362 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Honda (United States)US9 papers
- University of California, BerkeleyUS4 papers
- Purdue University West LafayetteUS3 papers
- University of Maryland, College ParkUS3 papers
- Atlanta Technical CollegeUS1 paper
- Boston UniversityUS1 paper
- Carnegie Mellon UniversityUS1 paper
- Georgia Institute of TechnologyUS1 paper
- Honda (Japan)JP1 paper
- IBM Research - Thomas J. Watson Research CenterUS1 paper
- IBM (United States)US1 paper
- Indiana UniversityUS1 paper
6 papers · 1 filter
Temporal Recurrent Networks for Online Action Detection
Mingze Xu, Mingfei Gao, Yi-Ting Chen +2
Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed. How…
Deep Transfer Learning of Pick Points on Fabric for Robot Bed-Making
Daniel Seita, Nawid Jamali, Michael Laskey +6
A fundamental challenge in manipulating fabric for clothes folding and textiles manufacturing is computing "pick points" to effectively modify the state of an uncertain manifold. W…
Two Stream Self-Supervised Learning for Action Recognition
Ahmed Taha, Moustafa Meshry, Xitong Yang +2
We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and tempor…
Local Descriptors Optimized for Average Precision
Kun He, Yan Lu, Stan Sclaroff
Extraction of local feature descriptors is a vital stage in the solution pipelines for numerous computer vision tasks. Learning-based approaches improve performance in certain task…
Learning to Cluster for Proposal-Free Instance Segmentation
Yen-Chang Hsu, Zheng Xu, Zsolt Kira +1
This work proposed a novel learning objective to train a deep neural network to perform end-to-end image pixel clustering. We applied the approach to instance segmentation, which i…
Decomposition Methods with Deep Corrections for Reinforcement Learning
Maxime Bouton, Kyle Julian, Alireza Nakhaei +2
Decomposition methods have been proposed to approximate solutions to large sequential decision making problems. In contexts where an agent interacts with multiple entities, utility…