Junnan Li

is this you? claim profile

0 followers
National University of Singapore ∙ Salesforce

MoPro: Webly Supervised Learning with Momentum Prototypes

We propose a webly-supervised representation learning method that does n...
09/17/2020 ∙ by Junnan Li, et al. ∙ 8 ∙ share

read it
The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Most existing object instance detection and segmentation models only wor...
07/23/2020 ∙ by Tao Wang, et al. ∙ 0 ∙ share

read it
Prototypical Contrastive Learning of Unsupervised Representations

This paper presents Prototypical Contrastive Learning (PCL), an unsuperv...
05/11/2020 ∙ by Junnan Li, et al. ∙ 10 ∙ share

read it
Improving out-of-distribution generalization via multi-task self-supervised pretraining

Self-supervised feature representations have been shown to be useful for...
03/30/2020 ∙ by Isabela Albuquerque, et al. ∙ 0 ∙ share

read it
Towards Noise-resistant Object Detection with Noisy Annotations

Training deep object detectors requires significant amount of human-anno...
03/03/2020 ∙ by Junnan Li, et al. ∙ 2 ∙ share

read it
DivideMix: Learning with Noisy Labels as Semi-supervised Learning

Deep neural networks are known to be annotation-hungry. Numerous efforts...
02/18/2020 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it
Weakly-Supervised Multi-Person Action Recognition in 360^∘ Videos

The recent development of commodity 360^∘ cameras have enabled a single ...
02/09/2020 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it
GradMix: Multi-source Transfer across Domains and Tasks

The computer vision community is witnessing an unprecedented rate of new...
02/09/2020 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it
Classification Calibration for Long-tail Instance Segmentation

Remarkable progress has been made in object instance detection and segme...
10/29/2019 ∙ by Tao Wang, et al. ∙ 23 ∙ share

read it
Visual Social Relationship Recognition

Social relationships form the basis of social structure of humans. Devel...
12/13/2018 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it
Learning to Learn from Noisy Labeled Data

Despite the success of deep neural networks (DNNs) in image classificati...
12/13/2018 ∙ by Junnan Li, et al. ∙ 46 ∙ share

read it
Unsupervised Learning of View-invariant Action Representations

The recent success in human action recognition with deep learning method...
09/06/2018 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it
Interact as You Intend: Intention-Driven Human-Object Interaction Detection

The recent advances in instance-level detection tasks lay strong foundat...
08/29/2018 ∙ by Bingjie Xu, et al. ∙ 0 ∙ share

read it
Video Storytelling

Bridging vision and natural language is a longstanding goal in computer ...
07/25/2018 ∙ by Junnan Li, et al. ∙ 2 ∙ share

read it
Attention Transfer from Web Images for Video Recognition

Training deep learning based video classifiers for action recognition re...
08/03/2017 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it
Dual-Glance Model for Deciphering Social Relationships

Since the beginning of early civilizations, social relationships derived...
08/02/2017 ∙ by Junnan Li, et al. ∙ 0 ∙ share

read it

Junnan Li

Featured Co-authors

Jiashi Feng

Richard Socher

Caiming Xiong

Tao Wang

Pan Zhou

Yu Li

Steven C. H. Hoi

Mohan Kankanhalli

Qi Zhao

Yongkang Wong

Steven Hoi

MoPro: Webly Supervised Learning with Momentum Prototypes

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Prototypical Contrastive Learning of Unsupervised Representations

Improving out-of-distribution generalization via multi-task self-supervised pretraining

Towards Noise-resistant Object Detection with Noisy Annotations

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

Weakly-Supervised Multi-Person Action Recognition in 360^∘ Videos

GradMix: Multi-source Transfer across Domains and Tasks

Classification Calibration for Long-tail Instance Segmentation

Visual Social Relationship Recognition

Learning to Learn from Noisy Labeled Data

Unsupervised Learning of View-invariant Action Representations

Interact as You Intend: Intention-Driven Human-Object Interaction Detection

Video Storytelling

Attention Transfer from Web Images for Video Recognition

Dual-Glance Model for Deciphering Social Relationships