Revealing Temporal Label Noise in Multimodal Hateful Video Classification

• URL: http://arxiv.org/abs/2508.04900v1
• Date: Wed, 06 Aug 2025 21:55:59 GMT
• Title: Revealing Temporal Label Noise in Multimodal Hateful Video Classification
• Authors: Shuonan Yang, Tailin Chen, Rahul Singh, Jiangbei Yue, Jianbo Jiao, Zeyu Fu,
• Abstract summary: We investigate the impact of label ambiguity through a fine-grained approach.<n>We trim hateful videos from the HateMM and MultiHateClip English datasets using annotated timestamps.<n>We then conduct an exploratory analysis of these trimmed segments to examine the distribution and characteristics of both hateful and non-hateful content.
• Score: 17.69786804367003
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rapid proliferation of online multimedia content has intensified the spread of hate speech, presenting critical societal and regulatory challenges. While recent work has advanced multimodal hateful video detection, most approaches rely on coarse, video-level annotations that overlook the temporal granularity of hateful content. This introduces substantial label noise, as videos annotated as hateful often contain long non-hateful segments. In this paper, we investigate the impact of such label ambiguity through a fine-grained approach. Specifically, we trim hateful videos from the HateMM and MultiHateClip English datasets using annotated timestamps to isolate explicitly hateful segments. We then conduct an exploratory analysis of these trimmed segments to examine the distribution and characteristics of both hateful and non-hateful content. This analysis highlights the degree of semantic overlap and the confusion introduced by coarse, video-level annotations. Finally, controlled experiments demonstrated that time-stamp noise fundamentally alters model decision boundaries and weakens classification confidence, highlighting the inherent context dependency and temporal continuity of hate speech expression. Our findings provide new insights into the temporal dynamics of multimodal hateful videos and highlight the need for temporally aware models and benchmarks for improved robustness and interpretability. Code and data are available at https://github.com/Multimodal-Intelligence-Lab-MIL/HatefulVideoLabelNoise.

Related papers

• HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection [8.323983138164547]
  HateClipSeg is a large-scale multimodal dataset with both video-level and segment-level annotations.<n>Our three-stage annotation process yields high inter-annotator agreement.<n>Results highlight substantial gaps in current models.
  arXiv  Detail & Related papers  (2025-08-03T10:46:06Z)
• Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion [7.728348842555291]
  The rapid rise of video content on platforms such as TikTok and YouTube has transformed information dissemination.<n>Despite significant efforts to combat hate speech, detecting these videos remains challenging due to their often implicit nature.<n>We present CMFusion, an enhanced multimodal hate video detection model utilizing a novel Channel-wise and Modality-wise Fusion Mechanism.
  arXiv  Detail & Related papers  (2025-05-17T15:24:48Z)
• TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs [56.92627816895305]
  Video large language models have achieved remarkable performance in tasks such as video question answering.<n>Our dataset focuses on enhancing temporal comprehension across five key dimensions.<n>We introduce a multi-task prompt fine-tuning approach that seamlessly integrates temporal-sensitive tasks into existing instruction datasets.
  arXiv  Detail & Related papers  (2025-03-13T03:05:11Z)
• On the Consistency of Video Large Language Models in Temporal Comprehension [57.985769348320616]
  Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments.<n>We conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding.
  arXiv  Detail & Related papers  (2024-11-20T00:47:17Z)
• MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili [11.049937698021054]
  This study presents MultiHateClip, a novel multilingual dataset created through hate lexicons and human annotation. It aims to enhance the detection of hateful videos on platforms such as YouTube and Bilibili, including content in both English and Chinese languages.
  arXiv  Detail & Related papers  (2024-07-28T08:19:09Z)
• SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding [50.337896542603524]
  We introduce SpikeMba: a multi-modal spiking saliency mamba for temporal video grounding. Our approach integrates Spiking Neural Networks (SNNs) with state space models (SSMs) to leverage their unique advantages. Our experiments demonstrate the effectiveness of SpikeMba, which consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-04-01T15:26:44Z)
• Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection [103.92970668001277]
  We propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection. We first propose a multi-scale temporal modeling module, capable of extracting features from segments of varying lengths. Then, we design a dynamic erasing strategy, which dynamically assesses the completeness of the detected anomalies.
  arXiv  Detail & Related papers  (2023-12-04T09:40:11Z)
• Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos [55.52369116870822]
  This paper focuses on tackling the problem of temporal language localization in videos. It aims to identify the start and end points of a moment described by a natural language sentence in an untrimmed video.
  arXiv  Detail & Related papers  (2021-10-12T14:59:25Z)
• Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing [48.87278703876147]
  A new problem, named audio-visual video parsing, aims to parse a video into temporal event segments and label them as audible, visible, or both. We propose a novel hybrid attention network to explore unimodal and cross-modal temporal contexts simultaneously. Experimental results show that the challenging audio-visual video parsing can be achieved even with only video-level weak labels.
  arXiv  Detail & Related papers  (2020-07-21T01:53:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.