activity
20172022
most citedExploring Cross-Domain Pretrained Model for Hyperspectral Image Classification

28 citations · 31 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV202228 cited

Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification

Hyungtae Lee, Sungmin Eum, Heesung Kwon

A pretrain-finetune strategy is widely used to reduce the overfitting that can occur when data is insufficient for CNN training. First few layers of a CNN pretrained on a large-sca…

cs.CV2019

Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing

Sungmin Eum, Heesung Kwon

We present a novel deep zero-shot learning (ZSL) model for inferencing human-object-interaction with verb-object (VO) query. While the previous two-stream ZSL approaches only use t…

cs.CV2019

S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition

Hyungtae Lee, Sungmin Eum, Heesung Kwon

We present a novel event recognition approach called Spatially-preserved Doubly-injected Object Detection CNN (S-DOD-CNN), which incorporates the spatially preserved object detecti…

cs.CV2019

Is Pretraining Necessary for Hyperspectral Image Classification?

Hyungtae Lee, Sungmin Eum, Heesung Kwon

We address two questions for training a convolutional neural network (CNN) for hyperspectral image classification: i) is it possible to build a pre-trained network? and ii) is the…

cs.CV2018

DOD-CNN: Doubly-injecting Object Information for Event Recognition

Hyungtae Lee, Sungmin Eum, Heesung Kwon

Recognizing an event in an image can be enhanced by detecting relevant objects in two ways: 1) indirectly utilizing object detection information within the unified architecture or…

cs.CV2018

Object and Text-guided Semantics for CNN-based Activity Recognition

Sungmin Eum, Christopher Reale, Heesung Kwon +2

Many previous methods have demonstrated the importance of considering semantically relevant objects for carrying out video-based human activity recognition, yet none of the methods…