Publications and tech reports

2022

• An AI-Assisted Labeling Tool for Cataloging High-Resolution Images of Galaxies Gustavo Perez, Sean Linden, Timothy McQuaid, Matteo Messa, Daniela Calzetti, Subhransu Maji, NeurIPS 2022 AI for Science: Progress and Promises
• Quantifying Long-term Phenological Patterns of Aerial Insectivores Roosting in the Great Lakes Region using Weather Surveillance Radar, Yuting Deng, Maria Belotti, Wenlong Zhao, Zezhou Cheng, Gustavo Perez, Elske Tielens, Victoria Simons, Daniel Sheldon, Subhransu Maji, Jeffrey Kelly, Kyle Horton, Global Change Biology, 2022.
• Using Spatio-Temporal Information in Weather Radar Data to Detect and Track Communal Bird Roosts, Gustavo Perez, Wenlong Zhao, Zezhou Cheng, Maria Belotti, Yuting Deng, Victoria Simons, Elske Tielens, Jeffrey Kelly, Kyle Horton, Subhransu Maji, Daniel Sheldon, bioRxiv, 2022
• How Well Does CLIP Understand Texture?, Chenyun Wu and Subhransu Maji, CV in the Wild Workshop, European Conference on Computer Vision (ECCV), 2022 | project page
• MVDECOR: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation, Gopal Sharma, Kangxue Yin, Subhransu Maji, Evangelos Kalogerakis, Or Litany, and Sanja Fidler, European Conference on Computer Vision (ECCV), 2022 | project page
• Improving Few-Shot Part Segmentation using Coarse Supervision, Oindrilla Saha, Zezhou Cheng, Subhransu Maji, European Conference on Computer Vision (ECCV), 2022 | project page
• Cross-Modal 3D Shape Generation and Manipulation, Zezhou Cheng, Menglei Chai, Jian Ren, Hsin-Ying Lee, Kyle Olszewski, Zeng Huang, Subhransu Maji, and Sergey Tulyakov, European Conference on Computer Vision (ECCV), 2022 | project page
• Dynamic Transformer for Few-shot Instance Segmentation, Haochen Wang, Jie Liu, Yongtuo Liu, Subhransu Maji, Jan-jakob Sonke, Efstratios Gavves, ACM Multimedia, 2022
• PriFit: Learning to Fit Primitives Improves Few Shot Learning on Point Clouds, Gopal Sharma*, Bidya Dash*, Aruni RoyChowdhury, Matheus Gadelha, Marios Loizou, Liangliang Cao, Rui Wang, Erik Learned-Miller, Subhransu Maji, and Evangelos Kalogerakis, Eurographics Symposium on Geometry Processing (SGP), 2022 | project page
• Star Cluster Formation and Evolution in M101: An Investigation with the Legacy Extragalactic UV Survey, Sean Linden, Gustavo Perez, Daniela Calzetti, Subhransu Maji, Matteo Messa, et al., The Astrophysical Journal (ApJ), 2022 | project page
• Domain Adaptors for Hyperspectral Images, Gustavo Perez, Subhransu Maji, International Conference on Pattern Recognition (ICPR), 2022 | project page, bibtex
• GANorCON: Are Generative Models Useful for Few-shot Segmentation? Oindrila Saha, Zezhou Cheng, Subhransu Maji, Computer Vision and Pattern Recognition (CVPR), 2022 | project page, code
• On Measuring and Controlling the Spectral Bias of the Deep Image Prior, Zenglin Shi, Pascal Mettes, Subhransu Maji, Cees G. M. Snoek, International Journal on Computer Vision (IJCV), 2022 | webpage

2021

• Semi-Supervised Learning with Taxonomic Labels, Jong-Chyi Su, Subhransu Maji, British Machine Vision Conference (BMVC), 2021 | code
• On Equivariant and Invariant Learning of Object Landmark Representations, Zezhou Cheng, Jong-Chyi Su, Subhransu Maji, International Conference on Computer Vision (ICCV), 2021 | website
• AI for Conservation: Learning to Track Birds with Radar, Zezhou Cheng, Subhransu Maji, Daniel Sheldon, XRDS: Crossroads, The ACM Magazine for Students, 2021.
• Deep Manifold Prior, Matheus Gadelha, Rui Wang, Subhransu Maji, VIPriors Workshop (ICCV), 2021
• Shot in the Dark: Few-Shot Learning with No Base-Class Labels, Zityan Chen, Subhransu Maji, Erik Learned-Miller, Learning from Limited or Imperfect Data (L2ID) Workshop, CVPR, 2021
• A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification, Jong-Chyi Su, Zezhou Cheng, Subhransu Maji, Computer Vision and Pattern Recognition (CVPR), 2021
• Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning, Zhaowei Cai, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Zhowen Tu, Stefano Soatto, Computer Vision and Pattern Recognition (CVPR), 2021
• The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop, Jong-Chyi Su, Subhransu Maji, arXiv:2106.01364, June 3, 2021 | Kaggle, Github page @ FGVC8 workshop
• The Semi-Supervised iNaturalist-Aves Challenge at the FGVC7 Workshop, Jong-Chyi Su, Subhransu Maji, arXiv:2103.06937, March 11, 2021 | Kaggle, Github page @ FGVC7 workshop
• StarcNet: Machine Learning for Star Cluster Classification, Gustavo Perez, Matteo Messa, Daniela Calzetti, Subhransu Maji, Dooseok Jung, Angela Adamo, Mattia Sirressi, The Astrophysical Journal (ApJ), 2021 | arXiv, code, bibtex
  CICS Outstanding Synthesis Award

2020

• Neural Shape Parsers for Constructive Solid Geometry, Gopal Sharma, Rishabh Goyal, Difan Liu, Evangelos Kalogerakis, Subhransu Maji, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), December 2020 | journal page
• Inferring 3D Shapes from Image Collections Using Adversarial Networks, Matheus Gadelha, Aartika Rai, Subhransu Maji, Rui Wang, International Journal of Computer Vision, vol. 128, pp. 2651–2664, 2020
• Exploring and Predicting Transferability across NLP Tasks, Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer, EMLNP 2020
• Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions, Matheus Gadelha*, Aruni RoyChowdhury*, Gopal Sharma, Evangelos Kalogerakis, Liangliang Cao, Erik Learned-Miller, Rui Wang, Subhransu Maji, European Conference on Computer Vision (ECCV), 2020
• ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds, Gopal Sharma, Difan Liu, Subhransu Maji, Evangelos Kalogerakis, Siddhartha Chaudhuri, Radomír Měch, European Conference on Computer Vision (ECCV), 2020 | webpage
• When Does Self-Supervision Improve Few-Shot Learning?, Jong-Chyi Su, Subhransu Maji, Bharath Hariharan, European Conference on Computer Vision (ECCV), 2020 | webpage
• Describing Textures using Natural Language, Chenyun Wu, Mikayla Timm, Subhransu Maji, European Conference on Computer Vision (ECCV), 2020, oral presentation | webpage
• PhraseCut: Language-based Image Segmentation in the Wild, Chenyun Wu, Trung Bai, Scott Cohen, Zhe Lin, Subhransu Maji, Conference on Computer Vision and Pattern Recognition (CVPR), 2020
• Learning Generative Models of Shape Handles, Matheus Gadelha, Giorgio Gori, Duygu Ceylan, Radomir Mech, Nathan Carr, Tamy Boubekeur, Rui Wang, Subhransu Maji, Conference on Computer Vision and Pattern Recognition (CVPR), 2020
• Active Adversarial Domain Adaptation, Jong-Chyi Su, Yi-Hsuan Tsai, Kihyuk Sohn, Buyu Liu, Subhransu Maji, Manmohan Chandraker, Winter Conference on Applications of Computer Vision (WACV), 2020
• Detecting and Tracking Communal Bird Roosts in Weather Radar Data, Zezhou Cheng, Saadia Gabriel, Pankaj Bhambhani, Daniel Sheldon, Subhransu Maji, Andrew Laughlin, David Winkler, Association for the Advancement of Artificial Intelligence (AAAI), 2020 (Social Impact Track), oral presentation | supplementary, project page

2019

• Phenology of Nocturnal Avian Migration has Shifted at the Continental Scale, Kyle G. Horton, Frank A. La Sorte, Daniel Sheldon, Tsung-Yu Lin, Kevin Winner, Garrett Bernstein, Subhransu Maji, Wesley M. Hochachka, Andrew Farnsworth, Nature Climate Change, December 2019 | Press
• MistNet: Measuring historical bird migration in the US using archived weather radar data and convolutional neural networks, Tsung‐Yu Lin, Kevin Winner, Garrett Bernstein, Abhay Mittal, Adriaan M. Dokter, Kyle G. Horton, Cecilia Nilsson, Benjamin M. Van Doren, Andrew Farnsworth, Frank A. La Sorte, Subhransu Maji, Daniel Sheldon, Methods in Ecology and Evolution, August 2019 | Journal version, Press @ phys.org, cics, others
  2019 Robert May Early Career Research Prize Shortlist (The Shortlist)
• Task2Vec: Task Embedding for Meta-Learning, Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Stefano Soatto, Pietro Perona, International Conference on Computer Vision (ICCV), 2019 | bibtex, supplementary, code
• Shape Reconstruction using Differentiable Projections and Deep Priors, Matheus Gadelha, Rui Wang, Subhransu Maji, International Conference on Computer Vision (ICCV), 2019 | bibtex
• Learning Point Embeddings from Shape Repositories for Few-Shot Segmentation, Gopal Sharma, Evangelos Kalogerakis, Subhransu Maji, Proceedings of the International Conference on 3D Vision (3DV), 2019 | bibtex, supplementary
• DeepRoof: A Data-driven Approach For Solar Potential Estimation Using Rootop Imagery, Stephen Lee, Srinivasan Iyengar, Menghong Feng, Prashant Shenoy, Subhransu Maji, SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019, oral presentation
• High Dimensional Inference with Random Maximum A-Posteriori Perturbations, Tamir Hazan, Francesco Orabona, Anand D. Sarwate, Subhransu Maji, Tommi Jaakkola, IEEE Transactions on Information Theory, 2019 | bibtex, IEEE version
• A Bayesian Perspective on the Deep Image Prior, Zezhou Cheng, Matheus Gadelha, Subhransu Maji, Daniel Sheldon, Computer Vision and Pattern Recognition (CVPR), 2019 | webpage, supplementary, bibtex
• Meta-Learning with Differentiable Convex Optimization, Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, Stefano Soatto, Computer Vision and Pattern Recognition (CVPR), 2019, oral presentation | bibtex, code
• Migratory flight on the Pacific Flyway: strategies and tendencies of wind drift compensation, Patrick B. Newcombe, Cecilia Nilsson, Tsung-Yu Lin, Kevin Winner, Garrett Bernstein, Subhransu Maji, Daniel Sheldon, Andrew Farnsworth and Kyle G. Horton. Biology Letters, 2019.
• Visualizing and Describing Fine-grained Categories as Textures, Tsung-Yu Lin, Mikayla Timm, Chenyun Wu, Subhransu Maji, The Sixth Fine-Grained Visual Categorization Workshop (FGVC6) at CVPR 19 | project page, poster
• W!NCE: Unobtrusive Sensing of Upper Facial Action Units with EOG-based Eyewear, Soha Rostaminia, Alexander Lamson, Subhransu Maji, Tauhidur Rahman, Deepak Ganesan, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (UBICOMP), 2019
• Random Feature Maps for the Itemset Kernel, Kyohei Atarashi, Subhransu Maji, Satoshi Oyama, Association for the Advancement of Artificial Intelligence (AAAI), 2019 | bibtex

2018

• Multiresolution Tree Networks for 3D Point Cloud Processing, Matheus Gadelha, Rui Wang, Subhransu Maji, Proceedings of the European Conference on Computer Vision (ECCV), 2018 | webpage, bibtex, code
• Second-order Democratic Aggregation, Tsung-Yu Lin, Subhransu Maji, Piotr Koniusz, Proceedings of the European Conference on Computer Vision (ECCV), 2018 | webpage, bibtex, code
• A Deeper Look at 3D Shape Classifiers, Jong-Chyi Su, Matheus Gahelda, Rui Wang, Subhransu Maji, Second Workshop on 3D Reconstruction Meets Semantics, ECCV, 2018 | webpage, bibtex
• VisemeNet: Audio-Driven Animator-Centric Speech Animation, Yang Zhou, Zhan Xu, Chris Landreth, Evangelos Kalogerakis, Subhransu Maji, Karan Singh, ACM Transactions on Graphics (also to be presented at SIGGRAPH 2018) | webpage, bibtex
• CSGNet: Neural Shape Parser for Constructive Solid Geometry, Gopal Sharma, Rishabh Goyal, Difan Liu, Evangelos Kalogerakis, Subhransu Maji, Proceedings of the Computer Vision and Pattern Recognition (CVPR), 2018 | supplementary, webpage, bibtex
• SPLATNet: Sparse Lattice Networks for Point Cloud Processing, Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz, Proceedings of the Computer Vision and Pattern Recognition (CVPR), 2018, oral presentation | supplementary, video, webpage, bibtex. Press @ CVPR, NVIDIA, Medium
  Best paper honorable mention (1 of 4/979 papers)
• Large-Scale Ecological Analyses of Animals in the Wild using Computer Vision, Mikayla Timm, Subhransu Maji, Todd Fuller, Fine-Grained Visual Categorization Workshop (FGVC5) at CVPR 2018, extended abstract

2017

• Reasoning about Fine-grained Attribute Phrases using Reference Games, Jong-Chyi Su*, Chenyun Wu*, Huaizu Jiang, Subhransu Maji, International Conference on Computer Vision (ICCV), 2017 | webpage, bibtex
• 3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks, Zhaoliang Lun, Matheus Gadelha, Evangelos Kalogerakis, Subhransu Maji, Rui Wang, International Conference on 3D Vision (3DV), 2017, oral presentation | webpage, bibtex
• 3D Shape Induction from 2D Views of Multiple Objects, Matheus Gadelha, Subhransu Maji, Rui Wang, International Conference on 3D Vision (3DV), 2017 | webpage
• 3D Shape Generation using Spatially Ordered Point Clouds, Matheus Gadhela, Subhransu Maji, Rui Wang, British Machine Vision Conference (BMVC), 2017
• Improved Bilinear Pooling with CNNs, Tsung Yu Lin, Subhransu Maji, British Machine Vision Conference (BMVC), 2017, oral presentation | webpage, bibtex, talk slides
• Adapting Models to Signal Degradation using Distillation, Jong-Chyi Su, Subhransu Maji, British Machine Vision Conference (BMVC), 2017 | webpage, bibtex
• Bilinear CNNs for Fine-grained Visual Recognition, Tsung Yu Lin, Aruni RoyChowdhury, Subhransu Maji, IEEE Transactions of Pattern Recognition and Machine Intelligence (PAMI), 2017 | webpage, bibtex
• 3D Shape Segmentation with Projective Convolutional Networks, Evangelos Kalogerakis, Melinos Averkiou, Subhransu Maji, Siddharth Chaudhuri, Computer Vision and Pattern Recognition (CVPR), 2017, oral presentation | webpage, bibtex
• A Taxonomy of Part and Attribute Discovery Techniques, S. Maji, Visual Attributes, Springer, 2016, D. Parikh, R. Feris and C. Lampert, Eds. | published version, bibtex
• Texture Attribute Synthesis and Transfer using Feed-forward CNNs, Thomas Irmer, Tobias Glasmachers, Subhransu Maji
  IEEE Winter Conference on Applications of Computer Vision (WACV), 2017 | talk slides, poster

2016

• Deep Filter Banks for Texture Recognition, Description, and Segmentation, Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos, Andrea Vedaldi, International Journal of Computer Vision (IJCV), 2016 | journal page, webpage
• Visualizing and Understanding Deep Texture Representations, Tsung-Yu Lin, Subhransu Maji, Computer Vision and Pattern Recognition (CVPR), 2016 | pdf, arXiv, webpage
  + poster at the Workshop on Visualization for Deep Learning at ICML, 2016
• Jointly Learning Multiple Perceptual Similarities, Liwen Zhang, Subhransu Maji, Ryota Tomioka, Multi-View Representation Learning Workshop (MVRL) at ICML, 2016 | longer arXiv version
• One-to-many Face Recognition with Bilinear CNNs, Aruni RoyChowdhury, Tsung-Yu Lin, Subhransu Maji, and Erik Learned-Miller, IEEE Winter Conference on Applications of Computer Vision (WACV), 2016 | arXiv, talk slides
• Perturbation Models and PAC-Bayesian Generalization Bounds, Joseph Keshet, Subhransu Maji, Tamir Hazan, Tommi Jaakkola, Perturbations, Optimization, and Statistics, MIT Press, 2016, T. Hazan, G. Papandreou, D. Tarlow, Eds. | book chapter preprint, the entire book
• Distinguishing Weather Phenomena from Bird Migration Patterns in Radar Imagery, A. RoyChowdhury, D. Sheldon, S. Maji, and E. Learned-Miller, IEEE Worksop on Perception Beyond the Visual Spectrum (PBVS), 2016
• SHREC’16 Track: Large-Scale 3D Shape Retrieval from ShapeNet Core55, M. Savva, F. Yu, H. Su, M. Aono, B. Chen, D. Cohen-Or, W. Deng, H. Su, S. Bai, X. Bai, N. Fish, J. Han, E. Kalogerakis, E. G. Learned-Miller, Y. Li, M. Liao, S. Maji, A. Tatsuma, Y. Wang, N. Zhang, and Z. Zhou, In Eurographics Workshop on 3D Object Retrieval, J. Jorge and M. Lin, editors, 2016 | pdf, webpage (our submission was based on the MV-CNN approach, ICCV 2015)

2015

• Bilinear CNN Models for Fine-grained Visual Recognition, Tsung-Yu Lin, Aruni RoyChowdhury, Subhransu Maji, International Conference on Computer Vision (ICCV), 2015, oral presentation | talk slides, webpage, bibtex
  + ImageNet+COCO workshop at ICCV 2015 keynote talk (slides)
  + Longer version of the talk presented at Microsoft Research (slides)
• Multi-view Convolutional Neural Networks for 3D Shape Recognition, Hang Su, Subhransu Maji, Evangelos Kalogerakis, Erik Learned-Miller, International Conference on Computer Vision (ICCV), 2015 | webpage, bibtex, arXiv, competetion report
  Winner of the SHREC 2016 Large-Scale 3D Shape Retrieval Competition (normal dataset)
• Deep Filter Banks for Texture Recognition and Segmentation, Mircea Cimpoi, Subhransu Maji, and Andrea Vedaldi, Computer Vision and Pattern Recognition (CVPR), 2015, oral presentation | code, abstract, talk video
  Best poster runner-up at Scene Understanding Workshop (SUNw), CVPR 2015
  
• Automatic Image Annotation using Deep Learning Representations, Venkatesh N. Murthy, Subhransu Maji, and R. Manmatha, International Conference on Multimedia Retrieval (ICMR), 2015
• Learning Localized Perceptual Similarity Metrics for Interactive Categorization, Catherine Wah, Subhransu Maji, and Serge Belongie, Winter Conference in Computer Vision (WACV), 2015,
  Best paper award
  

2014

• Part and Attribute Discovery from Relative Annotations, Subhransu Maji, Gregory Shakhnarovich, International Journal of Computer Vision (IJCV), 2014 | journal page
• Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection, Ejaz Ahmed, Gregory Shakhnarovich, and Subhransu Maji, European Conference on Computer Vision (ECCV), 2014, oral presentation | talk slides, poster
• Parsing World's Skylines using Shape Constrained MRFs, Rashmi Tonge, Subhransu Maji, and C.V. Jawahar, Computer Vision and Pattern Recognition (CVPR), 2014 | webpage
• Similarity Comparisons for Interactive Fine-Grained Categorization, Catherine Wah, Grant Van Horn, Steven Branson, Subhransu Maji, Pietro Perona, Serge Belongie, Computer Vision and Pattern Recognition (CVPR), 2014 | spotlight, poster
• Understanding Objects in Detail with Fine-grained Attributes, A. Vedaldi, S. Mahendran, S. Tsogkas, S. Maji, B. Girshick, J. Kannala, E. Rahtu, I. Kokkinos, M. B. Blaschko, D. Weiss, B. Taskar, K. Simonyan, N. Saphra, and S. Mohamed, Computer Vision and Pattern Recognition (CVPR), 2014 | webpage
• Describing Textures in the Wild, Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos, Sammy Mohamed, and Andrea Vedaldi, Computer Vision and Pattern Recognition (CVPR), 2014 | webpage
• Active Boundary Annotation using Random MAP Perturbations, Subhransu Maji, Tamir Hazan, Tommi Jaakkola, Artificial Intelligence and Statistics (AISTATS), 2014 | poster

2013

• Efficient Classification for Additive Kernel SVMs, Subhransu Maji, Alexander C. Berg, Jitendra Malik, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2013
• Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions, Tamir Hazan, Subhransu Maji, Jossi Keshet, Tommi Jaakkola, Neural Information Processing Systems (NIPS), 2013 | poster
• On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations, Tamir Hazan, Subhransu Maji, Tommi Jaakkola, Neural Information Processing Systems (NIPS), 2013 | poster
• Part Discovery from Partial Correspondence, Subhransu Maji and Gregory Shakhnarovich, Computer Vision and Pattern Recognition (CVPR), 2013 | poster

2012

• Discovering a Lexicon of Parts and Attributes, Subhransu Maji, Second International Workshop on Parts and Attributes, ECCV, 2012 | talk slides, fgvc workshop poster
  Best poster runner-up at Fine Grained Visual Categorization workshop (FGVC), 2013
• Linearized Smooth Additive Classifiers, S. Maji, Workshop on Web-scale Vision and Social Media, ECCV, 2012 | code, talk slides
• Part Annotations via Pairwise Correspondence S. Maji and G. Shakhnarovich, 4th Workshop on Human Computation, AAAI, 2012, oral presentation | talk slides

2011

• Describing People: A Poselet-Based Approach to Attribute Classification, Lubomir Bourdev, Subhransu Maji, and Jitendra Malik, International Conference on Computer Vision (ICCV), 2011, oral presentation | attribute annotations, talk slides
• Semantic Contours from Inverse Detectors, Bharath Hariharan, Pablo Arbelaez, Lubomir Bourdev, Subhransu Maji, and Jitendar Malik, International Conference on Computer Vision (ICCV), 2011 | semantic contour dataset
• Action Recognition from a Distributed Representation of Pose and Appearance, Subhransu Maji, Lubomir Bourdev, and Jitendra Malik, Computer Vision and Pattern Recognition (CVPR), 2011 | poster, pose estimation, action classification
• Biased Normalized Cuts, Subhransu Maji, Nisheeth Vishnoi, and Jitendra Malik, Computer Vision and Pattern Recognition (CVPR), 2011 | webpage, poster
• Object Segmentation by Alignment of Poselet Activations to Image Contours, Thomas Brox, Lubomir Bourdev, Subhransu Maji, and Jitendar Malik, Computer Vision and Pattern Recognition (CVPR), 2011 | poster

2010 and earlier

• Detecting People Using Mutually Consistent Poselet Activations, Lubomir Bourdev, Subhransu Maji, Thomas Brox, and Jitendra Malik, European Conference on Computer Vision (ECCV), 2010 | webpage, poster
• Max-Margin Additive Classifiers for Detection, Subhransu Maji, Alexander C. Berg, International Conference on Computer Vision (ICCV), 2009, oral presentation | talk slides, website, code
• Multiple-View Object Recognition in Band-Limited Distributed Camera Networks, A.Y. Yang, S. Maji, M.C. Christoudias, T. Darrell, J. Malik, and S.S. Sastry, International Conference on Distributed Smart Cameras (ICDSC), 2009, oral presentation | talk slides
• Distributed Compression and Fusion of Non-negative Sparse Signals for Multiple-view Object Recognition, A.Y. Yang, S. Maji, K. Hong, P. Yan, and S.S. Sastry, International Conference on Information Fusion (ICIF), 2009
  Best paper award
• Object Detection Using a Max-Margin Hough Transform, Subhransu Maji, and Jitendra Malik, Computer Vision and Pattern Recognition (CVPR), 2009, oral presentation | talk slides
• Classification using Intersection Kernel Support Vector Machines is Efficient, Subhransu Maji, Alexander C. Berg, Jitendra Malik, Computer Vision and Pattern Recognition (CVPR), 2009 | webpage
• Fast Unsupervised Alignment of Video and Text for Indexing/Names and Faces, Subhransu Maji, Ruzena Bajscy, Multimedia Semantics Workshop, ACM Multimedia, 2007
• Confidence Based updation of Motion Conspicuity in Dynamic Scenes, V.K. Singh, S. Maji, A. Mukerjee, Conference on Computer and Robot Vision (CRV), 2006

Older preprints and techreports

• Fine-Grained Visual Classification of Aircraft, S. Maji, E. Rahtu, J. Kannala, M. Blaschko and A. Vedaldi, arXiv:1306.5151, June 2013 | FGVC workshop poster, webpage + This dataset was part of FGCOMP 2013
• Large Scale Image Annotations on Amazon Mechanical Turk, Subhransu Maji, UC Berkeley, Tech. Rep. UCB/EECS-2011-79, 2011 | webpage
• Fast and Accurate Digit Classification, Subhransu Maji and Jitendra Malik, UC Berkeley, Tech. Rep. UCB/EECS-2009-159, 2009 | webpage

Thesis

• Algorithms and Representations for Visual Recognition, Subhransu Maji, Ph.D. Thesis, Computer Science Division, University of California at Berkeley, Dec. 2011 | webpage
• Graph Classification: Applications in ChemoInformatics, Subhransu Maji, Undergraduate Thesis, Computer Science and Engineering Department, IIT Kanpur, May 2006 | pdf