6 papers
M-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining
Rui Lv, Juncheng Mo, Tianyi Chu +11
Graphical User Interface (GUI) agent is pivotal to advancing intelligent human-computer interaction paradigms. Constructing powerful GUI agents necessitates the large-scale annotat…
Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection
Ziqiang Dang, Jianfang Li, Lin Liu
Facial landmark detection is a fundamental problem in computer vision for many downstream applications. This paper introduces a new facial landmark detector based on vision transfo…
SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing
Hongyi Jing, Jiafu Chen, Chen Rao +9
The existing Multimodal Large Language Models (MLLMs) for GUI perception have made great progress. However, the following challenges still exist in prior methods: 1) They model dis…
GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments
Lin Zeng, Boming Zhao, Jiarui Hu +4
Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-…
TexPro: Text-guided PBR Texturing with Procedural Material Modeling
Ziqiang Dang, Wenqi Dong, Zesong Yang +4
In this paper, we present TexPro, a novel method for high-fidelity material generation for input 3D meshes given text prompts. Unlike existing text-conditioned texture generation m…
SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis
Xiangyue Zhang, Jianfang Li, Jiaxu Zhang +4
Co-speech gesture generation must carefully integrate common rhythmic motion with rare yet essential semantic gestures. In this work, we propose SemTalk for holistic co-speech gest…