CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection

• URL: http://arxiv.org/abs/2608.15905v2
• Date: Wed, 19 Aug 2026 13:14:48 GMT
• Title: CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection
• Abstract summary: We propose CLARA, a clip-level multimodal framework for hateful video detection.<n>Instead of treating a video as a single instance, CLARA models it as a sequence of fine-grained clips.<n>Experiments on three hateful video datasets demonstrate that CLARA consistently outperforms state-of-the-art methods.
• Score: 15.553401928926457
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hateful video detection has become increasingly important with the rapid growth of video-centric social media platforms, given the serious risks that hate speech poses to both individual well-being and social cohesion. Compared with text or static multimodal content, hateful video detection remains underexplored and significantly more challenging, as hateful meaning often arises from complex interactions among multimodal cues, including speech, audio, and visual content. Moreover, such signals are often brief, implicit, and temporally dependent, making them difficult to capture using conventional video-level representations. In this work, we propose CLARA, a clip-level multimodal framework for hateful video detection. Instead of treating a video as a single instance, CLARA models it as a sequence of fine-grained clips, enabling more precise capture of temporally localized hateful signals. We introduce a Mixture-of-Experts clip encoder for adaptive multimodal alignment, a local-global segment contrastive objective to jointly model short-term cues and long-range temporal dependencies, and VLM-derived rationales integrated via a gated Transformer to provide high-level semantic guidance. Extensive experiments on three hateful video datasets demonstrate that CLARA consistently outperforms state-of-the-art methods. Further ablation studies and parameter analyses validate the effectiveness of each component.

Related papers

• VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding [61.00809248898572]
  Long video understanding is a problem in which an agent reads the video turn by turn along the temporal axis, deciding at each turn how fast to watch, what evidence to retain, when to revisit uncertain segments, and when to stop and answer.<n>We propose textbfVideoScout, a multi-turn reasoning agent that instantiates the SEA paradigm through adaptive reasoning pacing.<n>Experiments on long video understanding and reasoning benchmarks demonstrate that our 7B model achieves strong performance compared with existing trained 7B agentic models.
  arXiv  Detail & Related papers  (2026-09-14T14:04:03Z)
• Explainable Forensics of Manipulated Segments in Untrimmed Long Videos [50.190474724159465]
  We formulate the task of Temporal AI-Generated Segment localization and Explanation.<n>We introduce TASLE, a large-scale benchmark comprising 12,472 untrimmed videos with diverse manipulation patterns and rich annotation signals.<n>We propose MSLoc, a coarse-to-fine forensic baseline that combines a boundary-sensitive proposal generation module for efficient long-video scanning with an MLLM-based refinement module for precise boundary localization and interpretable reasoning.
  arXiv  Detail & Related papers  (2026-06-01T15:48:38Z)
• Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language [60.91064560080974]
  We propose an efficient approach, SpotVMR, to trim the query-relevant clip.<n>Our proposed SpotVMR can serve as plug-and-play module, which achieves efficiency for state-of-the-art VMR methods.
  arXiv  Detail & Related papers  (2026-05-28T11:42:28Z)
• Mode Seeking meets Mean Seeking for Fast Long Video Generation [79.62764340469]
  Scaling video generation from seconds to minutes faces a critical bottleneck.<n>We propose a training paradigm where Mode Seeking meets Mean Seeking.<n>Our method effectively closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency.
  arXiv  Detail & Related papers  (2026-02-27T18:59:02Z)
• CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models [66.56549019393042]
  Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actions and temporal order.<n>We propose a scalable framework for counterfactual video generation that synthesizes videos differing only in actions or temporal structure while preserving scene context.
  arXiv  Detail & Related papers  (2026-01-08T10:03:07Z)
• MultiHateLoc: Towards Temporal Localisation of Multimodal Hate Content in Online Videos [22.175314789730667]
  MultiHateLoc is a framework for weakly-supervised multimodal hate localisation.<n>It produces fine-grained, interpretable frame-level predictions.<n> Experiments on HateMM and MultiHateClip show that our method achieves state-of-the-art performance in the localisation task.
  arXiv  Detail & Related papers  (2025-12-11T08:18:22Z)
• Revealing Temporal Label Noise in Multimodal Hateful Video Classification [17.69786804367003]
  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.
  arXiv  Detail & Related papers  (2025-08-06T21:55:59Z)
• 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)
• Multi-Scale Contrastive Learning for Video Temporal Grounding [42.180296672043404]
  Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding.<n>We propose a contrastive learning framework to capture salient semantics among video moments.
  arXiv  Detail & Related papers  (2024-12-10T03:34:56Z)
• 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)
• Controllable Augmentations for Video Representation Learning [34.79719112810065]
  We propose a framework to jointly utilize local clips and global videos to learn from detailed region-level correspondence as well as minimization general long-term temporal relations. Our framework is superior on three video benchmarks in action recognition and video retrieval, capturing more accurate temporal dynamics.
  arXiv  Detail & Related papers  (2022-03-30T19:34:32Z)
• Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories [56.91664227337115]
  We introduce a collaborative memory mechanism that encodes information across multiple sampled clips of a video at each training iteration. This enables the learning of long-range dependencies beyond a single clip. Our proposed framework is end-to-end trainable and significantly improves the accuracy of video classification at a negligible computational overhead.
  arXiv  Detail & Related papers  (2021-04-02T18:59:09Z)

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.