Search Results for author: Yaosi Hu

Found 4 papers, 1 papers with code

LaMD: Latent Motion Diffusion for Video Generation

no code implementations23 Apr 2023 Yaosi Hu, Zhenzhong Chen, Chong Luo

We present a latent motion diffusion (LaMD) framework, which consists of a motion-decomposed video autoencoder and a diffusion-based motion generator, to implement this idea.

Video Generation Video Reconstruction

Learning Human Cognitive Appraisal Through Reinforcement Memory Unit

no code implementations6 Aug 2022 Yaosi Hu, Zhenzhong Chen

We conceptualize the memory-enhancing mechanism as Reinforcement Memory Unit (RMU) that contains an appraisal state together with two positive and negative reinforcement memories.

Video Quality Assessment

Make It Move: Controllable Image-to-Video Generation with Text Descriptions

1 code implementation CVPR 2022 Yaosi Hu, Chong Luo, Zhenzhong Chen

With both controllable appearance and motion, TI2V aims at generating videos from a static image and a text description.

Image to Video Generation

Predicate correlation learning for scene graph generation

no code implementations6 Jul 2021 Leitian Tao, Li Mi, Nannan Li, Xianhang Cheng, Yaosi Hu, Zhenzhong Chen

For a typical Scene Graph Generation (SGG) method, there is often a large gap in the performance of the predicates' head classes and tail classes.

Graph Generation Scene Graph Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.