activity
20192022
most citedAdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries

12 citations · 21 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CV20228 cited

HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

Xiao Wang, Zongzhen Wu, Bo Jiang +5

The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large…

cs.CV20221 cited

On the Importance of Asymmetry for Siamese Representation Learning

Xiao Wang, Haoqi Fan, Yuandong Tian +2

Many recent self-supervised frameworks for visual representation learning are based on certain forms of Siamese networks. Such networks are conceptually symmetric with two parallel…

cs.CV2022

CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-adversarial Contrastive Learning

Xiao Wang, Yuhang Huang, Dan Zeng +1

As a representative self-supervised method, contrastive learning has achieved great successes in unsupervised training of representations. It trains an encoder by distinguishing po…

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.LG202012 cited

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries

Qianjiang Hu, Xiao Wang, Wei Hu +1

Contrastive learning relies on constructing a collection of negative examples that are sufficiently hard to discriminate against positive queries when their representations are sel…

cs.CV2019

EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations

Xiao Wang, Daisuke Kihara, Jiebo Luo +1

Deep neural networks have been successfully applied to many real-world applications. However, such successes rely heavily on large amounts of labeled data that is expensive to obta…