Search Results for author: Greg Mori

Found 84 papers, 26 papers with code

Pretext Training Algorithms for Event Sequence Data

no code implementations16 Feb 2024 Yimu Wang, He Zhao, Ruizhi Deng, Frederick Tung, Greg Mori

Pretext training followed by task-specific fine-tuning has been a successful approach in vision and language domains.

Contrastive Learning

OPSurv: Orthogonal Polynomials Quadrature Algorithm for Survival Analysis

no code implementations2 Feb 2024 Lilian W. Bialokozowicz, Hoang M. Le, Tristan Sylvain, Peter A. I. Forsyth, Vineel Nagisetty, Greg Mori

This paper introduces the Orthogonal Polynomials Quadrature Algorithm for Survival Analysis (OPSurv), a new method providing time-continuous functional outputs for both single and competing risks scenarios in survival analysis.

Survival Analysis

Rethinking Learning Approaches for Long-Term Action Anticipation

1 code implementation20 Oct 2022 Megha Nawhal, Akash Abdu Jyothi, Greg Mori

Action anticipation involves predicting future actions having observed the initial portion of a video.

Action Anticipation Future prediction +1

Continuous-time Particle Filtering for Latent Stochastic Differential Equations

no code implementations1 Sep 2022 Ruizhi Deng, Greg Mori, Andreas M. Lehrmann

Particle filtering is a standard Monte-Carlo approach for a wide range of sequential inference tasks.

RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression

1 code implementation30 May 2022 Yu Gong, Greg Mori, Frederick Tung

Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks.

Inductive Bias regression +2

Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space

no code implementations ICLR 2022 Steeven Janny, Fabien Baradel, Natalia Neverova, Madiha Nadri, Greg Mori, Christian Wolf

Learning causal relationships in high-dimensional data (images, videos) is a hard task, as they are often defined on low dimensional manifolds and must be extracted from complex signals dominated by appearance, lighting, textures and also spurious correlations in the data.

counterfactual Counterfactual Reasoning +1

MUSE: Feature Self-Distillation with Mutual Information and Self-Information

no code implementations25 Oct 2021 Yu Gong, Ye Yu, Gaurav Mittal, Greg Mori, Mei Chen

Importantly, we argue and empirically demonstrate that MUSE, compared to other feature discrepancy functions, is a more functional proxy to introduce dependency and effectively improve the expressivity of all features in the knowledge distillation framework.

Image Classification Knowledge Distillation +2

Monotonicity as a requirement and as a regularizer: efficient methods and applications

no code implementations29 Sep 2021 Joao Monteiro, Mohamed Osama Ahmed, Hossein Hajimirsadeghi, Greg Mori

We study the setting where risk minimization is performed over general classes of models and consider two cases where monotonicity is treated as either a requirement to be satisfied everywhere or a useful property.

Image Classification

D3D-HOI: Dynamic 3D Human-Object Interactions from Videos

2 code implementations19 Aug 2021 Xiang Xu, Hanbyul Joo, Greg Mori, Manolis Savva

We evaluate this approach on our dataset, demonstrating that human-object relations can significantly reduce the ambiguity of articulated object reconstructions from challenging real-world videos.

Human-Object Interaction Detection Object

Continuous Latent Process Flows

1 code implementation NeurIPS 2021 Ruizhi Deng, Marcus A. Brubaker, Greg Mori, Andreas M. Lehrmann

Partial observations of continuous time-series dynamics at arbitrary time stamps exist in many disciplines.

Time Series Time Series Analysis

TD-GEN: Graph Generation With Tree Decomposition

no code implementations20 Jun 2021 Hamed Shirzad, Hossein Hajimirsadeghi, Amir H. Abdi, Greg Mori

We propose TD-GEN, a graph generation framework based on tree decomposition, and introduce a reduced upper bound on the maximum number of decisions needed for graph generation.

Graph Generation Tree Decomposition

Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation

no code implementations CVPR 2021 Mengyao Zhai, Lei Chen, Greg Mori

Deep neural networks are susceptible to catastrophic forgetting: when encountering a new task, they can only remember the new task and fail to preserve its ability to accomplish previously learned tasks.

Continual Learning

Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation

no code implementations ECCV 2020 Mengyao Zhai, Lei Chen, JiaWei He, Megha Nawhal, Frederick Tung, Greg Mori

In contrast, we propose a parameter efficient framework, Piggyback GAN, which learns the current task by building a set of convolutional and deconvolutional filters that are factorized into filters of the models trained on previous tasks.

Adaptive Appearance Rendering

1 code implementation24 Apr 2021 Mengyao Zhai, Ruizhi Deng, Jiacheng Chen, Lei Chen, Zhiwei Deng, Greg Mori

Hence, we develop an approach based on intermediate representations of poses and appearance: our pose-guided appearance rendering network firstly encodes the targets' poses using an encoder-decoder neural network.

Video Generation

Learning Discriminative Prototypes with Dynamic Time Warping

1 code implementation CVPR 2021 Xiaobin Chang, Frederick Tung, Greg Mori

We propose Discriminative Prototype DTW (DP-DTW), a novel method to learn class-specific discriminative prototypes for temporal recognition tasks.

Action Segmentation Dynamic Time Warping +4

Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data

no code implementations25 Feb 2021 Yu Gong, Hossein Hajimirsadeghi, JiaWei He, Thibaut Durand, Greg Mori

Learning from heterogeneous data poses challenges such as combining data from various sources and of different types.

Imputation

Activity Graph Transformer for Temporal Action Localization

no code implementations21 Jan 2021 Megha Nawhal, Greg Mori

Detecting and localizing action instances in untrimmed videos requires reasoning over multiple action instances in a video.

Ranked #3 on Temporal Action Localization on THUMOS’14 (mAP IOU@0.1 metric)

Temporal Action Localization

Neural fidelity warping for efficient robot morphology design

1 code implementation8 Dec 2020 Sha Hu, Zeshi Yang, Greg Mori

We consider the problem of optimizing a robot morphology to achieve the best performance for a target task, under computational resource limitations.

Bayesian Optimization

House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation

1 code implementation ECCV 2020 Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, Yasutaka Furukawa

This paper proposes a novel graph-constrained generative adversarial network, whose generator and discriminator are built upon relational architecture.

Generative Adversarial Network

Variational Hyper RNN for Sequence Modeling

no code implementations24 Feb 2020 Ruizhi Deng, Yanshuai Cao, Bo Chang, Leonid Sigal, Greg Mori, Marcus A. Brubaker

In this work, we propose a novel probabilistic sequence model that excels at capturing high variability in time series data, both across sequences and within an individual sequence.

Time Series Time Series Analysis

Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows

1 code implementation NeurIPS 2020 Ruizhi Deng, Bo Chang, Marcus A. Brubaker, Greg Mori, Andreas Lehrmann

Normalizing flows transform a simple base distribution into a complex target distribution and have proved to be powerful models for data generation and density estimation.

Density Estimation Irregular Time Series +2

Adapting Grad-CAM for Embedding Networks

1 code implementation17 Jan 2020 Lei Chen, Jianhui Chen, Hossein Hajimirsadeghi, Greg Mori

Then, we develop an efficient weight-transfer method to explain decisions for any image without back-propagation.

Image Captioning Image Classification

Point Process Flows

no code implementations18 Oct 2019 Nazanin Mehrasa, Ruizhi Deng, Mohamed Osama Ahmed, Bo Chang, JiaWei He, Thibaut Durand, Marcus Brubaker, Greg Mori

Event sequences can be modeled by temporal point processes (TPPs) to capture their asynchronous and probabilistic nature.

Point Processes

Arbitrarily-conditioned Data Imputation

no code implementations pproximateinference AABI Symposium 2019 Micael Carvalho, Thibaut Durand, JiaWei He, Nazanin Mehrasa, Greg Mori

In this paper, we propose an arbitrarily-conditioned data imputation framework built upon variational autoencoders and normalizing flows.

Imputation

Variational Selective Autoencoder

no code implementations pproximateinference AABI Symposium 2019 Yu Gong, Hossein Hajimirsadeghi, JiaWei He, Megha Nawhal, Thibaut Durand, Greg Mori

Despite promising progress on unimodal data imputation (e. g. image inpainting), models for multimodal data imputation are far from satisfactory.

Image Inpainting Imputation

Graph Generation with Variational Recurrent Neural Network

no code implementations2 Oct 2019 Shih-Yang Su, Hossein Hajimirsadeghi, Greg Mori

Generating graph structures is a challenging problem due to the diverse representations and complex dependencies among nodes.

Attribute Graph Generation +1

Policy Message Passing: A New Algorithm for Probabilistic Graph Inference

no code implementations ICLR 2020 Zhiwei Deng, Greg Mori

A general graph-structured neural network architecture operates on graphs through two core components: (1) complex enough message functions; (2) a fixed information aggregation process.

Relational Graph Learning for Crowd Navigation

1 code implementation28 Sep 2019 Changan Chen, Sha Hu, Payam Nikdel, Greg Mori, Manolis Savva

We present a relational graph learning approach for robotic crowd navigation using model-based deep reinforcement learning that plans actions by looking into the future.

Graph Learning Reinforcement Learning (RL)

CoPhy: Counterfactual Learning of Physical Dynamics

1 code implementation ICLR 2020 Fabien Baradel, Natalia Neverova, Julien Mille, Greg Mori, Christian Wolf

Understanding causes and effects in mechanical systems is an essential component of reasoning in the physical world.

counterfactual Video Prediction

Continuous Graph Flow

no code implementations7 Aug 2019 Zhiwei Deng, Megha Nawhal, Lili Meng, Greg Mori

In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data.

Density Estimation Graph Generation

Similarity-Preserving Knowledge Distillation

1 code implementation ICCV 2019 Frederick Tung, Greg Mori

Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network.

Knowledge Distillation Neural Network Compression

Variational Autoencoders with Jointly Optimized Latent Dependency Structure

no code implementations ICLR 2019 Jiawei He, Yu Gong, Joseph Marino, Greg Mori, Andreas Lehrmann

In particular, we express the latent variable space of a variational autoencoder (VAE) in terms of a Bayesian network with a learned, flexible dependency structure.

Learning a Deep ConvNet for Multi-label Classification with Partial Labels

no code implementations CVPR 2019 Thibaut Durand, Nazanin Mehrasa, Greg Mori

Multi-label classification is a more difficult task than single-label classification because both the input images and output label spaces are more complex.

Classification General Classification +3

Constraint-Aware Deep Neural Network Compression

no code implementations ECCV 2018 Changan Chen, Frederick Tung, Naveen Vedula, Greg Mori

Deep neural network compression has the potential to bring modern resource-hungry deep networks to resource-limited devices.

Bayesian Optimization Neural Network Compression +1

Hierarchical Relational Networks for Group Activity Recognition and Retrieval

1 code implementation ECCV 2018 Mostafa S. Ibrahim, Greg Mori

Second, we propose a Relational Autoencoder model for unsupervised learning of features for action and scene retrieval.

Denoising Group Activity Recognition +1

Time Perception Machine: Temporal Point Processes for the When, Where and What of Activity Prediction

no code implementations13 Aug 2018 Yatao Zhong, Bicheng Xu, Guang-Tong Zhou, Luke Bornn, Greg Mori

Numerous powerful point process models have been developed to understand temporal patterns in sequential data from fields such as health-care, electronic commerce, social networks, and natural disaster forecasting.

Activity Prediction Point Processes

Object Level Visual Reasoning in Videos

1 code implementation ECCV 2018 Fabien Baradel, Natalia Neverova, Christian Wolf, Julien Mille, Greg Mori

Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as features related to the global context.

Human Activity Recognition Object +3

CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization

no code implementations CVPR 2018 Frederick Tung, Greg Mori

This allows us to take advantage of the complementary nature of pruning and quantization and to recover from premature pruning errors, which is not possible with current two-stage approaches.

Image Classification Network Pruning +3

Distribution Aware Active Learning

no code implementations23 May 2018 Arash Mehrjou, Mehran Khodabandeh, Greg Mori

This strategy does not make good use of the structure of the dataset at hand and is prone to be misguided by outliers.

Active Learning

Structured Label Inference for Visual Understanding

1 code implementation18 Feb 2018 Nelson Nauata, Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori

In this paper, we exploit this rich structure for performing graph-based inference in label space for a number of tasks: multi-label image and video classification and action detection in untrimmed videos.

Action Detection General Classification +3

Sparsely Aggregated Convolutional Networks

2 code implementations ECCV 2018 Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng, Greg Mori, Ping Tan

We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers.

Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering

no code implementations5 Dec 2017 Mengyao Zhai, Jiacheng Chen, Ruizhi Deng, Lei Chen, Ligeng Zhu, Greg Mori

An architecture combining a hierarchical temporal model for predicting human poses and encoder-decoder convolutional neural networks for rendering target appearances is proposed.

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization

no code implementations28 Jul 2017 Frederick Tung, Srikanth Muralidharan, Greg Mori

When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain.

Bayesian Optimization Network Pruning

Factorized Variational Autoencoders for Modeling Audience Reactions to Movies

no code implementations CVPR 2017 Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews, Greg Mori

Matrix and tensor factorization methods are often used for finding underlying low-dimensional patterns from noisy data.

Hierarchical Label Inference for Video Classification

no code implementations15 Jun 2017 Nelson Nauata, Jonathan Smith, Greg Mori

Videos are a rich source of high-dimensional structured data, with a wide range of interacting components at varying levels of granularity.

Classification General Classification +1

Learning to Learn from Noisy Web Videos

no code implementations CVPR 2017 Serena Yeung, Vignesh Ramanathan, Olga Russakovsky, Liyue Shen, Greg Mori, Li Fei-Fei

Our method uses Q-learning to learn a data labeling policy on a small labeled training dataset, and then uses this to automatically label noisy web data for new visual concepts.

Action Recognition Q-Learning +1

Active Learning for Structured Prediction from Partially Labeled Data

no code implementations7 Jun 2017 Mehran Khodabandeh, Zhiwei Deng, Mostafa S. Ibrahim, Shinichi Satoh, Greg Mori

We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video.

Active Learning Structured Prediction

Learning Person Trajectory Representations for Team Activity Analysis

no code implementations3 Jun 2017 Nazanin Mehrasa, Yatao Zhong, Frederick Tung, Luke Bornn, Greg Mori

Activity analysis in which multiple people interact across a large space is challenging due to the interplay of individual actions and collective group dynamics.

Generic Tubelet Proposals for Action Localization

no code implementations30 May 2017 Jiawei He, Mostafa S. Ibrahim, Zhiwei Deng, Greg Mori

Our class-independent TPN outperforms other tubelet generation methods, and our unified temporal deep network achieves state-of-the-art localization results on all three datasets.

Action Classification Action Localization +1

LabelBank: Revisiting Global Perspectives for Semantic Segmentation

1 code implementation29 Mar 2017 Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou, Fei Sha, Greg Mori

We advocate that holistic inference of image concepts provides valuable information for detailed pixel labeling.

Segmentation Semantic Segmentation

Recalling Holistic Information for Semantic Segmentation

no code implementations24 Nov 2016 Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou, Fei Sha, Greg Mori

We advocate that high-recall holistic inference of image concepts provides valuable information for detailed pixel labeling.

Segmentation Semantic Segmentation

Deep Learning of Appearance Models for Online Object Tracking

no code implementations9 Jul 2016 Mengyao Zhai, Mehrsan Javan Roshtkhari, Greg Mori

This paper introduces a novel deep learning based approach for vision based single target tracking.

Object Tracking

Hierarchical Deep Temporal Models for Group Activity Recognition

1 code implementation9 Jul 2016 Mostafa S. Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori

In order to model both person-level and group-level dynamics, we present a 2-stage deep temporal model for the group activity recognition problem.

Group Activity Recognition

End-to-end Learning of Action Detection from Frame Glimpses in Videos

1 code implementation CVPR 2016 Serena Yeung, Olga Russakovsky, Greg Mori, Li Fei-Fei

In this work we introduce a fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions.

Ranked #9 on Temporal Action Localization on THUMOS’14 (mAP IOU@0.2 metric)

Action Detection Temporal Action Localization

A Hierarchical Deep Temporal Model for Group Activity Recognition

1 code implementation CVPR 2016 Moustafa Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori

In group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity.

Group Activity Recognition

Deep Structured Models For Group Activity Recognition

no code implementations12 Jun 2015 Zhiwei Deng, Mengyao Zhai, Lei Chen, Yuhao Liu, Srikanth Muralidharan, Mehrsan Javan Roshtkhari, Greg Mori

This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes.

Group Activity Recognition

Hierarchical Maximum-Margin Clustering

no code implementations6 Feb 2015 Guang-Tong Zhou, Sung Ju Hwang, Mark Schmidt, Leonid Sigal, Greg Mori

We present a hierarchical maximum-margin clustering method for unsupervised data analysis.

Clustering

A Max-Margin Riffled Independence Model for Image Tag Ranking

no code implementations CVPR 2013 Tian Lan, Greg Mori

We propose Max-Margin Riffled Independence Model (MMRIM), a new method for image tag ranking modeling the structured preferences among tags.

Attribute Retrieval +1

Kernel Latent SVM for Visual Recognition

no code implementations NeurIPS 2012 Weilong Yang, Yang Wang, Arash Vahdat, Greg Mori

Latent SVMs (LSVMs) are a class of powerful tools that have been successfully applied to many applications in computer vision.

Learning a discriminative hidden part model for human action recognition

no code implementations NeurIPS 2008 Yang Wang, Greg Mori

In particular, our experimental results demonstrate that combining large-scale global features and local patch features performs significantly better than directly applying hCRF on local patches alone.

Action Recognition Object +2

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