MUSA2: First ACM Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes

Abstract : Multimedia scientists have largely focused their research on the recognition of tangible properties of data, such as objects and scenes. Recently, the field has started evolving towards the modeling of more complex properties. For example, the understanding of social, affective and subjective attributes of data has attracted the attention of many research teams at the crossroads of computer vision, multimedia, and social sciences. These intangible attributes include, for example, visual beauty, video popularity, or user behavior. Multiple, diverse challenges arise when modeling such properties from multimedia data. Issues concern technical aspects such as reliable groundtruth collection, the effective learning of subjective properties, or the impact of context in subjective perception. The first edition of the ACM MM'17 MUSA2 workshop has gathered together high-quality research works focusing on the computational understanding of intangible properties from multimodal data, including visual emotions, user intent, human relationships, and personality.
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/hal-01858382
Contributor : Team Perception <>
Submitted on : Friday, September 14, 2018 - 11:10:16 AM
Last modification on : Friday, September 14, 2018 - 11:52:52 AM
Long-term archiving on : Saturday, December 15, 2018 - 2:13:05 PM

File

Alameda-MUSA2-2017.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Xavier Alameda-Pineda, Miriam Redi, Mohammad Soleymani, Nicu Sebe, Shih-Fu Chang, et al.. MUSA2: First ACM Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes. MM 2017 - ACM on Multimedia Conference, Oct 2017, Mountain View CA, United States. pp.1974-1975, ⟨10.1145/3123266.3132057⟩. ⟨hal-01858382⟩

Share

Metrics

Record views

189

Files downloads

52