English
Related papers

Related papers: Learning Object Permanence from Videos via Latent …

200 papers

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…

The problem of object localization and recognition on autonomous mobile robots is still an active topic. In this context, we tackle the problem of learning a model of visual saliency directly on a robot. This model, learned and improved…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Celine Craye , Timothee Lesort , David Filliat , Jean-Francois Goudou

Recent time-contrastive learning approaches manage to learn invariant object representations without supervision. This is achieved by mapping successive views of an object onto close-by internal representations. When considering this…

Machine Learning · Computer Science 2022-05-13 Arthur Aubret , Céline Teulière , Jochen Triesch

Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built. Recent work on simple 2D and 3D datasets has shown that models…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Thomas Kipf , Gamaleldin F. Elsayed , Aravindh Mahendran , Austin Stone , Sara Sabour , Georg Heigold , Rico Jonschkowski , Alexey Dosovitskiy , Klaus Greff

Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Andrii Zadaianchuk , Maximilian Seitzer , Georg Martius

Inspired by the remarkable ability of the infant visual learning system, a recent study collected first-person images from children to analyze the `training data' that they receive. We conduct a follow-up study that investigates two…

Computer Vision and Pattern Recognition · Computer Science 2019-06-05 Satoshi Tsutsui , Dian Zhi , Md Alimoor Reza , David Crandall , Chen Yu

Recently, learning-based ego-motion estimation approaches have drawn strong interest from studies mostly focusing on visual perception. These groundbreaking works focus on unsupervised learning for odometry estimation but mostly for visual…

Robotics · Computer Science 2019-02-28 Younggun Cho , Giseop Kim , Ayoung Kim

Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Jiaojiao Fang , Guizhong Liu

As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily…

Image and Video Processing · Electrical Eng. & Systems 2023-01-12 Ezgi Ozyilkan , Mateen Ulhaq , Hyomin Choi , Fabien Racape

Object detection models shipped with camera-equipped edge devices cannot cover the objects of interest for every user. Therefore, the incremental learning capability is a critical feature for a robust and personalized object detection…

Computer Vision and Pattern Recognition · Computer Science 2019-09-24 Dawei Li , Serafettin Tasci , Shalini Ghosh , Jingwen Zhu , Junting Zhang , Larry Heck

For computer vision systems to operate in dynamic situations, they need to be able to represent and reason about object permanence. We introduce a framework for learning to estimate 4D visual representations from monocular RGB-D, which is…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Basile Van Hoorick , Purva Tendulkar , Didac Suris , Dennis Park , Simon Stent , Carl Vondrick

Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understanding both what the objects are and where they are located is…

In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes…

Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representations for robotic manipulation tasks without human labeling…

Robotics · Computer Science 2018-11-20 Eric Jang , Coline Devin , Vincent Vanhoucke , Sergey Levine

This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in…

Machine Learning · Computer Science 2016-03-10 Peter Ondruska , Ingmar Posner

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

Computer Vision and Pattern Recognition · Computer Science 2016-02-03 Loris Bazzani , Alessandro Bergamo , Dragomir Anguelov , Lorenzo Torresani

Object-centric slot attention is a powerful framework for unsupervised learning of structured and explainable representations that can support reasoning about objects and actions, including in surgical videos. While conventional…

Image and Video Processing · Electrical Eng. & Systems 2026-03-04 Guiqiu Liao , Matjaz Jogan , Marcel Hussing , Kenta Nakahashi , Kazuhiro Yasufuku , Amin Madani , Eric Eaton , Daniel A. Hashimoto

We present a system for learning motion of independently moving objects from stereo videos. The only human annotation used in our system are 2D object bounding boxes which introduce the notion of objects to our system. Unlike prior learning…

Computer Vision and Pattern Recognition · Computer Science 2019-01-09 Zhe Cao , Abhishek Kar , Christian Haene , Jitendra Malik

Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distractors. Although recent latent action policy optimization…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Albina Klepach , Alexander Nikulin , Ilya Zisman , Denis Tarasov , Alexander Derevyagin , Andrei Polubarov , Nikita Lyubaykin , Igor Kiselev , Vladislav Kurenkov

Current autonomous driving systems are composed of a perception system and a decision system. Both of them are divided into multiple subsystems built up with lots of human heuristics. An end-to-end approach might clean up the system and…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Jianyu Chen , Zhuo Xu , Masayoshi Tomizuka