AI Paper Atlas

Research map / Video / Video-language understanding

HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews

Léo Hemamou, Ghazi Felhi, Vincent Vandenbussche, Jean-Claude Martin, Chloé Clavel

AAAI 2019 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 87 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add sequential modeling with a bidirectional GRU instead of non-sequential features (ablation)Monomodal interview classification · Text, audio, and videoF1: 0.376 -> 0.561; 0.519 -> 0.566; 0.507 -> 0.528Improved
Add hierarchical question-answer encoding with averaging instead of a flat bidirectional GRU (ablation)HireNet · Text and audioF1: 0.561 -> 0.617; 0.566 -> 0.598Improved
Add attention rather than averaging question-answer representations (ablation)Hierarchical interview model · Text and audioF1: 0.617 -> 0.625; 0.598 -> 0.614Improved
Add question and job-title context to attention (ablation)HireNet · Text, audio, and videoF1: 0.625 -> 0.643; 0.614 -> 0.642; 0.522 -> 0.605Improved
Fuse modality representations by concatenating them before predictionHireNet · MultimodalF1: 0.640Mixed
Fuse modality decisions by averaging scoresHireNet · MultimodalF1: 0.645Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy