1.1k citations
- Amazon (United States)US32 papers
- Carnegie Mellon UniversityUS8 papers
- Massachusetts Institute of TechnologyUS8 papers
- Microsoft Research (United Kingdom)GB8 papers
- Google (United States)US7 papers
- Johns Hopkins UniversityUS7 papers
- Meta (Israel)IL6 papers
- University of Maryland, College ParkUS6 papers
- California Southern UniversityUS5 papers
- University of California, Los AngelesUS5 papers
- University of OxfordGB5 papers
- University of Southern CaliforniaUS5 papers
7 papers · 1 filter
Semantic Segmentation from Limited Training Data
A. Milan, T. Pham, K. Vijay +22
We present our approach for robotic perception in cluttered scenes that led to winning the recent Amazon Robotics Challenge (ARC) 2017. Next to small objects with shiny and transpa…
A Generic Approach for Escaping Saddle points
Sashank J Reddi, Manzil Zaheer, Suvrit Sra +4
A central challenge to using first-order methods for optimizing nonconvex problems is the presence of saddle points. First-order methods often get stuck at saddle points, greatly d…
Cartman: The low-cost Cartesian Manipulator that won the Amazon Robotics Challenge
D. Morrison, A. W. Tow, M. McTaggart +19
The Amazon Robotics Challenge enlisted sixteen teams to each design a pick-and-place robot for autonomous warehousing, addressing development in robotic vision and manipulation. Th…
Joint Learning of Set Cardinality and State Distribution
S. Hamid Rezatofighi, Anton Milan, Qinfeng Shi +2
We present a novel approach for learning to predict sets using deep learning. In recent years, deep neural networks have shown remarkable results in computer vision, natural langua…
Content-Based Weak Supervision for Ad-Hoc Re-Ranking
Sean MacAvaney, Andrew Yates, Kai Hui +1
One challenge with neural ranking is the need for a large amount of manually-labeled relevance judgments for training. In contrast with prior work, we examine the use of weak super…
A High-Performance Algorithm for Identifying Frequent Items in Data Streams
Daniel Anderson, Pryce Bevan, Kevin Lang +3
Estimating frequencies of items over data streams is a common building block in streaming data measurement and analysis. Misra and Gries introduced their seminal algorithm for the…