Search Results for author: Eric Kim

Found 11 papers, 6 papers with code

CausalX: Causal Explanations and Block Multilinear Factor Analysis

no code implementations25 Feb 2021 M. Alex O. Vasilescu, Eric Kim, Xiao S. Zeng

When causal factors are not amenable for active manipulation in the real world due to current technological limitations or ethical considerations, a counterfactual approach performs an intervention on the model of data formation.

Object Recognition

Toward Transformer-Based Object Detection

no code implementations17 Dec 2020 Josh Beal, Eric Kim, Eric Tzeng, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk

The Vision Transformer was the first major attempt to apply a pure transformer model directly to images as input, demonstrating that as compared to convolutional networks, transformer-based architectures can achieve competitive results on benchmark classification tasks.

Natural Language Processing object-detection +1

Bootstrapping Complete The Look at Pinterest

1 code implementation18 Jun 2020 Eileen Li, Eric Kim, Andrew Zhai, Josh Beal, Kunlong Gu

In this paper, we will describe how we bootstrapped the Complete The Look (CTL) system at Pinterest.

Compositional Hierarchical Tensor Factorization: Representing Hierarchical Intrinsic and Extrinsic Causal Factors

no code implementations11 Nov 2019 M. Alex O. Vasilescu, Eric Kim

Visual objects are composed of a recursive hierarchy of perceptual wholes and parts, whose properties, such as shape, reflectance, and color, constitute a hierarchy of intrinsic causal factors of object appearance.

Face Recognition Object Recognition +1

Complete the Look: Scene-based Complementary Product Recommendation

1 code implementation CVPR 2019 Wang-Cheng Kang, Eric Kim, Jure Leskovec, Charles Rosenberg, Julian McAuley

We design an approach to extract training data for this task, and propose a novel way to learn the scene-product compatibility from fashion or interior design images.

Product Recommendation

Cannot find the paper you are looking for? You can Submit a new open access paper.