2 citations · 3 across the 8 of their papers we have counts for
8 papers · 1 filter
VIMI: Grounding Video Generation through Multi-modal Instruction
Yuwei Fang, Willi Menapace, Aliaksandr Siarohin +5
Existing text-to-video diffusion models rely solely on text-only encoders for their pretraining. This limitation stems from the absence of large-scale multimodal prompt video datas…
Hierarchical Patch Diffusion Models for High-Resolution Video Generation
Ivan Skorokhodov, Willi Menapace, Aliaksandr Siarohin +1
Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to high-resolution inputs is challenging and requires restructuring th…
Harnessing Large Language Models for Training-free Video Anomaly Detection
Luca Zanella, Willi Menapace, Massimiliano Mancini +2
Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Existing works mostly rely on training deep models to learn the distribution of normality with e…
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Tsai-Shien Chen, Aliaksandr Siarohin, Willi Menapace +8
The quality of the data and annotation upper-bounds the quality of a downstream model. While there exist large text corpora and image-text pairs, high-quality video-text data is mu…
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
Willi Menapace, Aliaksandr Siarohin, Ivan Skorokhodov +8
Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since vide…
Delving into CLIP latent space for Video Anomaly Recognition
Luca Zanella, Benedetta Liberatori, Willi Menapace +3
We tackle the complex problem of detecting and recognising anomalies in surveillance videos at the frame level, utilising only video-level supervision. We introduce the novel metho…