| RegionViT: Regional-to-Local Attention for Vision Transformers | 0 | 0.34 | 2022 |
| Distributed adversarial training to robustify deep neural networks at scale. | 0 | 0.34 | 2022 |
| Can an Image Classifier Suffice For Action Recognition? | 0 | 0.34 | 2022 |
| CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification | 8 | 0.66 | 2021 |
| Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition | 2 | 0.36 | 2021 |
| Generating Adversarial Computer Programs using Optimized Obfuscations | 0 | 0.34 | 2021 |
| Relationship Matters - Relation Guided Knowledge Transfer for Incremental Learning of Object Detectors. | 0 | 0.34 | 2020 |
| Moments in Time Dataset: one million videos for event understanding | 28 | 0.80 | 2020 |
| Interpreting Adversarial Examples by Activation Promotion and Suppression. | 1 | 0.35 | 2019 |
| Structured Adversarial Attack: Towards General Implementation and Better Interpretability | 0 | 0.34 | 2019 |
| More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation | 0 | 0.34 | 2019 |
| Reasoning About Human-Object Interactions Through Dual Attention Networks | 1 | 0.36 | 2019 |
| Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition. | 2 | 0.36 | 2018 |
| SC-Conv: Sparse-Complementary Convolution for Efficient Model Utilization on CNNs | 0 | 0.34 | 2018 |
| Efficient Fusion of Sparse and Complementary Convolutions for Object Recognition and Detection. | 0 | 0.34 | 2018 |
| Semantically Guided Visual Question Answering | 1 | 0.35 | 2018 |
| Object-Centric Spatio-Temporal Activity Detection and Recognition. | 0 | 0.34 | 2018 |
| Sparse Deep Feature Representation for Object Detection from Wearable Cameras. | 0 | 0.34 | 2017 |
| A Unified Multi-Scale Deep Convolutional Neural Network For Fast Object Detection | 206 | 4.83 | 2016 |
| People Detection In Crowded Scenes By Context-Driven Label Propagation | 0 | 0.34 | 2016 |
| Self-calibration from vehicle information | 2 | 0.36 | 2015 |
| Temporal Sequence Modeling for Video Event Detection | 32 | 0.82 | 2014 |
| Long-term object tracking for parked vehicle detection | 2 | 0.38 | 2014 |
| IBM-Northwestern@TRECVID 2014 - Surveillance Event Detection. | 0 | 0.34 | 2014 |
| Random Laplace Feature Maps for Semigroup Kernels on Histograms | 16 | 0.81 | 2014 |
| Riskwheel: Interactive Visual Analytics For Surveillance Event Detection | 2 | 0.39 | 2014 |
| Relative Attributes for Large-Scale Abandoned Object Detection | 16 | 0.65 | 2013 |
| Spatio-temporal fisher vector coding for surveillance event detection | 11 | 0.53 | 2013 |
| IBM Research and Columbia University TRECVID-2013 Multimedia Event Detection (MED), Multimedia Event Recounting (MER), Surveillance Event Detection (SED), and Semantic Indexing (SIN) Systems. | 0 | 0.34 | 2013 |
| Hand tracking by binary quadratic programming and its application to retail activity recognition | 1 | 0.35 | 2012 |
| Multimodal ranking for non-compliance detection in retail surveillance | 1 | 0.40 | 2012 |
| Robust Foreground and Abandonment Analysis for Large-Scale Abandoned Object Detection in Complex Surveillance Videos | 6 | 0.44 | 2012 |
| Practical computer vision: example techniques and challenges | 5 | 0.79 | 2011 |
| A pattern discovery approach to retail fraud detection | 3 | 0.44 | 2011 |
| Soft margin keyframe comparison: Enhancing precision of fraud detection in retail surveillance | 1 | 0.37 | 2011 |
| Modeling of temporarily static objects for robust abandoned object detection in urban surveillance | 14 | 0.63 | 2011 |
| Robust spatiotemporal matching of electronic slides to presentation videos. | 7 | 0.56 | 2011 |
| Robust Abandoned Object Detection Using Region-Level Analysis | 16 | 0.67 | 2011 |
| Graph based event detection from realistic videos using weak feature correspondence. | 2 | 0.43 | 2010 |
| An integer programming approach to visual compliance. | 0 | 0.34 | 2010 |
| Fast detection of retail fraud using polar touch buttons | 2 | 0.38 | 2009 |
| Recognition Of Repetitive Sequential Human Activity | 16 | 1.27 | 2009 |
| Detecting sweethearting in retail surveillance videos | 7 | 0.63 | 2009 |
| Accurate alignment of presentation slides with educational video | 2 | 0.45 | 2009 |
| Evaluation of Localized Semantics: Data, Methodology, and Experiments | 21 | 3.34 | 2008 |
| Reducing Correspondence Ambiguity In Loosely Labeled Training Data | 6 | 0.98 | 2007 |
| Temporal Modeling of Slide Change in Presentation Videos | 10 | 0.76 | 2007 |
| Curve Matching, Time Warping, and Light Fields: New Algorithms for Computing Similarity between Curves | 35 | 1.35 | 2007 |
| Matching slides to presentation videos using SIFT and scene background matching | 19 | 1.37 | 2006 |
