3IA PhD/Postdoc Seminar #35

Flash presentation

Spectral partitioning into protein structural domains

Abstract:
The decomposition of a biomolecular complex into domains is an important step to investigate biological functions, and is also relevant to ease structure determination. A successful approach to do so is the SPECTRUS algorithm, which provides a segmentation based on spectral clustering applied to a graph coding inter-atomic fluctuations derived from an elastic network model. I will present SpectralDom, a simplification and an extension of SPECTRUS, both straightforward and useful.
For single structures, we show that high quality partitioning can be obtained from a graph Laplacian derived from pairwise interactions, without the use of normal modes. For sets of homologous structures, we introduce a Multiple Sequence Alignment mode, exploiting both the sequence based information (MSA) and the geometric information embodied in experimental structures.
The algorithm compares favorably with the original SPECTRUS as well as state-of-the-art deep approaches.

Visual objectification in films as a new AI task

Abstract:
In film gender studies, the concept of “male gaze” refers to the way the characters are portrayed on-screen as objects of desire rather than subjects. In this talk, we introduce a novel video-interpretation task, to detect character objectification in films. The purpose is to reveal and quantify the usage of complex temporal patterns operated in cinema to produce the cognitive perception of objectification. We will present how to define, within a multi-disciplinary team made of researchers in computer science and AI, and in information and communication science with media and gender studies, a new interpretive construct for video, how to approach data creation, and how to show the feasibility of the task by adapting most recent vision and vision-language foundation models, analyzing their weaknesses with explainable AI approaches.
This work is being carried out within the ANR TRACTIVE project and is published at CVPR2024.

Open discussion about the two contributions