Chenyang Si

14

Papers

1,230

Total Citations

Papers (14)

VBench: Comprehensive Benchmark Suite for Video Generative Models

VideoBooth: Diffusion-based Video Generation with Image Prompts

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model

Multistage Adversarial Losses for Pose-Based Human Image Synthesis

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation

FreeU: Free Lunch in Diffusion U-Net

An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition

MetaFormer Is Actually What You Need for Vision

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

Inception Transformer

NeurIPS 2022arXiv

Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation