| 2026 | WACV | Timestamp Query Transformer for Temporal Action Segmentation. | Tieqiao Wang, Sinisa Todorovic |
| 2025 | CVPR | A Dataset for Semantic and Instance Segmentation of Modern Fruit Orchards. | Tieqiao Wang, Abhinav Jain, Liqiang He, Cindy Grimm, Sinisa Todorovic |
| 2025 | ICCV | Difformer for Action Segmentation. | Nicolas Aziere, Tieqiao Wang, Sinisa Todorovic |
| 2025 | ICCV | End-to-End Action Segmentation Transformer. | Tieqiao Wang, Sinisa Todorovic |
| 2024 | ECCV | Attention Decomposition for Cross-Domain Semantic Segmentation. | Liqiang He, Sinisa Todorovic |
| 2023 | ICCV | Markov Game Video Augmentation for Action Segmentation. | Nicolas Aziere, Sinisa Todorovic |
| 2023 | ICCV | Bidirectional Alignment for Domain Adaptive Detection with Transformers. | Liqiang He, Wei Wang, Albert Chen, Min Sun, Cheng-Hao Kuo, Sinisa Todorovic |
| 2022 | CVPR | DESTR: Object Detection with Split Transformer. | Liqiang He, Sinisa Todorovic |
| 2022 | CVPR | iFS-RCNN: An Incremental Few-shot Instance Segmenter. | Khoi Nguyen, Sinisa Todorovic |
| 2021 | CVPR | Anchor-Constrained Viterbi for Set-Supervised Action Segmentation. | Jun Li, Sinisa Todorovic |
| 2021 | CVPR | Action Shuffle Alternating Learning for Unsupervised Action Segmentation. | Jun Li, Sinisa Todorovic |
| 2021 | CVPR | FAPIS: A Few-Shot Anchor-Free Part-Based Instance Segmenter. | Khoi Nguyen, Sinisa Todorovic |
| 2021 | ICCV | A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation. | Khoi Nguyen, Sinisa Todorovic |
| 2020 | CVPR | Set-Constrained Viterbi for Set-Supervised Action Segmentation. | Jun Li, Sinisa Todorovic |
| 2020 | ICLR | Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform. | Jun Li, Fuxin Li, Sinisa Todorovic |
| 2020 | ICPR | A Self-supervised GAN for Unsupervised Few-shot Object Recognition. | Khoi Nguyen, Sinisa Todorovic |
| 2019 | CVPR | Explainable AI as Collaborative Task Solving. | Arjun R. Akula, Changsong Liu, Sinisa Todorovic, Joyce Y. Chai, Song-Chun Zhu |
| 2019 | CVPR | Natural Language Interaction with Explainable AI Models. | Arjun R. Akula, Sinisa Todorovic, Joyce Y. Chai, Song-Chun Zhu |
| 2019 | CVPR | Ensemble Deep Manifold Similarity Learning Using Hard Proxies. | Nicolas Aziere, Sinisa Todorovic |
| 2019 | ICCV | Weakly Supervised Energy-Based Learning for Action Segmentation. | Jun Li, Peng Lei, Sinisa Todorovic |
| 2019 | ICCV | Feature Weighting and Boosting for Few-Shot Segmentation. | Khoi Nguyen, Sinisa Todorovic |
| 2018 | CVPR | Boundary Flow: A Siamese Network That Predicts Boundary Motion Without Training on Motion. | Peng Lei, Fuxin Li, Sinisa Todorovic |
| 2018 | CVPR | Temporal Deformable Residual Networks for Action Segmentation in Videos. | Peng Lei, Sinisa Todorovic |
| 2018 | ICPR | Learning to Learn Second-Order Back-Propagation for CNNs Using LSTMs. | Anirban Roy, Sinisa Todorovic |
| 2017 | CVPR | Fine-Grained Recognition as HSnet Search for Informative Image Parts. | Michael Lam, Behrooz Mahasseni, Sinisa Todorovic |
| 2017 | CVPR | Unsupervised Video Summarization with Adversarial LSTM Networks. | Behrooz Mahasseni, Michael Lam, Sinisa Todorovic |
| 2017 | CVPR | Budget-Aware Deep Semantic Video Segmentation. | Behrooz Mahasseni, Sinisa Todorovic, Alan Fern |
| 2017 | CVPR | Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation. | Anirban Roy, Sinisa Todorovic |
| 2017 | CVPR | CERN: Confidence-Energy Recurrent Network for Group Activity Recognition. | Tianmin Shu, Sinisa Todorovic, Song-Chun Zhu |
| 2016 | CVPR | Regularizing Long Short Term Memory with 3D Human-Skeleton Sequences for Action Recognition. | Behrooz Mahasseni, Sinisa Todorovic |
| 2016 | CVPR | Monocular Depth Estimation Using Neural Regression Forest. | Anirban Roy, Sinisa Todorovic |
| 2016 | ECCV | Recurrent Temporal Deep Field for Semantic Video Labeling. | Peng Lei, Sinisa Todorovic |
| 2016 | ECCV | A Multi-scale CNN for Affordance Segmentation in RGB Images. | Anirban Roy, Sinisa Todorovic |
| 2016 | ICPR | Modeling human-skeleton motion patterns using conditional deep Boltzmann machine. | Peng Lei, Sinisa Todorovic |
| 2016 | ICPR | Context-regularized learning of fully convolutional networks for scene labeling. | Anirban Roy, Sinisa Todorovic, Longin Jan Latecki |
| 2016 | ICPR | Beam search for learning a deep Convolutional Neural Network of 3D shapes. | Xu Xu, Sinisa Todorovic |
| 2015 | CVPR | Person count localization in videos from noisy foreground and detections. | Sheng Chen, Alan Fern, Sinisa Todorovic |
| 2015 | CVPR | Latent trees for estimating intensity of Facial Action Units. | Sebastian Kaltwang, Sinisa Todorovic, Maja Pantic |
| 2015 | CVPR | ℋC-search for structured prediction in computer vision. | Michael Lam, Janardhan Rao Doppa, Sinisa Todorovic, Thomas G. Dietterich |
| 2015 | CVPR | Joint inference of groups, events and human roles in aerial videos. | Tianmin Shu, Dan Xie, Brandon Rothrock, Sinisa Todorovic, Song-Chun Zhu |
| 2015 | ICCV | Semantic Segmentation of RGBD Images with Mutex Constraints. | Zhuo Deng, Sinisa Todorovic, Longin Jan Latecki |
| 2014 | CVPR | Multi-object Tracking via Constrained Sequential Labeling. | Sheng Chen, Alan Fern, Sinisa Todorovic |
| 2014 | CVPR | Scene Labeling Using Beam Search under Mutex Constraints. | Anirban Roy, Sinisa Todorovic |
| 2014 | ECCV | HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos. | Mohamed Rabie Amer, Peng Lei, Sinisa Todorovic |
| 2014 | WACV | Play type recognition in real-world football video. | Sheng Chen, Zhongyuan Feng, Qingkai Lu, Behrooz Mahasseni, Trevor Fiez, Alan Fern, Sinisa Todorovic |
| 2013 | IAAI | Detecting the Moment of Snap in Real-World Football Videos. | Behrooz Mahasseni, Sheng Chen, Alan Fern, Sinisa Todorovic |
| 2013 | ICCV | Monte Carlo Tree Search for Scheduling Activity Recognition. | Mohamed R. Amer, Sinisa Todorovic, Alan Fern, Song-Chun Zhu |
| 2013 | ICCV | Latent Multitask Learning for View-Invariant Action Recognition. | Behrooz Mahasseni, Sinisa Todorovic |
| 2013 | ICCV | Inferring "Dark Matter" and "Dark Energy" from Videos. | Dan Xie, Sinisa Todorovic, Song-Chun Zhu |
| 2012 | CVPR | Sum-product networks for modeling activities with stochastic structure. | Mohamed R. Amer, Sinisa Todorovic |
| 2012 | ECCV | Cost-Sensitive Top-Down/Bottom-Up Inference for Multiscale Activity Recognition. | Mohamed R. Amer, Dan Xie, Mingtian Zhao, Sinisa Todorovic, Song Chun Zhu |
| 2012 | ECCV | Human Activities as Stochastic Kronecker Graphs. | Sinisa Todorovic |
| 2012 | IUI | Towards recognizing "cool": can end users help computer vision recognize subjective attributes of objects in images? | William Curran, Travis Moore, Todd Kulesza, Weng-Keen Wong, Sinisa Todorovic, Simone Stumpf, Rachel White, Margaret M. Burnett |
| 2011 | CVPR | Multiobject tracking as maximum weight independent set. | William Brendel, Mohamed R. Amer, Sinisa Todorovic |
| 2011 | CVPR | Probabilistic event logic for interval-based event recognition. | William Brendel, Alan Fern, Sinisa Todorovic |
| 2011 | CVPR | Scene shape from texture of objects. | Nadia Payet, Sinisa Todorovic |
| 2011 | ICCV | A chains model for localizing participants of group activities in videos. | Mohamed R. Amer, Sinisa Todorovic |
| 2011 | ICCV | Learning spatiotemporal graphs of human activities. | William Brendel, Sinisa Todorovic |
| 2011 | ICCV | From contours to 3D object detection and pose estimation. | Nadia Payet, Sinisa Todorovic |
| 2010 | ECCV | Activities as Time Series of Human Postures. | William Brendel, Sinisa Todorovic |
| 2010 | ECCV | From a Set of Shapes to Object Discovery. | Nadia Payet, Sinisa Todorovic |
| 2010 | ICIP | Monocular Extraction of 2.1D Sketch. | Mohamed R. Amer, Raviv Raich, Sinisa Todorovic |
| 2010 | SSPR | From Region Based Image Representation to Object Discovery and Recognition. | Narendra Ahuja, Sinisa Todorovic |
| 2009 | CVPR | Dictionary-free categorization of very similar objects via stacked evidence trees. | Gonzalo Martnez-Muoz, Natalia Larios Delgado, Eric N. Mortensen, Wei Zhang, Asako Yamamuro, Robert Paasch, Nadia Payet, David A. Lytle, Linda G. Shapiro, Sinisa Todorovic, Andrew Moldenke, Thomas G. Dietterich |
| 2009 | ICCV | Video object segmentation by tracking regions. | William Brendel, Sinisa Todorovic |
| 2009 | ICCV | Texel-based texture segmentation. | Sinisa Todorovic, Narendra Ahuja |
| 2008 | CVPR | Connected Segmentation Tree - A joint representation of region layout and hierarchy. | Narendra Ahuja, Sinisa Todorovic |
| 2008 | CVPR | Learning subcategory relevances for category recognition. | Sinisa Todorovic, Narendra Ahuja |
| 2008 | ICPR | Scale-invariant region-based hierarchical imagematching. | Sinisa Todorovic, Narendra Ahuja |
| 2008 | SDM | A Feature Selection Algorithm Capable of Handling Extremely Large Data Dimensionality. | Yijun Sun, Sinisa Todorovic, Steve Goodison |
| 2007 | ICCV | Extracting Texels in 2.1D Natural Textures. | Narendra Ahuja, Sinisa Todorovic |
| 2007 | ICCV | Learning the Taxonomy and Models of Categories Present in Arbitrary Images. | Narendra Ahuja, Sinisa Todorovic |
| 2006 | CVPR | Extracting Subimages of an Unknown Category from a Set of Images. | Sinisa Todorovic, Narendra Ahuja |
| 2006 | ICPR | 3D Texture Classification Using the Belief Net of a Segmentation Tree. | Sinisa Todorovic, Narendra Ahuja |
| 2005 | ICML | Unifying the error-correcting and output-code AdaBoost within the margin framework. | Yijun Sun, Sinisa Todorovic, Jian Li, Dapeng Wu |
| 2004 | CVPR | Interpretation of Complex Scenes Using Generative Dynamic-Structure Models. | Sinisa Todorovic, Michael C. Nechyba |
| 2004 | ECCV | Towards Intelligent Mission Profiles of Micro Air Vehicles: Multiscale Viterbi Classification. | Sinisa Todorovic, Michael C. Nechyba |
| 2004 | ICPR | Detection of Artificial Structures in Natural-Scene Images Using Dynamic Trees. | Sinisa Todorovic, Michael C. Nechyba |
| 2004 | ICRA | Intelligent Missions for MAVs: Visual Contexts for Control, Tracking and Recognition. | Sinisa Todorovic, Michael C. Nechyba |
| 2003 | ICIP | Multiresolution linear discriminant analysis: efficient extraction of geometrical structures in images. | Sinisa Todorovic, Michael C. Nechyba |
| 2003 | ICRA | Sky/ground modeling for autonomous MAV flight. | Sinisa Todorovic, Michael C. Nechyba, Peter G. Ifju |