English
Related papers

Related papers: Hyperbolic Multiview Pretraining for Robotic Manip…

200 papers

Representing data in hyperbolic space can effectively capture latent hierarchical relationships. With the goal of enabling accurate classification of points in hyperbolic space while respecting their hyperbolic geometry, we introduce…

Machine Learning · Computer Science 2018-06-04 Hyunghoon Cho , Benjamin DeMeo , Jian Peng , Bonnie Berger

Understanding the intricate mappings between visual stimuli and neural responses is a fundamental challenge in cognitive neuroscience. While current approaches predominantly align images and functional magnetic resonance imaging (fMRI)…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Zihan Ma , Tian Xia , Kexin Wang , Xiao Li , Xiaowei He , Yudan Ren

3D human meshes show a natural hierarchical structure (like torso-limbs-fingers). But existing video-based 3D human mesh recovery methods usually learn mesh features in Euclidean space. It's hard to catch this hierarchical structure…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Xiang Zhang , Suping Wu , Weibin Qiu , Zhaocheng Jin , Sheng Yang

In recent years, there has been a growing trend of incorporating hyperbolic geometry methods into computer vision. While these methods have achieved state-of-the-art performance on various metric learning tasks using hyperbolic distance…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Yun Yue , Fangzhou Lin , Guanyi Mou , Ziming Zhang

Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph. However, in practice, learning hyperbolic embeddings of hierarchical data is…

Machine Learning · Computer Science 2024-07-24 Zhangyu Wang , Lantian Xu , Zhifeng Kong , Weilong Wang , Xuyu Peng , Enyang Zheng

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean…

Machine Learning · Computer Science 2018-06-29 Octavian-Eugen Ganea , Gary Bécigneul , Thomas Hofmann

Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…

Robotics · Computer Science 2025-12-16 Yicheng Feng , Wanpeng Zhang , Ye Wang , Hao Luo , Haoqi Yuan , Sipeng Zheng , Zongqing Lu

General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Chengkai Hou , Yanjie Ze , Yankai Fu , Zeyu Gao , Songbo Hu , Yue Yu , Shanghang Zhang , Huazhe Xu

Existing weakly supervised video violence detection (VVD) methods primarily rely on Euclidean representation learning, which often struggles to distinguish visually similar yet semantically distinct events due to limited hierarchical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Jiaxu Leng , Zhanjie Wu , Mingpi Tan , Mengjingcheng Mo , Jiankang Zheng , Qingqing Li , Ji Gan , Xinbo Gao

The deployment of humanoid robots for dexterous manipulation in unstructured environments remains challenging due to perceptual limitations that constrain the effective workspace. In scenarios where physical constraints prevent the robot…

Robotics · Computer Science 2026-03-09 Pei Qu , Zheng Li , Yufei Jia , Ziyun Liu , Liang Zhu , Haoang Li , Jinni Zhou , Jun Ma

Backward compatible representation learning enables updated models to integrate seamlessly with existing ones, avoiding to reprocess stored data. Despite recent advances, existing compatibility approaches in Euclidean space neglect the…

Machine Learning · Computer Science 2025-06-09 Ngoc Bui , Menglin Yang , Runjin Chen , Leonardo Neves , Mingxuan Ju , Rex Ying , Neil Shah , Tong Zhao

Visual environments are inherently hierarchical, as a panoramic view naturally encompasses and organizes multiple perspective views within its field. Capturing this hierarchy is crucial for effective perspective-to-equirectangular (P2E)…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Suhan Woo , Seongwon Lee , Jinwoo Jang , Euntai Kim

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained…

We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Muhammad Abdullah Jamal , Omid Mohareri

Learning representations according to the underlying geometry is of vital importance for non-Euclidean data. Studies have revealed that the hyperbolic space can effectively embed hierarchical or tree-like data. In particular, the few past…

Machine Learning · Computer Science 2023-06-16 Eric Qu , Dongmian Zou

Recently, there has been a surge of interest in representation learning in hyperbolic spaces, driven by their ability to represent hierarchical data with significantly fewer dimensions than standard Euclidean spaces. However, the viability…

Machine Learning · Computer Science 2022-11-02 Melanie Weber , Manzil Zaheer , Ankit Singh Rawat , Aditya Menon , Sanjiv Kumar

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

Robotics · Computer Science 2023-08-16 Jianren Wang , Sudeep Dasari , Mohan Kumar Srirama , Shubham Tulsiani , Abhinav Gupta

Visual robotic manipulation research and applications often use multiple cameras, or views, to better perceive the world. How else can we utilize the richness of multi-view data? In this paper, we investigate how to learn good…

Robotics · Computer Science 2023-06-01 Younggyo Seo , Junsu Kim , Stephen James , Kimin Lee , Jinwoo Shin , Pieter Abbeel

Hyperbolic embeddings have demonstrated their effectiveness in capturing measures of uncertainty and hierarchical relationships across various deep-learning tasks, including image segmentation and active learning. However, their application…

Machine Learning · Computer Science 2024-08-12 Paolo Mandica , Luca Franco , Konstantinos Kallidromitis , Suzanne Petryk , Fabio Galasso

Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trained for static recognition or vision-language alignment,…