3.6k citations
- Japan Science and Technology AgencyJP16 papers
- RIKENJP15 papers
- The University of TokyoJP15 papers
- VTT Technical Research Centre of FinlandFI6 papers
- Tohoku UniversityJP5 papers
- Massachusetts Institute of TechnologyUS4 papers
- MIT Lincoln LaboratoryUS4 papers
- National Institute of Advanced Industrial Science and TechnologyJP4 papers
- NEC (United States)US4 papers
- RIKEN Advanced Science InstituteJP4 papers
- RIKEN Center for Emergent Matter ScienceJP4 papers
- University of California, Santa BarbaraUS4 papers
5 papers · 1 filter
Universal Adversarial Spoofing Attacks against Face Recognition
Takuma Amada, Seng Pei Liew, Kazuya Kakizaki +1
We assess the vulnerabilities of deep face recognition systems for images that falsify/spoof multiple identities simultaneously. We demonstrate that, by manipulating the deep featu…
Theoretical study of reflection spectroscopy for superconducting quantum parametrons
S. Masuda, A. Yamaguchi, T. Yamaji +4
Superconducting parametrons in the single-photon Kerr regime, also called KPOs, have been attracting increasing attention in terms of their applications to quantum annealing and un…
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
Mathias Niepert, Pasquale Minervini, Luca Franceschi
Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propo…
Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
Honglu Zhou, Asim Kadav, Farley Lai +4
This paper considers the problem of spatiotemporal object-centric reasoning in videos. Central to our approach is the notion of object permanence, i.e., the ability to reason about…
A Multi-Scale Conditional Deep Model for Tumor Cell Ratio Counting
Eric Cosatto, Kyle Gerard, Hans-Peter Graf +5
We propose a method to accurately obtain the ratio of tumor cells over an entire histological slide. We use deep fully convolutional neural network models trained to detect and cla…