8 papers
Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep
Tianyi Liu, Ye Lu, Linfeng Zhang +5
Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity,…
A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba
Ye Lu, Jie Wang, Jianjun Gao +3
Recent Mamba-based methods for the pose-lifting task tend to model joint dependencies by 2D-to-1D mapping with diverse scanning strategies. Though effective, they struggle to model…
PromptSR: Cascade Prompting for Lightweight Image Super-Resolution
Wenyang Liu, Chen Cai, Jianjun Gao +4
Although the lightweight Vision Transformer has significantly advanced image super-resolution (SR), it faces the inherent challenge of a limited receptive field due to the window-b…
From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition
Chen Cai, Tianyi Liu, Jianjun Gao +5
Recent Multimodal Large Language Models (MLLMs) exhibit strong zero-shot abilities but struggle with complex Grounded Situation Recognition (GSR) and are resource-intensive for edg…
SSH-Net: A Self-Supervised and Hybrid Network for Noisy Image Watermark Removal
Wenyang Liu, Jianjun Gao, Kim-Hui Yap
Visible watermark removal is challenging due to its inherent complexities and the noise carried within images. Existing methods primarily rely on supervised learning approaches tha…
CL-HOI: Cross-Level Human-Object Interaction Distillation from Vision Large Language Models
Jianjun Gao, Chen Cai, Ruoyu Wang +4
Human-object interaction (HOI) detection has seen advancements with Vision Language Models (VLMs), but these methods often depend on extensive manual annotations. Vision Large Lang…