# Audio-Text Cross-Attention with Psycholinguistic Support Features for Ambivalence/Hesitancy Recognition

arXiv: https://arxiv.org/abs/2607.13345 · HTML: https://mlsanity.com/paper/2607.13345/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 43 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2305.17861/) (2023)
- [BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change](https://mlsanity.com/paper/2505.19328/) (2025)
- [From Affect to Complex Behavior: Advancing Multimodal Human-Centered AI at the 10th ABAW Workshop & Competition](https://mlsanity.com/paper/2605.27451/) (2026)
- [Conflict-Aware Multimodal Fusion for Ambivalence and Hesitancy Recognition](https://mlsanity.com/paper/2603.15818/) (2026)
- [Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions](https://mlsanity.com/paper/2604.11730/) (2026)
- [Simple Features and Honest Calibration for Ambivalence and Hesitancy Recognition in Video](https://mlsanity.com/paper/2607.11120/) (2026)
- [HSEmotion Team at the 11th ABAW Challenge: Multi-Task Learning and Ambivalence/Hesitancy Video Recognition](https://mlsanity.com/paper/2607.12774/) (2026)

## Abstract (arXiv)

We present a frame-independent audio-text system for the 3rd Ambivalence/Hesitancy Video Recognition Challenge at the 11th Affective & Behavior Analysis in-the-Wild (ABAW) Workshop. Videos are divided into overlapping 5-s windows aligned with transcript timestamps. Each window combines prosodic audio descriptors, emotion-oriented RoBERTa embeddings, and 74 psycholinguistic features representing uncertainty, hedging, and attitudinal conflict. Temporal cross-attention fuses audio and text, while the support features condition gated Multiple Instance Learning (MIL) pooling. A five-seed ensemble achieves an average precision of 0.875 and a macro-F1 of 0.722 on the 525-video labeled public-test split. Notably, our submission ranked third overall on the official challenge leaderboard, with a macro-F1 of 0.7455. Source code is available at https://github.com/Liga-de-IA-PUCPR/abaw-11-ah-challenge/.