual (Image and Video) Question Answering including, but not limited to:

• Datasets and evaluation

• Deep learning methods for vision and language

• Egocentric visual question answering

• Image question answering

• Multimodal question answering

• Representation learning

• Transfer learning for vision and language

• Video analysis and understanding

• Video question answering

• Video summarization

• Vision and language and/or other modalities

• Vision applications and systems

• Visual reasoning and logical representation

The first VIQA workshop wants to gather all the people from academia and industry interested in the aforementioned topics, this in order to stimulate the sharing between participants of state-of-the-art approaches, best practices, and future directions.

A special issue about Video and Image Question Answering is going to be organized in a top journal.

Technical Program Committee:

• Meng Wang, Hefei University of Technology

• Jingkuan Song, Columbia University

• Federico Becattini, University of Florence

• Pietro Bongini, University of Florence

• Marcella Cornia, University of Modena and Reggio Emilia

• Tommaso Campari, University of Padova/FBK

• Davide Rigoni, University of Padova/FBK

• Antonino Furnari, University of Catania

• Cheng Wenlong, CRIPAC