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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add TCN temporal context to the visual backbone (ablation) | ResNet101 visual model · BAH test (frame-level) | AVGF1: 0.4929 -> 0.5165 | Improved |
| add TCN temporal context to the visual backbone (ablation) | ResNet34 visual model · BAH test (frame-level) | AVGF1: 0.5138 -> 0.4998 | Hurt |
| add TCN temporal context to the visual backbone (ablation) | ResNet50 visual model · BAH test (frame-level) | AVGF1: 0.4737 -> 0.4985 | Improved |
| add text modality to visual-only model (ablation) | ResNet101 visual model · BAH test (frame-level) | AVGF1: 0.5165 -> 0.5547 | Improved |
| add audio modality to text-only model (ablation) | Text-only model · BAH test (frame-level) | AVGF1: 0.5497 -> 0.5586 | Improved |
| add visual modality to audio + text model (ablation) | Audio + Text model · BAH test (frame-level) | AP: 0.2609 -> 0.2548 | Hurt |
| 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) | AVGF1 | Improved |
| use a very large temporal context window (ablation) | Visual model with TCN · BAH test (frame-level) | AVGF1 | Hurt |
Closest papers by meaning
- EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition (NeurIPS 2025 · similarity 0.85)
- $E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset (NeurIPS 2024 · similarity 0.84)
- Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis (AAAI 2026 · similarity 0.84)
- EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment (ICML 2026 · similarity 0.83)
- Bridge Then Begin Anew: Generating Target-Relevant Intermediate Model for Source-Free Visual Emotion Adaptation (AAAI 2025 · similarity 0.83)
- FindingEmo: An Image Dataset for Emotion Recognition in the Wild (NeurIPS 2024 · similarity 0.83)
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.
