English
Related papers

Related papers: Building a Strong Pre-Training Baseline for Univer…

200 papers

3D captioning, which aims to describe the content of 3D scenes in natural language, remains highly challenging due to the inherent sparsity of point clouds and weak cross-modal alignment in existing methods. To address these challenges, we…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Ting Huang , Zeyu Zhang , Yemin Wang , Hao Tang

Multilingual vision-language (V&L) pre-training has achieved remarkable progress in learning universal representations across different modalities and languages. In spite of recent success, there still remain challenges limiting further…

Computation and Language · Computer Science 2023-05-16 Chulun Zhou , Yunlong Liang , Fandong Meng , Jinan Xu , Jinsong Su , Jie Zhou

General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped. We present an algorithm which…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Kirill Mazur , Edgar Sucar , Andrew J. Davison

Open-vocabulary 3D object detection for autonomous driving aims to detect novel objects beyond the predefined training label sets in point cloud scenes. Existing approaches achieve this by connecting traditional 3D object detectors with…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Adrian Chow , Evelien Riddell , Yimu Wang , Sean Sedwards , Krzysztof Czarnecki

Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Xingyi He , Hao Yu , Sida Peng , Dongli Tan , Zehong Shen , Hujun Bao , Xiaowei Zhou

Vision-Language Models (VLMs) have shown significant progress in open-set challenges. However, the limited availability of 3D datasets hinders their effective application in 3D scene understanding. We propose LOC, a general language-guided…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Yuhang Gao , Xiang Xiang , Sheng Zhong , Guoyou Wang

Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Xun Jiang , Yufan Gu , Disen Hu , Yuqing Hou , Yazhou Yao , Fumin Shen , Heng Tao Shen , Xing Xu

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…

Computer Vision and Pattern Recognition · Computer Science 2023-07-19 Chong Liu , Yuqi Zhang , Hongsong Wang , Weihua Chen , Fan Wang , Yan Huang , Yi-Dong Shen , Liang Wang

A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in…

Computer Vision and Pattern Recognition · Computer Science 2021-01-28 Ting Yao , Yiheng Zhang , Zhaofan Qiu , Yingwei Pan , Tao Mei

3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Feng Xiao , Hongbin Xu , Guocan Zhao , Wenxiong Kang

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Julien Denize , Jaonary Rabarisoa , Astrid Orcesi , Romain Hérault

Learning from source code usually requires a large amount of labeled data. Despite the possible scarcity of labeled data, the trained model is highly task-specific and lacks transferability to different tasks. In this work, we present…

Machine Learning · Computer Science 2021-03-05 Linfeng Liu , Hoan Nguyen , George Karypis , Srinivasan Sengamedu

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific levels of linguistic units. This work introduces universal language representation learning, i.e.,…

Computation and Language · Computer Science 2021-06-01 Yian Li , Hai Zhao

Recent advancements in vision foundation models (VFMs) have revolutionized visual perception in 2D, yet their potential for 3D scene understanding, particularly in autonomous driving applications, remains underexplored. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Lingdong Kong , Xiang Xu , Youquan Liu , Jun Cen , Runnan Chen , Wenwei Zhang , Liang Pan , Kai Chen , Ziwei Liu

High-fidelity 3D scene reconstruction has been substantially advanced by recent progress in neural fields. However, most existing methods train a separate network from scratch for each individual scene. This is not scalable, inefficient,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-02 Yang Fu , Shalini De Mello , Xueting Li , Amey Kulkarni , Jan Kautz , Xiaolong Wang , Sifei Liu

Recovering 3D structures with open-vocabulary scene understanding from 2D images is a fundamental but daunting task. Recent developments have achieved this by performing per-scene optimization with embedded language information. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Fangfu Liu , Hao Li , Jiawei Chi , Hanyang Wang , Minghui Yang , Fudong Wang , Yueqi Duan

Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies have turned to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Jianbiao Mei , Yu Yang , Mengmeng Wang , Junyu Zhu , Jongwon Ra , Yukai Ma , Laijian Li , Yong Liu

Existing diffusion-based 3D scene generation methods primarily operate in 2D image/video latent spaces, which makes maintaining cross-view appearance and geometric consistency inherently challenging. To bridge this gap, we present OneWorld,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Sensen Gao , Zhaoqing Wang , Qihang Cao , Dongdong Yu , Changhu Wang , Tongliang Liu , Mingming Gong , Jiawang Bian

Semantic segmentation networks are usually pre-trained once and not updated during deployment. As a consequence, misclassifications commonly occur if the distribution of the training data deviates from the one encountered during the robot's…

Robotics · Computer Science 2023-02-15 Jonas Frey , Hermann Blum , Francesco Milano , Roland Siegwart , Cesar Cadena

Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspective-invariance…

Computer Vision and Pattern Recognition · Computer Science 2022-07-14 Lanxiao Li , Michael Heizmann