181 citations · 310 across the 12 of their papers we have counts for
13 papers
JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions
Mo Yu, Yi Gu, Xiaoxiao Guo +5
Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an essential cornerstone in building general AI systems. We propose a new…
Multiscale Crowd Counting and Localization By Multitask Point Supervision
Mohsen Zand, Haleh Damirchi, Andrew Farley +3
We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly ta…
Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation
Joy Mazumder, Mohsen Zand, Michael Greenspan
This work presents a novel approach to improve the results of pose estimation by detecting and distinguishing between the occurrence of True and False Positive results. It achieves…
Oriented Bounding Boxes for Small and Freely Rotated Objects
Mohsen Zand, Ali Etemad, Michael Greenspan
A novel object detection method is presented that handles freely rotated objects of arbitrary sizes, including tiny objects as small as pixels. Such tiny objects appear…
Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
Yangzheng Wu, Mohsen Zand, Ali Etemad +1
We propose a novel keypoint voting scheme based on intersecting spheres, that is more accurate than existing schemes and allows for fewer, more disperse keypoints. The scheme is ba…
Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition
Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan +1
We present the Teacher-Student Generative Adversarial Network (TS-GAN) to generate depth images from single RGB images in order to boost the performance of face recognition systems…
Procam Calibration from a Single Pose of a Planar Target
Ghani O. Lawal, Michael Greenspan
A novel user friendly method is proposed for calibrating a procam system from a single pose of a planar chessboard target. The user simply needs to orient the chessboard in a singl…
Depth as Attention for Face Representation Learning
Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan +1
Face representation learning solutions have recently achieved great success for various applications such as verification and identification. However, face recognition approaches t…
Exploring End-to-End Differentiable Natural Logic Modeling
Yufei Feng, Zi'ou Zheng, Quan Liu +2
We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natura…
Deriving Commonsense Inference Tasks from Interactive Fictions
Mo Yu, Xiaoxiao Guo, Yufei Feng +3
Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an indispensable cornerstone in building general AI systems. We propose a…
Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games
Yufei Feng, Mo Yu, Wenhan Xiong +6
We propose the new problem of learning to recover reasoning chains from weakly supervised signals, i.e., the question-answer pairs. We propose a cooperative game approach to deal w…
Two-Level Attention-based Fusion Learning for RGB-D Face Recognition
Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan +1
With recent advances in RGB-D sensing technologies as well as improvements in machine learning and fusion techniques, RGB-D facial recognition has become an active area of research…
Difference of Normals as a Multi-Scale Operator in Unorganized Point Clouds
Yani Ioannou, Babak Taati, Robin Harrap +1
A novel multi-scale operator for unorganized 3D point clouds is introduced. The Difference of Normals (DoN) provides a computationally efficient, multi-scale approach to processing…