activity
20192021
most citedFew-Shot Action Localization without Knowing Boundaries

6 citations · 12 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV20214 cited

Spatial-Temporal Transformer for 3D Point Cloud Sequences

Yimin Wei, Hao Liu, Tingting Xie +2

Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recog…

cs.CV20216 cited

Few-Shot Action Localization without Knowing Boundaries

Ting-Ting Xie, Christos Tzelepis, Fan Fu +1

Learning to localize actions in long, cluttered, and untrimmed videos is a hard task, that in the literature has typically been addressed assuming the availability of large amounts…

cs.CV2021

Relationship-based Neural Baby Talk

Fan Fu, Tingting Xie, Ioannis Patras +1

Understanding interactions between objects in an image is an important element for generating captions. In this paper, we propose a relationship-based neural baby talk (R-NBT) mode…

cs.CV20201 cited

Temporal Action Localization with Variance-Aware Networks

Ting-Ting Xie, Christos Tzelepis, Ioannis Patras

This work addresses the problem of temporal action localization with Variance-Aware Networks (VAN), i.e., DNNs that use second-order statistics in the input and/or the output of re…

cs.CV20201 cited

Boundary Uncertainty in a Single-Stage Temporal Action Localization Network

Ting-Ting Xie, Christos Tzelepis, Ioannis Patras

In this paper, we address the problem of temporal action localization with a single stage neural network. In the proposed architecture we model the boundary predictions as uni-vari…

cs.CV2019

Exploring Feature Representation and Training strategies in Temporal Action Localization

Tingting Xie, Xiaoshan Yang, Tianzhu Zhang +2

Temporal action localization has recently attracted significant interest in the Computer Vision community. However, despite the great progress, it is hard to identify which aspects…