# MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model Source: [MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model]() Collection index: [llms.txt]() Data updated: 2026-05-27T05:00:13.467Z Authors: Eyal Hanania, Nadav Kirsch, Daniel Arkushin, Jonathan Benvenisti, Amos Bercovich, Elie Zemmour, Sahar Froim Published: 2026-05-25T04:21:37.000Z ## Abstract Detecting laughter in video is essential for affective computing and narrative understanding, yet existing approaches treat it as coarse clip-level classification, failing to capture precise temporal boundaries of brief, transient laughter events. We address this gap with two complementary contributions. First, we introduce UR-FUNNY-Temporal and SMILE-Temporal, fully annotated temporal laughter datasets extending two widely-used humor benchmarks. Our annotations cover over 11,053 videos (78.8 hours) and provide precise onset/offset boundaries for each laughter event, along with rich metadata distinguishing speaker vs. audience laughter, modality dominance (acoustic, visual, or both), and intensity levels. Second, we propose a lightweight weakly-supervised framework for temporal laughter localization. Our architecture combines fixed HuBERT and MAE encoders with temporal softmax pooling and adaptive modality gating, learning fine-grained temporal grounding from clip-level labels without requiring frame-level annotations during training. Experiments across three datasets demonstrate that our approach substantially outperforms multimodal foundation models including Gemini 3 Flash, achieving 99% F1 and 68.1% localization precision on sports broadcast data. Ablations validate each architectural component. Furthermore, our precise temporal tags improve downstream laughter reasoning by 227% on CIDEr, enabling GPT-3.5 to outperform GPT-4o. The code, UR-FUNNY-Temporal and SMILE-Temporal datasets are publicly available at https://github.com/WSCSports/MTLLFM-temporal-laughter-localization. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Laughter Classification on UR-Funny (test)](): Laughter Classification; UR-FUNNY (test); F1 Score (Classification): 84.9. - [Laughter Classification on SMILE (test)](): Laughter Classification; SMILE (test); F1 Score (Classification): 80.3. - [Laughter Temporal Localization on SportsPress (test)](): Laughter Temporal Localization; SportsPress (test); Localization Accuracy @ 0.5 IoU: 68.1. - [Laughter Temporal Localization on UR-Funny (test)](): Laughter Temporal Localization; UR-FUNNY (test); Localization Accuracy @0.5 IoU: 49.7. - [Laughter Classification on SportsPress (test)](): Laughter Classification; SportsPress (test); F1 Score (Classification): 99. - [Laughter Temporal Localization on SMILE (test)](): Laughter Temporal Localization; SMILE (test); Localization Accuracy @ IoU=0.5: 56.7. ## Original sources and implementation [Original paper]() [PDF]()