AI Paper Atlas

Research map / Video / Video-language understanding

BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Behavioural Change

Manuela González-González, Soufiane Belharbi, Muhammad Osama Zeeshan, Masoumeh Sharafi, Muhammad Haseeb Aslam, Marco Pedersoli, Alessandro Lameiras Koerich, Simon L Bacon, Eric Granger

ICLR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video

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 TCN temporal context to the visual backbone (ablation)ResNet101 visual model · BAH test (frame-level)AVGF1: 0.4929 -> 0.5165Improved
add TCN temporal context to the visual backbone (ablation)ResNet34 visual model · BAH test (frame-level)AVGF1: 0.5138 -> 0.4998Hurt
add TCN temporal context to the visual backbone (ablation)ResNet50 visual model · BAH test (frame-level)AVGF1: 0.4737 -> 0.4985Improved
add text modality to visual-only model (ablation)ResNet101 visual model · BAH test (frame-level)AVGF1: 0.5165 -> 0.5547Improved
add audio modality to text-only model (ablation)Text-only model · BAH test (frame-level)AVGF1: 0.5497 -> 0.5586Improved
add visual modality to audio + text model (ablation)Audio + Text model · BAH test (frame-level)AP: 0.2609 -> 0.2548Hurt
use transformer or cross-attention fusion instead of concatenation (ablation)Three-modality fusion · BAH test (frame-level)AVGF1: 0.5526 -> 0.5137 (MT), 0.5241 (JMT)Hurt
use cropped faces instead of full-frame or head-pose visual input (ablation)Visual modality · BAH test (frame-level)AVGF1Improved
use a very large temporal context window (ablation)Visual model with TCN · BAH test (frame-level)AVGF1Hurt

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