English
Related papers

Related papers: JIST: Joint Image and Sequence Training for Sequen…

200 papers

We propose a method to train deep networks to decompose videos into 3D geometry (camera and depth), moving objects, and their motions, with no supervision. We build on the idea of view synthesis, which uses classical camera geometry to…

Computer Vision and Pattern Recognition · Computer Science 2021-06-02 Dan Xu , Andrea Vedaldi , Joao F. Henriques

Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which…

Computer Vision and Pattern Recognition · Computer Science 2021-08-26 Golnaz Ghiasi , Barret Zoph , Ekin D. Cubuk , Quoc V. Le , Tsung-Yi Lin

We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot. Our system learns from conventional geometric SLAM, and outputs, using a single camera, the topological pose of…

Computer Vision and Pattern Recognition · Computer Science 2019-02-07 Punarjay Chakravarty , Praveen Narayanan , Tom Roussel

Visual (re)localization addresses the problem of estimating the 6-DoF (Degree of Freedom) camera pose of a query image captured in a known scene, which is a key building block of many computer vision and robotics applications. Recent…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Siyan Dong , Shuzhe Wang , Yixin Zhuang , Juho Kannala , Marc Pollefeys , Baoquan Chen

This work presents a novel RGB-D SLAM approach to simultaneously segment, track and reconstruct the static background and large dynamic rigid objects that can occlude major portions of the camera view. Previous approaches treat dynamic…

Robotics · Computer Science 2022-01-17 Ran Long , Christian Rauch , Tianwei Zhang , Vladimir Ivan , Sethu Vijayakumar

Simultaneous Localization and Mapping (SLAM) plays an important role in many robotics fields, including social robots. Many of the available visual SLAM methods are based on the assumption of a static world and struggle in dynamic…

Robotics · Computer Science 2025-10-06 Mobin Habibpour , Alireza Nemati , Ali Meghdari , Alireza Taheri , Shima Nazari

Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent…

Computer Vision and Pattern Recognition · Computer Science 2021-07-15 Ping Wang , Jizong Peng , Marco Pedersoli , Yuanfeng Zhou , Caiming Zhang , Christian Desrosiers

Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this…

Robotics · Computer Science 2024-03-06 Christina Kassab , Matias Mattamala , Lintong Zhang , Maurice Fallon

Visual Geo-localization (VG) refers to the process to identify the location described in query images, which is widely applied in robotics field and computer vision tasks, such as autonomous driving, metaverse, augmented reality, and SLAM.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Chen Mao , Jingqi Hu

Recent algorithms for image manipulation detection almost exclusively use deep network models. These approaches require either dense pixelwise groundtruth masks, camera ids, or image metadata to train the networks. On one hand, constructing…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Susmit Agrawal , Prabhat Kumar , Siddharth Seth , Toufiq Parag , Maneesh Singh , Venkatesh Babu

This paper presents a new regularization method to train a fully convolutional network for semantic tissue segmentation in histopathological images. This method relies on the benefit of unsupervised learning, in the form of image…

Computer Vision and Pattern Recognition · Computer Science 2020-11-26 C. T. Sari , C. Sokmensuer , C. Gunduz-Demir

Cross-domain Click-Through Rate prediction aims to tackle the data sparsity and the cold start problems in online advertising systems by transferring knowledge from source domains to a target domain. Most existing methods rely on…

Artificial Intelligence · Computer Science 2025-07-08 Wei Xu , Haoran Li , Baoyuan Ou , Lai Xu , Yingjie Qin , Ruilong Su , Ruiwen Xu

Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art…

Robotics · Computer Science 2018-11-05 Mehdi Hosseinzadeh , Yasir Latif , Trung Pham , Niko Suenderhauf , Ian Reid

Image registration is a process of aligning two or more images of same objects using geometric transformation. Most of the existing approaches work on the assumption of location invariance. These approaches require object-centric images to…

Computer Vision and Pattern Recognition · Computer Science 2019-01-14 Deepak Mishra , Rajeev Ranjan , Santanu Chaudhury , Mukul Sarkar , Arvinder Singh Soin

We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation. While existing work has largely focused on…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Tete Xiao , Colorado J Reed , Xiaolong Wang , Kurt Keutzer , Trevor Darrell

Existing Simultaneous Localization and Mapping (SLAM) approaches are limited in their scalability due to growing map size in long-term robot operation. Moreover, processing such maps for localization and planning tasks leads to the…

Humans' ability to detect and locate salient objects on images is remarkably fast and successful. Performing this process by using eye tracking equipment is expensive and cannot be easily applied, and computer modeling of this human…

Computer Vision and Pattern Recognition · Computer Science 2014-03-03 Hamdi Yalin Yalic

We present joint learning of instance and semantic segmentation for visible and occluded region masks. Sharing the feature extractor with instance occlusion segmentation, we introduce semantic occlusion segmentation into the instance…

Robotics · Computer Science 2020-01-22 Kentaro Wada , Kei Okada , Masayuki Inaba

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Kaifeng Chen , Daniel Salz , Huiwen Chang , Kihyuk Sohn , Dilip Krishnan , Mojtaba Seyedhosseini

Environment perception is a crucial ability for robot's interaction into an environment. One of the first steps in this direction is the combined problem of simultaneous localization and mapping (SLAM). A new method, called G-SLAM, is…

Robotics · Computer Science 2016-07-19 Nikos Zikos , Vassilios Petridis