65 citations · 99 across the 13 of their papers we have counts for
14 papers · 1 filter
ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inference
Youze Huang, Penghui Ruan, Bojia Zi +3
Geometry-aware video object scaling aims to anisotropically resize the object along object-centric axes while preserving geometric plausibility, temporal coherence, and background…
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
Binhao Wang, Shihao Zhao, Bo Cheng +6
Recent diffusion-based approaches have made substantial progress in image layer decomposition. However, accurately decomposing complex natural images remains challenging due to dif…
Unison: A Fully Automatic, Task-Universal, and Low-Cost Framework for Unified Understanding and Generation
Shihao Zhao, Yitong Chen, Zeyinzi Jiang +5
Unified understanding and generation is a highly appealing research direction in multimodal learning. There exist two approaches: one trains a transformer via an auto-regressive pa…
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
Bojia Zi, Weixuan Peng, Xianbiao Qi +4
Recent advances in video diffusion models have driven rapid progress in video editing techniques. However, video object removal, a critical subtask of video editing, remains challe…
Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
Bojia Zi, Penghui Ruan, Marco Chen +7
Recent advancements in video generation have spurred the development of video editing techniques, which can be divided into inversion-based and end-to-end methods. However, current…
Adversarial Prompt Distillation for Vision-Language Models
Lin Luo, Xin Wang, Bojia Zi +3
Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image Pre-training (CLIP) have been shown to be susceptible to adversarial attacks, raising concerns ab…
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities
Shaozhe Hao, Xuantong Liu, Xianbiao Qi +5
We introduce BiGR, a novel conditional image generation model using compact binary latent codes for generative training, focusing on enhancing both generation and representation ca…
ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction
Shaozhe Hao, Kai Han, Zhengyao Lv +2
While personalized text-to-image generation has enabled the learning of a single concept from multiple images, a more practical yet challenging scenario involves learning multiple…
CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
Bojia Zi, Shihao Zhao, Xianbiao Qi +6
Recent advancements in video generation have been remarkable, yet many existing methods struggle with issues of consistency and poor text-video alignment. Moreover, the field lacks…
Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation
Shihao Zhao, Shaozhe Hao, Bojia Zi +2
Text-to-image generation has made significant advancements with the introduction of text-to-image diffusion models. These models typically consist of a language model that interpre…
ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation
Shaozhe Hao, Kai Han, Shihao Zhao +1
Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustra…
Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
Shihao Zhao, Dongdong Chen, Yen-Chun Chen +4
Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. How…
What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Shihao Zhao, Xingjun Ma, Yisen Wang +3
Deep neural networks (DNNs) are increasingly deployed in different applications to achieve state-of-the-art performance. However, they are often applied as a black box with limited…
Clean-Label Backdoor Attacks on Video Recognition Models
Shihao Zhao, Xingjun Ma, Xiang Zheng +3
Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean tes…