activity
20172026
most citedSimultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion

19 citations · 19 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

KD-CVG: A Knowledge-Driven Approach for Creative Video Generation

Linkai Liu, Wei Feng, Xi Zhao +9

Creative Generation (CG) leverages generative models to automatically produce advertising content that highlights product features, and it has been a significant focus of recent re…

cs.CV2025

RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning

Zipeng Guo, Lichen Ma, Xiaolong Fu +13

In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional…

cs.CV2025

Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models

Yuchen Zhou, Jiayu Tang, Shuo Yang +6

Vision-Language Models (VLMs), exemplified by CLIP, have emerged as foundational for multimodal intelligence. However, their capacity for logical understanding remains significantl…

cs.CV2025

Where, What, Why: Towards Explainable Driver Attention Prediction

Yuchen Zhou, Jiayu Tang, Xiaoyan Xiao +6

Modeling task-driven attention in driving is a fundamental challenge for both autonomous vehicles and cognitive science. Existing methods primarily predict where drivers look by ge…

cs.CV2024

Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition

Yuchen Zhou, Linkai Liu, Chao Gou

Most existing attention prediction research focuses on salient instances like humans and objects. However, the more complex interaction-oriented attention, arising from the compreh…

cs.CV2018

M4CD: A Robust Change Detection Method for Intelligent Visual Surveillance

Kunfeng Wang, Chao Gou, Fei-Yue Wang

In this paper, we propose a robust change detection method for intelligent visual surveillance. This method, named M4CD, includes three major steps. Firstly, a sample-based backgro…