1 code implementation • 22 May 2024 • Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Mohamed Osama Ahmed, Yoshua Bengio, Greg Mori
Tackling this, we (3) introduce a new efficient method of computing attention's \textit{many-to-many} RNN output based on the parallel prefix scan algorithm.
Ranked #66 on
Time Series Forecasting
on ETTh1 (336) Multivariate
no code implementations • 16 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.
no code implementations • 2 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.
1 code implementation • 20 Oct 2022 • Megha Nawhal, Akash Abdu Jyothi, Greg Mori
Action anticipation involves predicting future actions having observed the initial portion of a video.
no code implementations • 1 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.
1 code implementation • 30 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.
no code implementations • 17 May 2022 • Joao Monteiro, Mohamed Osama Ahmed, Hossein Hajimirsadeghi, Greg Mori
We study settings where gradient penalties are used alongside risk minimization with the goal of obtaining predictors satisfying different notions of monotonicity.
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.
no code implementations • 25 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.
no code implementations • 29 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.
2 code implementations • 19 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.
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.
no code implementations • 20 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.
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.
1 code implementation • 24 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.
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.
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.
no code implementations • 25 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.
no code implementations • 21 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)
1 code implementation • 8 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.
1 code implementation • 6 Jul 2020 • Xiang Xu, Megha Nawhal, Greg Mori, Manolis Savva
We present a mutual information-based framework for unsupervised image-to-image translation.
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.
no code implementations • 24 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.
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.
1 code implementation • 17 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.
no code implementations • ECCV 2020 • Megha Nawhal, Mengyao Zhai, Andreas Lehrmann, Leonid Sigal, Greg Mori
Human activity videos involve rich, varied interactions between people and objects.
no code implementations • 18 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.
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.
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.
no code implementations • 2 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.
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.
1 code implementation • 28 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.
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.
no code implementations • 25 Sep 2019 • Yu Gong, Hossein Hajimirsadeghi, JiaWei He, Megha Nawhal, Thibaut Durand, Greg Mori
Learning from only partially-observed data for imputation has been an active research area.
no code implementations • 7 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.
2 code implementations • ICCV 2019 • Akash Abdu Jyothi, Thibaut Durand, JiaWei He, Leonid Sigal, Greg Mori
Recently there is an increasing interest in scene generation within the research community.
no code implementations • ICCV 2019 • Mengyao Zhai, Lei Chen, Fred Tung, JiaWei He, Megha Nawhal, Greg Mori
This makes it possible to perform image-conditioned generation tasks in a lifelong learning setting.
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.
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.
no code implementations • CVPR 2019 • Nazanin Mehrasa, Akash Abdu Jyothi, Thibaut Durand, JiaWei He, Leonid Sigal, Greg Mori
We propose a novel probabilistic generative model for action sequences.
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.
1 code implementation • NeurIPS 2018 • Zhiwei Deng, Jiacheng Chen, Yifang Fu, Greg Mori
In this paper we address the text to scene image generation problem.
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.
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.
no code implementations • 13 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.
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.
Ranked #1 on
Semantic Object Interaction Classification
on VLOG
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.
no code implementations • 23 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.
1 code implementation • ECCV 2018 • Jiawei He, Andreas Lehrmann, Joseph Marino, Greg Mori, Leonid Sigal
Videos express highly structured spatio-temporal patterns of visual data.
1 code implementation • 18 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.
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.
no code implementations • 5 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.
no code implementations • 28 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.
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.
no code implementations • 15 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.
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.
no code implementations • 7 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.
no code implementations • 3 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.
no code implementations • 30 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.
1 code implementation • 29 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.
no code implementations • 24 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.
1 code implementation • 9 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.
no code implementations • 9 Jul 2016 • Mengyao Zhai, Mehrsan Javan Roshtkhari, Greg Mori
This paper introduces a novel deep learning based approach for vision based single target tracking.
no code implementations • ICCV 2015 • Hossein Hajimirsadeghi, Greg Mori
This paper presents HCRF-Boost, a novel and general framework for learning HCRFs in functional space.
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)
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.
no code implementations • CVPR 2016 • Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori
Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible.
no code implementations • CVPR 2016 • Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori
As a concrete example, group activity recognition involves the interactions and relative spatial relations of a set of people in a scene.
Ranked #6 on
Group Activity Recognition
on Collective Activity
1 code implementation • 21 Jul 2015 • Serena Yeung, Olga Russakovsky, Ning Jin, Mykhaylo Andriluka, Greg Mori, Li Fei-Fei
Every moment counts in action recognition.
Ranked #7 on
Action Detection
on Multi-THUMOS
no code implementations • 1 Jul 2015 • Greg Mori, Caroline Pantofaru, Nisarg Kothari, Thomas Leung, George Toderici, Alexander Toshev, Weilong Yang
We present a method for learning an embedding that places images of humans in similar poses nearby.
no code implementations • 12 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.
no code implementations • ICCV 2015 • Vignesh Ramanathan, Kevin Tang, Greg Mori, Li Fei-Fei
In this paper, we propose to learn temporal embeddings of video frames for complex video analysis.
no code implementations • 12 Feb 2015 • Mehran Khodabandeh, Arash Vahdat, Guang-Tong Zhou, Hossein Hajimirsadeghi, Mehrsan Javan Roshtkhari, Greg Mori, Stephen Se
We present a novel approach for discovering human interactions in videos.
no code implementations • CVPR 2015 • Hossein Hajimirsadeghi, Wang Yan, Arash Vahdat, Greg Mori
Many visual recognition problems can be approached by counting instances.
no code implementations • 6 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.
no code implementations • NeurIPS 2013 • Nataliya Shapovalova, Michalis Raptis, Leonid Sigal, Greg Mori
We propose a new weakly-supervised structured learning approach for recognition and spatio-temporal localization of actions in video.
no code implementations • NeurIPS 2013 • Guang-Tong Zhou, Tian Lan, Arash Vahdat, Greg Mori
We present a maximum margin framework that clusters data using latent variables.
no code implementations • 26 Sep 2013 • Hossein Hajimirsadeghi, Jinling Li, Greg Mori, Mohammad Zaki, Tarek Sayed
We introduce a graphical framework for multiple instance learning (MIL) based on Markov networks.
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.
no code implementations • CVPR 2013 • Guang-Tong Zhou, Tian Lan, Weilong Yang, Greg Mori
We conduct image classification by learning a class-toimage distance function that matches objects.
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.
no code implementations • NeurIPS 2010 • Tian Lan, Yang Wang, Weilong Yang, Greg Mori
We propose a discriminative model for recognizing group activities.
no code implementations • NeurIPS 2010 • Yang Wang, Greg Mori
In particular, we model the mapping that translates image regions to annotations.
no code implementations • NeurIPS 2009 • Yang Wang, Gholamreza Haffari, Shaojun Wang, Greg Mori
We propose a novel information theoretic approach for semi-supervised learning of conditional random fields.
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.