Search Results for author: Michael Greenspan

Found 24 papers, 15 papers with code

Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation

no code implementations16 Nov 2023 Yangzheng Wu, Michael Greenspan

This paper addresses the simulation-to-real domain gap in 6DoF PE, and proposes a novel self-supervised keypoint radial voting-based 6DoF PE framework, effectively narrowing this gap using a learnable kernel in RKHS.

Pose Estimation

Diffusion Models with Deterministic Normalizing Flow Priors

1 code implementation3 Sep 2023 Mohsen Zand, Ali Etemad, Michael Greenspan

We use normalizing flows to parameterize the noisy data at any arbitrary step of the diffusion process and utilize it as the prior in the reverse diffusion process.

Denoising Image Generation

Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction

1 code implementation31 Aug 2023 Mohsen Zand, Ali Etemad, Michael Greenspan

Our experiments on two challenging benchmark datasets, CMU Mocap and Human3. 6M, demonstrate that our proposed method is able to effectively model the sequence information for motion prediction and outperform other techniques to set a new state-of-the-art.

Human motion prediction motion prediction

Learning Better Keypoints for Multi-Object 6DoF Pose Estimation

1 code implementation15 Aug 2023 Yangzheng Wu, Michael Greenspan

We address the problem of keypoint selection, and find that the performance of 6DoF pose estimation methods can be improved when pre-defined keypoint locations are learned, rather than being heuristically selected as has been the standard approach.

Object Pose Estimation

Context-aware Pedestrian Trajectory Prediction with Multimodal Transformer

no code implementations7 Jul 2023 Haleh Damirchi, Michael Greenspan, Ali Etemad

Quantitative results demonstrate the superiority of our proposed model over the current state-of-the-art, which consistently achieves the lowest error for 3 time horizons of 0. 5, 1. 0 and 1. 5 seconds.

Pedestrian Trajectory Prediction Trajectory Prediction

Continual Learning for Out-of-Distribution Pedestrian Detection

1 code implementation26 Jun 2023 Mahdiyar Molahasani, Ali Etemad, Michael Greenspan

A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection.

Continual Learning object-detection +3

Can Continual Learning Improve Long-Tailed Recognition? Toward a Unified Framework

no code implementations23 Jun 2023 Mahdiyar Molahasani, Michael Greenspan, Ali Etemad

Next, we assert that by treating the learning of the Head and Tail as two separate and sequential steps, Continual Learning (CL) methods can effectively update the weights of the learner to learn the Tail without forgetting the Head.

Continual Learning

Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection

no code implementations16 May 2023 Andrew Farley, Mohsen Zand, Michael Greenspan

We propose a method that augments a simulated dataset using diffusion models to improve the performance of pedestrian detection in real-world data.

Pedestrian Detection

JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions

1 code implementation18 Oct 2022 Mo Yu, Yi Gu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell, Chuang Gan

Hence, in order to achieve higher performance on our tasks, models need to effectively utilize such functional knowledge to infer the outcomes of actions, rather than relying solely on memorizing facts.

Reading Comprehension

Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimation

1 code implementation14 Oct 2022 Yangzheng Wu, Alireza Javaheri, Mohsen Zand, Michael Greenspan

We propose a novel keypoint voting 6DoF object pose estimation method, which takes pure unordered point cloud geometry as input without RGB information.

Keypoint Estimation Pose Estimation +1

ObjectBox: From Centers to Boxes for Anchor-Free Object Detection

1 code implementation14 Jul 2022 Mohsen Zand, Ali Etemad, Michael Greenspan

We present ObjectBox, a novel single-stage anchor-free and highly generalizable object detection approach.

Object object-detection +1

Multiscale Crowd Counting and Localization By Multitask Point Supervision

1 code implementation21 Feb 2022 Mohsen Zand, Haleh Damirchi, Andrew Farley, Mahdiyar Molahasani, Michael Greenspan, Ali Etemad

As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multiscale representations of encoded crowd images, and subsequently fusing them.

Crowd Counting

Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation

no code implementations12 Jun 2021 Joy Mazumder, Mohsen Zand, Michael Greenspan

Applying our method can also improve the pose estimation average precision results of Op-Net by 6. 06% on average.

6D Pose Estimation using RGB

Oriented Bounding Boxes for Small and Freely Rotated Objects

no code implementations24 Apr 2021 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 $2\times 2$ pixels.

Novel Object Detection object-detection +1

Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics

1 code implementation9 Apr 2021 Mohsen Zand, Ali Etemad, Michael Greenspan

We specifically propose to use conditional priors to factorize the latent space for the time dependent modeling.

motion prediction Structured Prediction +3

Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition

1 code implementation ICCV 2021 Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad

Moreover, face recognition experiments demonstrate that our hallucinated depth along with the input RGB images boosts performance across various architectures when compared to a single RGB modality by average values of +1. 2%, +2. 6%, and +2. 6% for IIIT-D, EURECOM, and LFW datasets respectively.

Face Recognition Generative Adversarial Network +1

Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting

1 code implementation6 Apr 2021 Yangzheng Wu, Mohsen Zand, Ali Etemad, Michael Greenspan

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.

 Ranked #1 on 6D Pose Estimation using RGBD on YCB-Video (ADDS AUC metric)

6D Pose Estimation using RGBD

Procam Calibration from a Single Pose of a Planar Target

no code implementations22 Feb 2021 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.

Depth as Attention for Face Representation Learning

1 code implementation3 Jan 2021 Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad

Our novel attention mechanism directs the deep network "where to look" for visual features in the RGB image by focusing the attention of the network using depth features extracted by a Convolution Neural Network (CNN).

Face Recognition Representation Learning

Exploring End-to-End Differentiable Natural Logic Modeling

1 code implementation COLING 2020 Yufei Feng, Zi'ou Zheng, Quan Liu, Michael Greenspan, Xiaodan Zhu

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 natural logic formalism while introducing subsymbolic vector representations and neural components.

Inductive Bias

Deriving Commonsense Inference Tasks from Interactive Fictions

no code implementations19 Oct 2020 Mo Yu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell

Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an indispensable cornerstone in building general AI systems.

Reading Comprehension

Two-Level Attention-based Fusion Learning for RGB-D Face Recognition

1 code implementation29 Feb 2020 Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad

A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition.

Face Recognition Transfer Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.