01
Multimedia Understanding and Safety
Fusing and reasoning across vision, audio and text to detect and localise hateful content, deepfakes and misinformation in online media, and building the benchmark datasets that measure this.
Multimedia Understanding and Safety
9 publications- 2026CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video DetectionACM International Conference on Multimedia (ACM MM)
- 2026MultiHateLoc: Towards Temporal Localisation of Multimodal Hate Content in Online VideosProceedings of the ACM Web Conference (The Web Conference)
- 2026Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake DetectionIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2026Reasoning-Aware Multimodal Fusion for Hateful Video DetectionTransactions on Machine Learning Research (TMLR)
- 2026Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial ReasoningIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2025DeHate: A Holistic Hateful Video Dataset for Explicit and Implicit Hate DetectionACM Multimedia 2025
- 2025Integrating Semantic, Sentiment, and Object-Level Cues for Multimodal Video-Based Fake News DetectionACM DHOW 2025
- 2025Multimodal Hate Detection Using Dual-Stream Graph Neural NetworksBritish Machine Vision Conference (BMVC)
- 2025Revealing Temporal Label Noise in Multimodal Hateful Video ClassificationACM Multimedia Workshop on Multimodal Understanding for a Safer Web
