Shared task @ AAAI 2024
Third Workshop on Multimodal Fact-Checking and Hate Speech
Detection
February, 2024
ABOUT DE : HATE
Important News Datasets Released:
DE : HATE
Colab: https://codalab.lisn.upsaclay.fr/competitions/16256Form: https://forms.gle/Ft99tXQFsZvZ5BG49
Please register here to access the dataset.
DE : HATE
We present a pioneering endeavor: a challenge focused on the automatic blurring of offensive segments within a hate- ful image. In the context of multimodal content (comprising both text and image) infused with hate, the objective is to pinpoint the pertinent hateful portions within the image and effectively apply blurring techniques to obfuscate the malev- olent aspects and thus, mitigate the antagonism conveyed by the media.
DE:HATE Task Details
- The dataset will be created by giving adversarial prompts to a large image generation model like stable diffusion.
- We will release at least 1000 data samples of images with the relevant parts blurred.
- The participants will have to build systems to automatically mask the hateful parts of the images.
- Mean IOU will be the metric used to rank the participants.
Some Samples from Data
- Dataset link : Please register in the Codalab page linked above to find details to access the dataset.
- Evaluation metric : Since the task has the output image subsection polygon as the target variable, we will use the Intersection Over Union (IOU) or jaccard index as the evaluation metric. Only if this score is greater than a set threshold, do we consider that as a right prediction. The final IOU will be considered as the average IOU over the test set. The winning team will be the one with the highest average IOU score .
- Submission instructions : Results are to be submitted in json file named "answer.json" in a zipped format. Refer to the starting kit for more details.
- System description paper : All teams/participants will be invited to submit a paper describing their system. Accepted papers will be published in formal proceedings.
- Paper submission instruction : To be updated.
IMPORTANT DATES
- 13 October 2023 : Release of the training set.
- 8 November 2023 : Release of the test set.
- 30 November 2023 : Deadline for submitting the final results.
- 3 December 2023 : Announcement of the results.
- 10 December 2023 : System paper submission deadline (All teams are invited to submit a paper).
- 20 December 2023 : Notification of system papers.
- 25 December 2023 : Camera ready submission.
ORGANIZING COMMITTEE CHAIRS
Dr. Amitava Das:
Dr. Amitava Das is a Core Faculty & Research Associate Professor of the
Artificial Intelligence Institute, at the University of South Carolina, and an
Advisory Scientist to Wipro AI.
Research interests : Code-Mixing
and Social Computing.
Organizing Activities [selective] :
• Memotion @SemEval2020 • SentiMix @SemEval2020 • Computational Approaches to
Linguistic Code-Switching @LREC 2020 • CONSTRAINT @AAAI2021
Dr. Amit Sheth:
Dr. Amit Sheth is the founding Director of the Artificial Intelligence
Institute, and a CSE Professor at
University of South Carolina.
Research interests : Knowledge
Graph, NLP, Analysing Social
Media
Organizing Activities [selective] :
• Cysoc2021 @ ICWSM2021 • Emoji2021 @ICWSM2021 • KiLKGC 2021 @KGC21
Dr. Asif Ekbal:
Dr. Asif Ekbal is an Associate Professor of CSE at IIT Patna, India.
Research interests : NLP, CodeMixing and Social Computing.
Organizing Activities [selective] : • CONSTRAINT @AAAI2021
Aman Chadha
Aman Chadha is an Applied Sci-
ence Manager at Amazon Alexa AI
and a Researcher at Stanford AI.
Research interests : Multimodal AI, On-device AI, and
Human-Centered AI.
ASSOCIATE ORGANIZERS
Parth Patwa
University of California Los Angeles (UCLA)
Megha Chakraborty
UNIVERSITY OF SOUTH CAROLINA, USA
Suryavardan Suresh
New York University
Anku Rani
University of South Carolina, USA
WEB CHAIR
Jinendra Malekar
UNIVERSITY OF SOUTH CAROLINA, USA