activity
20162024
most citedOn Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization

119 citations · 167 across the 18 of their papers we have counts for

collaborators
Showing cs.CVShow all

13 papers · 1 filter

cs.CV2024

Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation

Ming Xu, Stephen Gould

We propose a novel approach to the action segmentation task for long, untrimmed videos, based on solving an optimal transport problem. By encoding a temporal consistency prior into…

cs.CV20241 cited

Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection

Qinyu Zhao, Ming Xu, Kartik Gupta +3

Feature shaping refers to a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection. These approaches manipulate the feature representat…

cs.CV20232 cited

Scaling Data Generation in Vision-and-Language Navigation

Zun Wang, Jialu Li, Yicong Hong +6

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for trainin…

cs.CV20231 cited

Exploring Predicate Visual Context in Detecting Human-Object Interactions

Frederic Z. Zhang, Yuhui Yuan, Dylan Campbell +2

Recently, the DETR framework has emerged as the dominant approach for human--object interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are amongst…

cs.CV20231 cited

Learning Navigational Visual Representations with Semantic Map Supervision

Yicong Hong, Yang Zhou, Ruiyi Zhang +4

Being able to perceive the semantics and the spatial structure of the environment is essential for visual navigation of a household robot. However, most existing works only employ…

cs.CV2023

Adaptive Cross Batch Normalization for Metric Learning

Thalaiyasingam Ajanthan, Matt Ma, Anton van den Hengel +1

Metric learning is a fundamental problem in computer vision whereby a model is trained to learn a semantically useful embedding space via ranking losses. Traditionally, the effecti…