Maxwell D. Collins

Computer Science · Physical Sciences

20h-index2.6kcitations47works0.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(22), Advanced Image and Video Retrieval Techniques(18), Domain Adaptation and Few-Shot Learning(14), Video Surveillance and Tracking Methods(7), Multimodal Machine Learning Applications(6)

Publications47 total

FAR: Function-preserving Attention Replacement for IMC-friendly Inference
arXiv (Cornell University)·2025Open Access
Learning to Generate Image Embeddings with User-Level Differential Privacy
2023· 16 cited
Learning to Generate Image Embeddings with User-level Differential Privacy
arXiv (Cornell University)·2022Open Access
kMaX-DeepLab: k-means Mask Transformer
arXiv (Cornell University)·2022Open Access
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
arXiv (Cornell University)·2022· 3 citedOpen Access
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 76 cited
k-means Mask Transformer
Lecture notes in computer science·2022· 89 cited
DeepLab2: A TensorFlow Library for Deep Labeling
arXiv (Cornell University)·2021· 34 citedOpen Access
STEP: Segmenting and Tracking Every Pixel
arXiv (Cornell University)·2021· 9 citedOpen Access
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2020· 615 cited
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
arXiv (Cornell University)·2020· 12 citedOpen Access
Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation.
arXiv (Cornell University)·2020· 12 citedOpen Access
Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
arXiv (Cornell University)·2020· 16 citedOpen Access
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
Lecture notes in computer science·2020· 152 cited
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
arXiv (Cornell University)·2019· 42 citedOpen Access
SegSort: Segmentation by Discriminative Sorting of Segments
arXiv (Cornell University)·2019· 10 citedOpen Access
Panoptic-DeepLab
arXiv (Cornell University)·2019· 2 citedOpen Access
Panoptic-DeepLab
arXiv (Cornell University)·2019Open Access
SegSort: Segmentation by Discriminative Sorting of Segments
2019· 123 cited
No Means No and More Elementary Grammar: Moving Towards a More Codified Approach to Sexual Harassment Law
ScholarsArchive (Brigham Young University)·2019Open Access
page 1 of 3Next →

Frequent Co-authors

Liang-Chieh Chen(19), Hartwig Adam(15), Yukun Zhu(13), Vikas Singh(12), Bowen Cheng(8), Barret Zoph(6), Jonathon Shlens(6), Florian Schroff(5), Qihang Yu(5), Huiyu Wang(5), Siyuan Qiao(5), Alan Yuille(5), Ting Liu(4), Thomas S. Huang(4), Raphael Gontijo Lopes(4), Ekin D. Cubuk(4), Sathya N. Ravi(4), George Papandreou(3), Tien-Ju Yang(3), Jyh-Jing Hwang(3)