activity
20202022
most citedCycle-Contrast for Self-Supervised Video Representation Learning

32 citations · 49 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2022

Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs

Yoshiki Ito, Quan Kong, Kenichi Morita +1

Skeleton-based two-person interaction recognition has been gaining increasing attention as advancements are made in pose estimation and graph convolutional networks. Although the a…

cs.CV2021

Robust Unsupervised Multi-Object Tracking in Noisy Environments

C. -H. Huck Yang, Mohit Chhabra, Y. -C. Liu +3

Physical processes, camera movement, and unpredictable environmental conditions like the presence of dust can induce noise and artifacts in video feeds. We observe that popular uns…

cs.CV2021

Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection

Masato Tamura, Tomoaki Yoshinaga

We propose a segmentation-based bounding box generation method for omnidirectional pedestrian detection that enables detectors to tightly fit bounding boxes to pedestrians without…

cs.CV2021★ 17 cited

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

Masato Tamura, Hiroki Ohashi, Tomoaki Yoshinaga

We propose a simple, intuitive yet powerful method for human-object interaction (HOI) detection. HOIs are so diverse in spatial distribution in an image that existing CNN-based met…

cs.CV2020★ 32 cited

Cycle-Contrast for Self-Supervised Video Representation Learning

Quan Kong, Wenpeng Wei, Ziwei Deng +2

We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Following a nature that there is a belong and inclusion relation of v…