output
20092022
most citedDeep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway

1.1k citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2018Show all

6 papers · 1 filter

cs.CC2018

Probabilistic Parameterized Polynomial Time

Nils Donselaar

We examine a parameterized complexity class for randomized computation where only the error bound and not the full runtime is allowed to depend more than polynomially on the parame…

cs.CL2018

Discourse Embellishment Using a Deep Encoder-Decoder Network

Leonid Berov, Kai Standvoss

We suggest a new NLG task in the context of the discourse generation pipeline of computational storytelling systems. This task, textual embellishment, is defined by taking a text a…

stat.ML2018

Forward Amortized Inference for Likelihood-Free Variational Marginalization

Luca Ambrogioni, Umut Güçlü, Julia Berezutskaya +5

In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortize…

cond-mat.stat-mech2018★ 7 cited

Atom-by-atom construction of attractors in a tunable finite size spin array

Alex Kolmus, Mikhail I. Katsnelson, Alexander A. Khajetoorians +1

We demonstrate that a two-dimensional finite and periodic array of Ising spins coupled via RKKY-like exchange can exhibit tunable magnetic states ranging from three distinct magnet…

cs.CV2018★ 26 cited

First Impressions: A Survey on Vision-Based Apparent Personality Trait Analysis

Julio C. S. Jacques Junior, Yağmur Güçlütürk, Marc Pérez +8

Personality analysis has been widely studied in psychology, neuropsychology, and signal processing fields, among others. From the past few years, it also became an attractive resea…

cs.CV2018★ 34 cited

Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos

Hugo Jair Escalante, Heysem Kaya, Albert Ali Salah +14

Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analy…