11 citations · 19 across the 17 of their papers we have counts for
17 papers
Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing
Amin Jalali, Milad Soltany, Michael Greenspan +1
We propose TimeHUT, a novel method for learning time-series representations by hierarchical uniformity-tolerance balancing of contrastive representations. Our method uses two disti…
PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection
Mahdiyar Molahasani, Azadeh Motamedi, Michael Greenspan +2
We introduce Projection-based Reduction of Implicit Spurious bias in vision-language Models (PRISM), a new data-free and task-agnostic solution for bias mitigation in VLMs like CLI…
Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting
Haleh Damirchi, Ali Etemad, Michael Greenspan
Pedestrian trajectory prediction remains a challenge for autonomous systems, particularly due to the intricate dynamics of social interactions. Accurate forecasting requires a comp…
Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training
Milad Soltany, Farhad Pourpanah, Mahdiyar Molahasani +2
In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data hete…
CycleCrash: A Dataset of Bicycle Collision Videos for Collision Prediction and Analysis
Nishq Poorav Desai, Ali Etemad, Michael Greenspan
Self-driving research often underrepresents cyclist collisions and safety. To address this, we present CycleCrash, a novel dataset consisting of 3,000 dashcam videos with 436,347 f…
Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients
Farhad Pourpanah, Mahdiyar Molahasani, Milad Soltany +2
We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alig…
Diffusion Models with Deterministic Normalizing Flow Priors
Mohsen Zand, Ali Etemad, Michael Greenspan
For faster sampling and higher sample quality, we propose DiNof (ffusion with rmalizing low priors), a technique that makes use of normalizing…
Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction
Mohsen Zand, Ali Etemad, Michael Greenspan
A new method is proposed for human motion prediction by learning temporal and spatial dependencies. Recently, multiscale graphs have been developed to model the human body at highe…
Learning Better Keypoints for Multi-Object 6DoF Pose Estimation
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…
Context-aware Pedestrian Trajectory Prediction with Multimodal Transformer
Haleh Damirchi, Michael Greenspan, Ali Etemad
We propose a novel solution for predicting future trajectories of pedestrians. Our method uses a multimodal encoder-decoder transformer architecture, which takes as input both pede…
Continual Learning for Out-of-Distribution Pedestrian Detection
Mahdiyar Molahasani, Ali Etemad, Michael Greenspan
A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection. While recent pedestrian detection models have achieved…
On The Relationship Between Continual Learning and Long-Tailed Recognition
Mahdiyar Molahasani, Michael Greenspan, Ali Etemad
Real-world datasets often exhibit long-tailed distributions, where a few dominant "Head" classes have abundant samples while most "Tail" classes are severely underrepresented, lead…
Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection
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. The high cost of collecting and…
Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimation
Yangzheng Wu, Alireza Javaheri, Mohsen Zand +1
We propose a novel keypoint voting 6DoF object pose estimation method, which takes pure unordered point cloud geometry as input without RGB information. The proposed cascaded keypo…
ObjectBox: From Centers to Boxes for Anchor-Free Object Detection
Mohsen Zand, Ali Etemad, Michael Greenspan
We present ObjectBox, a novel single-stage anchor-free and highly generalizable object detection approach. As opposed to both existing anchor-based and anchor-free detectors, which…
Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference
Yufei Feng, Xiaoyu Yang, Xiaodan Zhu +1
We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision. The model samples and rewards specific reasoning paths through po…
Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
Mohsen Zand, Ali Etemad, Michael Greenspan
Conditional Normalizing Flows (CNFs) are flexible generative models capable of representing complicated distributions with high dimensionality and large interdimensional correlatio…