Led by Alan Yuille, the Bloomberg Distinguished Professor of Computational Cognitive Science, computer scientists from the Johns Hopkins Computational Cognition, Vision, and Learning research group will present eight new papers at the 2024 European Conference on Computer Vision, to be held September 29 through October 4 in Milan, Italy.
Managed by the European Computer Vision Association, ECCV is a biennial premier research conference that gathers the scientific and industrial communities in the areas of computer vision and machine learning.
The following papers will be presented by CCVL researchers:
- “3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation” by Zihao Xiao, Longlong Jing, Shangxuan Wu, Alex Zihao Zhu, Jingwei Ji, Chiyu Max Jiang, Wei-Chih Hung, Thomas Funkhouser, Weicheng Kuo, Anelia Angelova, Yin Zhou, and Shiwei Sheng
- “IG Captioner: Information Gain Captioners are Strong Zero-Shot Classifiers” by Chenglin Yang, Engr ’24 (PhD); Siyuan Qiao; Yuan Cao; Yu Zhang; Tao Zhu; Alan Yuille; and Jiahui Yu
- “iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning” by Tom Fischer, Yaoyao Liu, Artur Jesslen, Noor Ahmed, Prakhar Kaushik, Angtian Wang, Alan Yuille, Adam Kortylewski, and Eddy Ilg
- “NOVUM: Neural Object Volumes for Robust Object Classification” by Artur Jesslen, Guofeng Zhang, Angtian Wang, Wufei Ma, Alan Yuille, and Adam Kortylewski
- “SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference” by Feng Wang, Jieru Mei, and Alan Yuille
- “A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties” by Junfei Xiao, Ziqi Zhou, Wenxuan Li, Shiyi Lan, Jieru Mei, Zhiding Yu, Bingchen Zhao, Alan Yuille, Yuyin Zhou, and Cihang Xie
- “Radiative Gaussian Splatting for Efficient X-Ray Novel View Synthesis” by Yuanhao Cai, Yixun Liang, Jiahao Wang, Angtian Wang, Yulun Zhang, Xiaokang Yang, Zongwei Zhou, and Alan Yuille
- “Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data” by Wufei Ma, Kai Li, Zhongshi Jiang, Moustafa Meshry, Qihao Liu, Huiyu Wang, Christian Häne, and Alan Yuille