Search Results for author:
Found 35 papers, 16 papers with code
CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation
To generate high-quality segmentation predictions from referring expressions, we propose CLIPUNetr - a new CLIP-driven referring expression segmentation network.
Deep Probabilistic Movement Primitives with a Bayesian Aggregator
Movement primitives are trainable parametric models that reproduce robotic movements starting from a limited set of demonstrations.
A Simple Decentralized Cross-Entropy Method
To tackle this issue, we propose Decentralized CEM (DecentCEM), a simple but effective improvement over classical CEM, by using an ensemble of CEM instances running independently from one another, and each performing a local improvement of its own sampling distribution.
Dynamic Decision Frequency with Continuous Options
In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals.
Generalizable task representation learning from human demonstration videos: a geometric approach
We study the problem of generalizable task learning from human demonstration videos without extra training on the robot or pre-recorded robot motions.
Decentralized Cross-Entropy Method for Model-Based Reinforcement Learning
Further, we extend the decentralized approach to sequential decision-making problems where we show in 13 continuous control benchmark environments that it matches or outperforms the state-of-the-art CEM algorithms in most cases, under the same budget of the total number of samples for planning.
Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving
Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects.
Video Class Agnostic Segmentation Benchmark for Autonomous Driving
We formalize the task of video class agnostic segmentation from monocular video sequences in autonomous driving to account for unknown objects.
Boundary-Aware Segmentation Network for Mobile and Web Applications
In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation.
Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning
We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills.
U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD).
Ranked #1 on
Salient Object Detection
on SOD
A Geometric Perspective on Visual Imitation Learning
We consider the problem of visual imitation learning without human supervision (e. g. kinesthetic teaching or teleoperation), nor access to an interactive reinforcement learning (RL) training environment.
Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream
In this paper, to model the intended concepts of manipulation, we present a vision dataset under a strictly constrained knowledge domain for both robot and human manipulations, where manipulation concepts and relations are stored by an ontology system in a taxonomic manner.
Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings
Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels.
One-Shot Weakly Supervised Video Object Segmentation
Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks.
Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans
We observe that our method demonstrates time-efficient path planning behavior with high success rate in mapless navigation tasks.
Robotics
Bridging Visual Perception with Contextual Semantics for Understanding Robot Manipulation Tasks
Using the framework, we present a case study where robot performs manipulation actions in a kitchen environment, bridging visual perception with contextual semantics using the generated dynamic knowledge graphs.
Adaptive Masked Proxies for Few-Shot Segmentation
Our method is evaluated on PASCAL-$5^i$ dataset and outperforms the state-of-the-art in the few-shot semantic segmentation.
Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting
A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing manual segmentation labels.
Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approach
Our proposed method can directly learn from raw videos, which removes the need for hand-engineered task specification.
Robotics
RTSeg: Real-time Semantic Segmentation Comparative Study
In this paper, we address this gap by presenting a real-time semantic segmentation benchmarking framework with a decoupled design for feature extraction and decoding methods.
End-to-end detection-segmentation network with ROI convolution
We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit.
Segmentation-by-Detection: A Cascade Network for Volumetric Medical Image Segmentation
We propose an attention mechanism for 3D medical image segmentation.
MODNet: Moving Object Detection Network with Motion and Appearance for Autonomous Driving
Our experiments show that the proposed method outperforms state of the art methods that utilize motion cue only with 21. 5% in mAP on KITTI MOD.
Incremental 3D Line Segment Extraction from Semi-dense SLAM
This approach reduces a 3D line segment fitting problem into two 2D line segment fitting problems and takes advantage of both images and depth maps.
Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges
In this paper, the semantic segmentation problem is explored from the perspective of automated driving.
Real-Time Salient Closed Boundary Tracking via Line Segments Perceptual Grouping
The tracking scheme is coherently integrated into a perceptual grouping framework in which the visual tracking problem is tackled by identifying a subset of these line segments and connecting them sequentially to form a closed boundary with the largest saliency and a certain similarity to the previous one.
4-DoF Tracking for Robot Fine Manipulation Tasks
One of these trackers is a newly developed learning based tracker that relies on learning discriminative correlation filters while the other is a refinement of a recent 8 DoF RANSAC based tracker adapted with a new appearance model for tracking 4 DoF motion.
Incremental Learning for Robot Perception through HRI
Given this information, the robot visually explores the object and adds images from it to re-train the perception module.
Convolutional Gated Recurrent Networks for Video Segmentation
This architecture is tested for both binary and semantic video segmentation tasks.
Unifying Registration based Tracking: A Case Study with Structural Similarity
This paper adapts a popular image quality measure called structural similarity for high precision registration based tracking while also introducing a simpler and faster variant of the same.
Parking Stall Vacancy Indicator System Based on Deep Convolutional Neural Networks
Visual detection methods represent a cost-effective option, since they can take advantage of hardware usually already available in many parking lots, namely cameras.
Recurrent Fully Convolutional Networks for Video Segmentation
Accordingly, we propose a novel method for online segmentation of video sequences that incorporates temporal data.
Modular Decomposition and Analysis of Registration based Trackers
We show how existing trackers can be broken down using the suggested methodology and compare the performance of the default configuration chosen by the authors against other possible combinations to demonstrate the new insights that can be gained by such an approach.
Modular Tracking Framework: A Unified Approach to Registration based Tracking
This paper presents a modular, extensible and highly efficient open source framework for registration based tracking called Modular Tracking Framework (MTF).
