Publications
Journals, Conferences, and Workshops
Weiyao Wang, Pierre Gleize, Hao Tang, Xingyu Chen, Kevin J Liang, Matt Feiszli. ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization, Computer Vision and Pattern Recognition (CVPR) 2024. (website)
Kristen Grauman, …, Kevin J Liang, …, et. al. Ego-Exo4D: Understanding Skilled Human Activity from First-and Third-Person Perspectives, Computer Vision and Pattern Recognition (CVPR) 2024. (website, video)
Nikhli Mehta*, Kevin J Liang*, Jing Huang, Fu-Jen Chu, Li Yin, Tal Hassner. HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings, Winter Conference on Applications of Computer Vision (WACV) 2024.
Vinay Kumar Verma, Kevin J Liang, Nikhil Mehta, Aakansha Mishra, Lawrence Carin. Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning, Winter Conference on Applications of Computer Vision (WACV) 2024.
Hao Tang, Kevin J Liang, Kristen Grauman, Matt Feiszli*, Weiyao Wang*. EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset, Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS D&B) 2023.
Peri Akiva, Jing Huang, Kevin J Liang, Xingyu Chen, Rama Kovvuri, Matt Feiszli, Kristin Dana, Tal Hassner. Self-Supervised Object Detection from Egocentric Videos, International Conference on Computer Vision (ICCV) 2023.
Samrudhdhi B. Rangrej, Kevin J Liang, Tal Hassner, James J. Clark. GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction, Winter Conference on Applications of Computer Vision (WACV) 2023.
Jing Huang, Kevin J Liang, Rama Kovvuri, Tal Hassner. Task Grouping for Multilingual Text Recognition, European Conference on Computer Vision Workshop: Text in Everything (ECCVw - Best Paper) 2022.
Weituo Hao, Nikhil Mehta, Kevin J Liang, Pengyu Cheng, Mostafa El-Khamy, Lawrence Carin. WAFFLe: Weight Anonymized Factorization for Federated Learning, IEEE Access 2022.
Kevin J Liang, Samrudhdhi B. Rangrej, Vladan Petrovic, Tal Hassner. Few-shot Learning with Noisy Labels, Computer Vision and Pattern Recognition (CVPR) 2022.
Li Yin, Juan-Manuel Perez-Rua, Kevin J Liang. Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection, Computer Vision and Pattern Recognition (CVPR) 2022.
Nathan Inkawhich, Kevin J Liang, Jingyang Zhang, Huanrui Yang, Hai Li, and Yiran Chen. Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?, International Conference on Computer Vision Workshop: Adversarial Robustness in the Real World (ICCVw) 2021.
Weituo Hao, Mostafa El-Khamy, Jungwon Lee, Jianyi Zhang, Kevin J Liang, Changyou Chen, Lawrence Carin. Towards Fair Federated Learning with Zero-Shot Data Augmentation, Computer Vision and Pattern Recognition Workshop: Fair, Data Efficient and Trusted Computer Vision (CVPRw) 2021.
Vinay Kumar Verma, Kevin J Liang, Nikhil Mehta, Piyush Rai, Lawrence Carin. Efficient Feature Transformations for Discriminative and Generative Incremental Learning, Computer Vision and Pattern Recognition (CVPR) 2021.
Jing Huang, Guan Pang, Rama Kovvuri, Mandy Toh, Kevin J Liang, Praveen Krishnan, Xi Yin, Tal Hassner. A Multiplexed Network for End-to-End, Multilingual OCR, Computer Vision and Pattern Recognition (CVPR) 2021.
Nikhil Mehta, Kevin J Liang, Vinay Kumar Verma, Lawrence Carin. Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors, Artificial Intelligence and Statistics (AISTATS) 2021.
Kevin J Liang*, Weituo Hao*, Dinghan Shen, Yufan Zhou, Weizhu Chen, Changyou Chen, Lawrence Carin. MixKD: Towards Efficient Distillation of Large-scale Language Models, International Conference on Learning Representations (ICLR) 2021.
Nathan Inkawhich, Kevin J Liang, Binghui Wang, Matthew Inkawhich, Lawrence Carin, Yiran Chen. Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability, Neural Information Processing Systems (NeurIPS) 2020.
Yuewei Yang*, Kevin J Liang*, Lawrence Carin. Object Detection as a Positive-Unlabeled Problem, British Machine Vision Conference (BMVC) 2020.
Kevin J Liang, John Sigman, Gregory Spell, Dan Strellis, William Chang, Felix Liu, Tejas Mehta, Lawrence Carin. Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection, Denver X-ray Conference (DXC) 2020.
John Sigman, Gregory Spell, Kevin J Liang, Lawrence Carin. Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-ray Images, SPIE Anomaly Detection and Imaging with X-Rays (ADIX) V (SPIE ADIX) 2020.
Nathan Inkawhich, Kevin J Liang, Lawrence Carin, Yiran Chen. Transferable Perturbations of Deep Feature Distributions, International Conference on Learning Representations (ICLR) 2020.
Kevin J Liang*, Guoyin Wang*, Yitong Li, Ricardo Henao, Lawrence Carin. Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods, Neural Information Processing Systems (NeurIPS) 2019.
Kevin J Liang, Chunyuan Li, Guoyin Wang, Lawrence Carin. Generative Adversarial Networks and Continual Learning, Neural Information Processing Systems Workshop: Continual Learning (NeurIPSw) 2018.
Kevin J Liang, Geert Heilmann, Christopher Gregory, Souleymane O Diallo, David Carlson, Gregory P. Spell, John B. Sigman, Kris Roe, Lawrence Carin. Automatic Threat Recognition of Prohibited Items at Aviation Checkpoints with X-ray Imaging: a Deep Learning Approach, SPIE Anomaly Detection and Imaging with X-Rays (ADIX) III (SPIE ADIX) 2018.
Pre-prints
Samrudhdhi Bharatkumar Rangrej, Kevin J Liang, Xi Yin, Guan Pang, Theofanis Karaletsos, Lior Wolf, Tal Hassner. Revisiting Linear Decision Boundaries for Few-Shot Learning with Transformer Hypernetworks, 2022.
Sachin Konan, Kevin J Liang, Li Yin. Extending One-Stage Detection with Open-World Proposals, 2022.
Kevin J Liang, Chunyuan Li, Guoyin Wang, Lawrence Carin. Generative Adversarial Networks are a Continual Learning Problem, 2018.
Dissertation
- Kevin J Liang. Deep Automatic Threat Recognition: Considerations for Airport X-Ray Baggage Screening, 2020.