69 citations · 149 across the 13 of their papers we have counts for
13 papers · 1 filter
Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
Wang Chen, Yuhui Zeng, Yongdong Luo +5
Frame selection is crucial due to high frame redundancy and limited context windows when applying Large Vision-Language Models (LVLMs) to long videos. Current methods typically sel…
Event-Anchored Frame Selection for Effective Long-Video Understanding
Wang Chen, Yongdong Luo, Yuhui Zeng +5
Massive frame redundancy and limited context window make efficient frame selection crucial for long-video understanding with large vision-language models (LVLMs). Prevailing approa…
MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild
Yu-Xiang Zeng, Jun-Wei Hsieh, Xin Li +1
Detecting small scene text instances in the wild is particularly challenging, where the influence of irregular positions and nonideal lighting often leads to detection errors. We p…
Securing Deep Generative Models with Universal Adversarial Signature
Yu Zeng, Mo Zhou, Yuan Xue +1
Recent advances in deep generative models have led to the development of methods capable of synthesizing high-quality, realistic images. These models pose threats to society due to…
SceneComposer: Any-Level Semantic Image Synthesis
Yu Zeng, Zhe Lin, Jianming Zhang +4
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes. More s…
Shape-guided Object Inpainting
Yu Zeng, Zhe Lin, Vishal M. Patel
Previous works on image inpainting mainly focus on inpainting background or partially missing objects, while the problem of inpainting an entire missing object remains unexplored.…
SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
Yu Zeng, Zhe Lin, Vishal M. Patel
Sketch-based image manipulation is an interactive image editing task to modify an image based on input sketches from users. Existing methods typically formulate this task as a cond…
CR-Fill: Generative Image Inpainting with Auxiliary Contexutal Reconstruction
Yu Zeng, Zhe Lin, Huchuan Lu +1
Recent deep generative inpainting methods use attention layers to allow the generator to explicitly borrow feature patches from the known region to complete a missing region. Due t…
High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
Yu Zeng, Zhe Lin, Jimei Yang +3
Existing image inpainting methods often produce artifacts when dealing with large holes in real applications. To address this challenge, we propose an iterative inpainting method w…
Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation
Yu Zeng, Yunzhi Zhuge, Huchuan Lu +1
Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connection…
Multi-source weak supervision for saliency detection
Yu Zeng, Yunzhi Zhuge, Huchuan Lu +3
The high cost of pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source usually does not con…
An Unsupervised Game-Theoretic Approach to Saliency Detection
Yu Zeng, Huchuan Lu, Ali Borji +1
We propose a novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data. First, saliency detection problem is formulated as a…
Statistics of Deep Generated Images
Yu Zeng, Huchuan Lu, Ali Borji
Here, we explore the low-level statistics of images generated by state-of-the-art deep generative models. First, Variational auto-encoder (VAE~\cite{kingma2013auto}), Wasserstein g…