Ziyun Zeng

5

Papers

40

Total Citations

Papers (5)

VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting

GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval

Learning Transferable Spatiotemporal Representations From Natural Script Knowledge