# MultiHateLoc: Towards Temporal Localisation of Multimodal Hate Content in Online Videos

arXiv: https://arxiv.org/abs/2512.10408 · HTML: https://mlsanity.com/paper/2512.10408/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows](https://mlsanity.com/paper/2008.12577/) (2020)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [All You Need is "Love": Evading Hate-speech Detection](https://mlsanity.com/paper/1808.09115/) (2018)
- [HateMM: A Multi-Modal Dataset for Hate Video Classification](https://mlsanity.com/paper/2305.03915/) (2023)
- [Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts](https://mlsanity.com/paper/2408.05905/) (2024)
- [Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models](https://mlsanity.com/paper/2401.16727/) (2024)
- [ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos](https://mlsanity.com/paper/2508.06570/) (2025)
- [Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content](https://mlsanity.com/paper/2502.07138/) (2025)
- [Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion](https://mlsanity.com/paper/2505.12051/) (2025)
- [MM-HSD: Multi-Modal Hate Speech Detection in Videos](https://mlsanity.com/paper/2508.20546/) (2025)
- [Revealing Temporal Label Noise in Multimodal Hateful Video Classification](https://mlsanity.com/paper/2508.04900/) (2025)

## Built on by (most cited first, 1 of 1)

- [TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech](https://mlsanity.com/paper/2601.11178/) (2026)

## Abstract (arXiv)

The rapid growth of video content on platforms such as TikTok and YouTube has intensified the spread of multimodal hate speech, where harmful cues emerge subtly and asynchronously across visual, acoustic, and textual streams. Existing research primarily focuses on video-level classification, leaving the practically crucial task of temporal localisation, identifying when hateful segments occur, largely unaddressed. This challenge is even more noticeable under weak supervision, where only video-level labels are available, and static fusion or classification-based architectures struggle to capture cross-modal and temporal dynamics. To address these challenges, we propose MultiHateLoc, the first framework designed for weakly-supervised multimodal hate localisation. MultiHateLoc incorporates (1) modality-aware temporal encoders to model heterogeneous sequential patterns, including a tailored text-based preprocessing module for feature enhancement; (2) dynamic cross-modal fusion to adaptively emphasise the most informative modality at each moment and a cross-modal contrastive alignment strategy to enhance multimodal feature consistency; (3) a modality-aware MIL objective to identify discriminative segments under video-level supervision. Despite relying solely on coarse labels, MultiHateLoc produces fine-grained, interpretable frame-level predictions. Experiments on HateMM and MultiHateClip show that our method achieves state-of-the-art performance in the localisation task.