Kevin J. Liang

Orcid: 0000-0002-0221-9108

According to our database1, Kevin J. Liang authored at least 28 papers between 2018 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization.
CoRR, 2024

2023
HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings.
CoRR, 2023

Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning.
CoRR, 2023

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives.
CoRR, 2023

GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Self-Supervised Object Detection from Egocentric Videos.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
Extending One-Stage Detection with Open-World Proposals.
CoRR, 2022

WAFFLe: Weight Anonymized Factorization for Federated Learning.
IEEE Access, 2022

Task Grouping for Multilingual Text Recognition.
Proceedings of the Computer Vision - ECCV 2022 Workshops, 2022

Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Few-shot Learning with Noisy Labels.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning.
CoRR, 2021

MixKD: Towards Efficient Distillation of Large-scale Language Models.
Proceedings of the 9th International Conference on Learning Representations, 2021

Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021

Efficient Feature Transformations for Discriminative and Generative Continual Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Towards Fair Federated Learning With Zero-Shot Data Augmentation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

A Multiplexed Network for End-to-End, Multilingual OCR.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Deep Automatic Threat Recognition: Considerations for Airport X-Ray Baggage Screening.
PhD thesis, 2020

Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images.
CoRR, 2020

Bayesian Nonparametric Weight Factorization for Continual Learning.
CoRR, 2020

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Transferable Perturbations of Deep Feature Distributions.
Proceedings of the 8th International Conference on Learning Representations, 2020

Object Detection as a Positive-Unlabeled Problem.
Proceedings of the 31st British Machine Vision Conference 2020, 2020

2019
Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection.
CoRR, 2019

Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018
Generative Adversarial Network Training is a Continual Learning Problem.
CoRR, 2018


  Loading...