COGNITIVE ROBOTICS & AI LABORATORY
Research.
01 / RESEARCH FIELDS
Research
- 01Computer vision
- 02Robotics
- 03Machine learning
- 043D data recognition
02 / PRESENTATION MATERIAL
Presentation Material
- Feb. 2021 Information session, School of Computing, Tokyo Institute of Technology "Introductoin of Kanezaki Laboratory"
- Apr. 2020 Information session, School of Computing, Tokyo Institute of Technology "Introductoin of Kanezaki Laboratory"
03 / JOURNAL PUBLICATIONS
Journal Publications
EED: Embodied Environment Description through Robotic Visual Exploration.
A Framework for Training Larger Networks for Deep Reinforcement Learning.
Egocentric Human Activities Recognition with Multi-modal Interaction Sensing.
Multi-Agent Visual Coordination using Optical Wireless Communication.
View all+8
DAC: Disentanglement-and-Calibration Module for Cross-Domain Few-Shot Classification.
RotationNet for Joint Object Categorization and Unsupervised Pose Estimation from Multi-view Images.
Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering.
Visual Object Search by Learning Spatial Context.
GOSELO: Goal-Directed Obstacle and Self-Location Map for Robot Navigation using Reactive Neural Networks.
An Integration of Bottom-up and Top-Down Salient Cues on RGB-D Data: Saliency from Objectness vs. Non-Objectness.
Part-Based Geometric Categorization and Object Reconstruction in Cluttered Table-Top Scenes.
Partial Matching of Real Textured 3D Objects Using Color Cubic Higher-order Local Auto-Correlation Features.
04 / INTERNATIONAL CONFERENCES
International Conferences
Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images.
CounterAlign: Counterfactual Supervision for Vision-Language-Action Models.
COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation.
Touch2Insert: Zero-Shot Peg Insertion by Touching Intersections of Peg and Hole.
Embodied Navigation with Auxiliary Task of Action Description Prediction.
Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models.
View all+42
FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models.
Modality Selection and Skill Segmentation via Cross-Modality Attention.
EED: Embodied Environment Description through Robotic Visual Exploration.
OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation.
Active Object Recognition with Trained Multi-view Based 3D Object Recognition Network.
OffNav: Offline Reinforcement Learning for Visual Semantic Navigation.
Tactile Estimation of Extrinsic Contact Patch for Stable Placement.
Linking Vision and Multi-Agent Communication through Visible Light Communication using Event Cameras.
Multi-goal Audio-visual Navigation using Sound Direction Map.
Point Anywhere: Directed Object Estimation from Omnidirectional Images.
Multi Event Localization by Audio-Visual Fusion with Omnidirectional Camera and Microphone Array.
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification.
H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions.
EvIs-Kitchen: Egocentric Human Activities Recognition with Video and Inertial Sensor data.
OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching.
Object Memory Transformer for Object Goal Navigation.
Incremental Multi-view Object Detection from a Moving Camera.
Deep Reactive Planning in Dynamic Environments.
Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path.
A3C Based Motion Learning for an Autonomous Mobile Robot in Crowds.
Salient object detection on hyperspectral images using features learned from unsupervised segmentation task.
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints.
Unsupervised Image Segmentation by Backpropagation.
"Change the changeable" framework for implementation research in health.
Multi-modal U-Nets for Multi-task Scene Understanding.
SHREC'17 Track: Large-Scale 3D Shape Retrieval from ShapeNet Core55.
SHREC'17: RGB-D to CAD Retrieval with ObjectNN Dataset.
IBC127: Video Dataset for Fine-grained Bird Classification.
Recognizing Activities of Daily Living with a Wrist-mounted Camera.
Probabilistic Semi-Canonical Correlation Analysis.
3D Selective Search for Obtaining Object Candidates.
Learning Similarities for Rigid and Non-Rigid Object Detection.
Automatic Image Synthesis from Keywords Using Scene Context.
Clothing Retrieval Based on Local Similarity with Multiple Images.
Mirror Reflection Invariant HOG descriptors for Object Detection.
Hard Negative Classes for Multiple Object Detection.
Weakly-supervised Multi-class Object Detection Using Multi-type 3D Features.
Scale and Rotation Invariant Color Features for Weakly-Supervised Object Learning in 3D Space.
Voxelized Shape and Color Histograms for RGB-D.
Fast Object Detection for Robots in a Cluttered Indoor Environment Using Integral 3D Feature Table.
High-speed 3D Object Recognition Using Additive Features in A linear Subspace.
Partial Matching for Real Textured 3D Objects using Color Cubic Higher-order Local Auto-Correlation Features.
No matching publications or materials.