Alexander W. Stone

113V Davis Hall

Buffalo, New York, 14260

I am a PhD candidate in Computer Science and Engineering at the University at Buffalo, and a Presidential Fellow. I am advised by Ranga Setlur and Venu Govindaraju. I work as a graduate research assistant in the Center for Unified Biometrics and Sensors.

My research is in machine learning and computer vision. With collaborators at CUBS I coauthored ProxyFusion, presented at NeurIPS 2024, which aggregates a set of face features for recognition in unconstrained, long-range imagery. I also work on vision-language models for generating reliable educational material for children, as part of the AI4ExceptionalEd Institute. Earlier at CUBS I worked on detecting and summarizing handwritten content in whiteboard lecture videos. Between those projects I studied neural-network methods for numerical homogenization of multiscale partial differential equations with Matthew Knepley, and presented that work at the SIAM Conference on Computational Science and Engineering in 2023.

I received a BS in Computer Science from the University at Buffalo in 2019.

news

Dec 10, 2024	ProxyFusion was presented at NeurIPS 2024.

selected publications

NeurIPS
ProxyFusion: Face Feature Aggregation Through Sparse Experts

Bhavin Jawade, Alexander Stone, Deen Dayal Mohan, and 3 more authors

In Advances in Neural Information Processing Systems, 2024

Abs Bib HTML PDF Code Website

Face feature fusion is needed for robust recognition when not every frame of a long-range, low-resolution video is equally informative. ProxyFusion selects a sparse set of pooling experts with learnable proxies and aggregates a variable-size set of face features in linear time. The method is order-invariant, does not need intermediate feature maps or extra face metadata, and can run on legacy biometric templates. Evaluations on IARPA BTS3.1 and DroneSURF show gains for unconstrained long-range face recognition.
@inproceedings{jawade2024proxyfusion, title = {ProxyFusion: Face Feature Aggregation Through Sparse Experts}, author = {Jawade, Bhavin and Stone, Alexander and Mohan, Deen Dayal and Wang, Xiao and Setlur, Srirangaraj and Govindaraju, Venu}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, }
IJDAR
Generalized Framework for Summarization of Fixed-Camera Lecture Videos by Detecting and Binarizing Handwritten Content

Bhargava Urala Kota, Kenny Davila, Alexander Stone, and 2 more authors

International Journal on Document Analysis and Recognition (IJDAR), 2019

Abs Bib PDF

A framework for extracting and binarizing handwritten content in fixed-camera lecture videos, so the content can be used to index and navigate the video. A deep learning pipeline detects handwritten text, formulae, and sketches, and the spatio-temporal structure of those detections is used to segment the lecture. On the AccessMath dataset the framework reaches an F-measure of 94.32 percent for binary connected components.
@article{urala2019generalized, title = {Generalized Framework for Summarization of Fixed-Camera Lecture Videos by Detecting and Binarizing Handwritten Content}, author = {Urala Kota, Bhargava and Davila, Kenny and Stone, Alexander and Setlur, Srirangaraj and Govindaraju, Venu}, journal = {International Journal on Document Analysis and Recognition (IJDAR)}, volume = {22}, number = {3}, pages = {221--233}, year = {2019}, publisher = {Springer}, doi = {10.1007/s10032-019-00327-y}, }
ICDARW
Summarizing Lecture Videos by Key Handwritten Content Regions

Bhargava Urala Kota, Saleem Ahmed, Alexander Stone, and 3 more authors

In 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), 2019

Best paper award

Abs Bib PDF

Whiteboard lecture videos are summarized by key handwritten content regions. A detector finds semantically meaningful groups of handwriting, and a triplet-loss embedding distinguishes unique content across frames. A spatiotemporal index maps each summary region back to where it appears in the video. On AccessMath the method recalls 92.09 percent of unique ground-truth objects.
@inproceedings{kota2019summarizing, title = {Summarizing Lecture Videos by Key Handwritten Content Regions}, author = {Kota, Bhargava Urala and Ahmed, Saleem and Stone, Alexander and Davila, Kenny and Setlur, Srirangaraj and Govindaraju, Venu}, booktitle = {2019 International Conference on Document Analysis and Recognition Workshops (ICDARW)}, volume = {4}, pages = {13--18}, year = {2019}, organization = {IEEE}, doi = {10.1109/ICDARW.2019.30058}, note = {Best paper award} }