activity
20182022
most citedLearning a Unified Sample Weighting Network for Object Detection

4 citations · 19 across the 10 of their papers we have counts for

collaborators

15 papers

cs.CV2022

A-ACT: Action Anticipation through Cycle Transformations

Akash Gupta, Jingen Liu, Liefeng Bo +2

While action anticipation has garnered a lot of research interest recently, most of the works focus on anticipating future action directly through observed visual cues only. In thi…

cs.CV20221 cited

Cross-modal Contrastive Distillation for Instructional Activity Anticipation

Zhengyuan Yang, Jingen Liu, Jing Huang +4

In this study, we aim to predict the plausible future action steps given an observation of the past and study the task of instructional activity anticipation. Unlike previous antic…

cs.CV20222 cited

Smart Director: An Event-Driven Directing System for Live Broadcasting

Yingwei Pan, Yue Chen, Qian Bao +4

Live video broadcasting normally requires a multitude of skills and expertise with domain knowledge to enable multi-camera productions. As the number of cameras keep increasing, di…

cs.CV2021

CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation

Xiao Wang, Jingen Liu, Tao Mei +1

Some cognitive research has discovered that humans accomplish event segmentation as a side effect of event anticipation. Inspired by this discovery, we propose a simple yet effecti…

cs.CV20212 cited

Memory-Augmented Non-Local Attention for Video Super-Resolution

Jiyang Yu, Jingen Liu, Liefeng Bo +1

In this paper, we propose a novel video super-resolution method that aims at generating high-fidelity high-resolution (HR) videos from low-resolution (LR) ones. Previous methods pr…

cs.CV20214 cited

Improving Contrastive Learning by Visualizing Feature Transformation

Rui Zhu, Bingchen Zhao, Jingen Liu +2

Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised…