activity
20192022
most citedFeature and Label Embedding Spaces Matter in Addressing Image Classifier Bias

6 citations · 8 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2023

Query by Activity Video in the Wild

Tao Hu, William Thong, Pascal Mettes +1

This paper focuses on activity retrieval from a video query in an imbalanced scenario. In current query-by-activity-video literature, a common assumption is that all activities hav…

cs.CV2022

Content-Diverse Comparisons improve IQA

William Thong, Jose Costa Pereira, Sarah Parisot +2

Image quality assessment (IQA) forms a natural and often straightforward undertaking for humans, yet effective automation of the task remains highly challenging. Recent metrics fro…

cs.CV20216 cited

Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias

William Thong, Cees G. M. Snoek

This paper strives to address image classifier bias, with a focus on both feature and label embedding spaces. Previous works have shown that spurious correlations from protected at…

cs.CV2021

Object Priors for Classifying and Localizing Unseen Actions

Pascal Mettes, William Thong, Cees G. M. Snoek

This work strives for the classification and localization of human actions in videos, without the need for any labeled video training examples. Where existing work relies on transf…

cs.CV20201 cited

Bias-Awareness for Zero-Shot Learning the Seen and Unseen

William Thong, Cees G. M. Snoek

Generalized zero-shot learning recognizes inputs from both seen and unseen classes. Yet, existing methods tend to be biased towards the classes seen during training. In this paper,…

cs.CV2019

Open Cross-Domain Visual Search

William Thong, Pascal Mettes, Cees G. M. Snoek

This paper addresses cross-domain visual search, where visual queries retrieve category samples from a different domain. For example, we may want to sketch an airplane and retrieve…