no code implementations • CVPR 2014 • Chuan Sun, Marshall Tappen, Hassan Foroosh
To extract their internal dynamics, we devised a novel Two-Phase Decomposition (TP-Decomp) of a tensor that generates very compact and discriminative representations that are robust to even heavily perturbed data.
no code implementations • CVPR 2015 • Amara Tariq, Hassan Foroosh
Automatic image annotation is a highly valuable tool for image search, retrieval and archival systems.
no code implementations • CVPR 2015 • Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, Marianna Pensky
Deep neural networks have achieved remarkable performance in both image classification and object detection problems, at the cost of a large number of parameters and computational complexity.
no code implementations • CVPR 2015 • Maryam Jaberi, Marianna Pensky, Hassan Foroosh
We study the simultaneous detection of multiple structures in the presence of overwhelming number of outliers in a large population of points.
1 code implementation • 15 Aug 2016 • Min Wang, Baoyuan Liu, Hassan Foroosh
A topological subdivisioning is adopted to reduce the connection between the input channels and output channels.
no code implementations • 1 May 2017 • Vildan Atalay Aydin, Hassan Foroosh
In view of these new emerging needs for applications of wavelet encoded imaging, we propose a sub-pixel registration method that can achieve direct wavelet domain registration from a sparse set of coefficients.
no code implementations • 3 May 2017 • Vildan Atalay Aydin, Hassan Foroosh
We propose a novel point of view for multiview SRIR: Unlike existing multiview methods that reconstruct the entire spectrum of the HR image from the multiple given LR images, we derive explicit expressions that show how the high-frequency spectra of the unknown HR image are related to the spectra of the LR images.
no code implementations • 6 May 2017 • Amara Tariq, Hassan Foroosh
Vocabulary words are the fine labels to be associated with images.
no code implementations • 12 May 2017 • Marjaneh Safaei, Hassan Foroosh
We first map the input static image to a new domain that we refer to as the Predicted Optical Flow-Saliency Map domain (POF-SM), and then fine-tune the layers of a deep CNN model trained on classifying the ImageNet dataset to perform action classification in the POF-SM domain.
no code implementations • 12 May 2017 • Sina Lotfian, Hassan Foroosh
Change in viewpoint is one of the major factors for variation in object appearance across different images.
no code implementations • 13 May 2017 • Vildan Atalay Aydin, Hassan Foroosh
We propose a novel motion estimation/compensation (ME/MC) method for wavelet-based (in-band) motion compensated temporal filtering (MCTF), with application to low-bitrate video coding.
no code implementations • 14 May 2017 • Mais Alnasser, Hassan Foroosh
In this paper, we present a new mathematical foundation for image-based lighting.
no code implementations • 14 May 2017 • Vildan Atalay Aydin, Hassan Foroosh
In order to reconstruct a high-spatial/high-spectral resolution multispectral image volume, either the information in MS and PAN images are fused (i. e. pansharpening) or super-resolution reconstruction (SRR) is used with only MS images captured on different dates.
no code implementations • 15 May 2017 • Amara Tariq, Hassan Foroosh
Image search and retrieval engines rely heavily on textual annotation in order to match word queries to a set of candidate images.
no code implementations • 20 May 2017 • Mais Alnasser, Hassan Foroosh
At the root of all the above problems is the lack of efficient run-time solution to the nontrivial problem of rotating wavelets (a non-linear phase-shift), which we solve in this paper.
no code implementations • 20 May 2017 • Mais Alnasser, Hassan Foroosh
First, we derive closed form expressions for phase shifting in the Haar domain both in partially decimated and fully decimated transforms.
no code implementations • 22 May 2017 • Yuping Shen, Hassan Foroosh
In this paper, we show that different body parts do not play equally important roles in recognizing a human action in video data.
no code implementations • 22 May 2017 • Yuping Shen, Hassan Foroosh
Self-similarity was recently introduced as a measure of inter-class congruence for classification of actions.
no code implementations • CVPR 2017 • Dustin Morley, Hassan Foroosh
In this work, we present a method for improving a random sample consensus (RANSAC) based image segmentation algorithm by encapsulating it within a convolutional neural network (CNN).
no code implementations • 17 Aug 2017 • Dustin Morley, Hassan Foroosh, Saad Shaikh, Ulas Bagci
We propose a new deep learning approach for automatic detection and segmentation of fluid within retinal OCT images.
no code implementations • 28 Aug 2018 • Maryam Jaberi, Marianna Pensky, Hassan Foroosh
(ii) We demonstrate that delayed association is better suited for clustering subspaces that have ambiguities, i. e. when subspaces intersect or data are contaminated with outliers/noise.
no code implementations • 26 Sep 2018 • Amir Emad Marvasti, Ehsan Emad Marvasti, George Atia, Hassan Foroosh
We propose a new way of thinking about deep neural networks, in which the linear and non-linear components of the network are naturally derived and justified in terms of principles in probability theory.
1 code implementation • CVPR 2019 • Xiaojun Jia, Xingxing Wei, Xiaochun Cao, Hassan Foroosh
In other words, ComDefend can transform the adversarial image to its clean version, which is then fed to the trained classifier.
no code implementations • 21 Dec 2018 • Maryam Jaberi, Marianna Pensky, Hassan Foroosh
One of the main approaches that is explored in the literature to tackle the problems of size and dimensionality is sampling subsets of the data in order to estimate the characteristics of the whole population, e. g. estimating the underlying clusters or structures in the data.
2 code implementations • 24 Dec 2018 • Yang Zhang, Philip David, Hassan Foroosh, Boqing Gong
Hence, we propose a curriculum-style learning approach to minimizing the domain gap in urban scene semantic segmentation.
Ranked #26 on Image-to-Image Translation on SYNTHIA-to-Cityscapes
1 code implementation • ICLR 2019 • Yang Zhang, Hassan Foroosh, Philip David, Boqing Gong
In particular, we learn a camouflage pattern to hide vehicles from being detected by state-of-the-art convolutional neural network based detectors.
1 code implementation • ACL 2019 • Sangwoo Cho, Logan Lebanoff, Hassan Foroosh, Fei Liu
The most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data.
no code implementations • 17 Jun 2019 • Sangwoo Cho, Hassan Foroosh
The video based CNN works have focused on effective ways to fuse appearance and motion networks, but they typically lack utilizing temporal information over video frames.
no code implementations • 17 Jun 2019 • Sangwoo Cho, Hassan Foroosh
The words are then combined into a sentence to represent the video, as a sentence.
no code implementations • 3 Jul 2019 • Ankit Sharma, Hassan Foroosh
We introduce a computationally-efficient CNN micro-architecture Slim Module to design a lightweight deep neural network Slim-Net for face attribute prediction.
no code implementations • 25 Sep 2019 • Yangyang Sun, Yang Zhang, Hassan Foroosh, Shuo Pang
Optimal sensor placement achieves the minimal cost of sensors while obtaining the prespecified objectives.
no code implementations • 21 Oct 2019 • Amir Emad Marvasti, Ehsan Emad Marvasti, Ulas Bagci, Hassan Foroosh
Instead, the regularizing effects of assuming prior over parameters is seen through maximizing probabilities of models or according to information theory, minimizing the information content of a model.
no code implementations • WS 2019 • Sangwoo Cho, Chen Li, Dong Yu, Hassan Foroosh, Fei Liu
Emerged as one of the best performing techniques for extractive summarization, determinantal point processes select the most probable set of sentences to form a summary according to a probability measure defined by modeling sentence prominence and pairwise repulsion.
no code implementations • 18 Dec 2019 • Sangwoo Cho, Muhammad Hasan Maqbool, Fei Liu, Hassan Foroosh
In order to come up with a better representation and capturing of long term spatio-temporal relationships, we propose three variants of Self-Attention Network (SAN), namely, SAN-V1, SAN-V2 and SAN-V3.
Ranked #61 on Skeleton Based Action Recognition on NTU RGB+D
4 code implementations • CVPR 2020 • Yang Zhang, Zixiang Zhou, Philip David, Xiangyu Yue, Zerong Xi, Boqing Gong, Hassan Foroosh
The need for fine-grained perception in autonomous driving systems has resulted in recently increased research on online semantic segmentation of single-scan LiDAR.
Ranked #11 on Robust 3D Semantic Segmentation on nuScenes-C
no code implementations • 19 Aug 2020 • Shengnan Hu, Yang Zhang, Sumit Laha, Ankit Sharma, Hassan Foroosh
Deep neural network based object detection hasbecome the cornerstone of many real-world applications.
1 code implementation • EMNLP 2020 • Sangwoo Cho, Kaiqiang Song, Chen Li, Dong Yu, Hassan Foroosh, Fei Liu
Amongst the best means to summarize is highlighting.
2 code implementations • CVPR 2021 • Zixiang Zhou, Yang Zhang, Hassan Foroosh
Panoptic segmentation presents a new challenge in exploiting the merits of both detection and segmentation, with the aim of unifying instance segmentation and semantic segmentation in a single framework.
1 code implementation • EMNLP 2021 • Sangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui, Nedim Lipka, Walter Chang, Hailin Jin, Jonathan Brandt, Hassan Foroosh, Fei Liu
With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge.
no code implementations • 26 Mar 2022 • Sumit Laha, Ankit Sharma, Shengnan Hu, Hassan Foroosh
We propose a fusion algorithm for haze removal that combines color information from an RGB image and edge information extracted from its corresponding NIR image using Haar wavelets.
no code implementations • 23 Jun 2022 • Dongqiangzi Ye, Weijia Chen, Zixiang Zhou, Yufei Xie, Yu Wang, Panqu Wang, Hassan Foroosh
This technical report presents the 1st place winning solution for the Waymo Open Dataset 3D semantic segmentation challenge 2022.
1 code implementation • 12 Sep 2022 • Zixiang Zhou, Xiangchen Zhao, Yu Wang, Panqu Wang, Hassan Foroosh
It then uses the feature of the center candidate as the query embedding in the transformer.
Ranked #2 on 3D Object Detection on waymo cyclist
no code implementations • 19 Sep 2022 • Dongqiangzi Ye, Zixiang Zhou, Weijia Chen, Yufei Xie, Yu Wang, Panqu Wang, Hassan Foroosh
LidarMultiNet is extensively tested on both Waymo Open Dataset and nuScenes dataset, demonstrating for the first time that major LiDAR perception tasks can be unified in a single strong network that is trained end-to-end and achieves state-of-the-art performance.
no code implementations • 12 Mar 2023 • M. H. Maqbool, Umar Farooq, Adib Mosharrof, A. B. Siddique, Hassan Foroosh
To facilitate research for app recommendation systems, we introduce a large-scale dataset, called MobileRec.
no code implementations • 21 Mar 2023 • Zixiang Zhou, Dongqiangzi Ye, Weijia Chen, Yufei Xie, Yu Wang, Panqu Wang, Hassan Foroosh
The proposed LiDARFormer utilizes cross-space global contextual feature information and exploits cross-task synergy to boost the performance of LiDAR perception tasks across multiple large-scale datasets and benchmarks.
no code implementations • 24 Mar 2023 • A. B. Siddique, M. H. Maqbool, Kshitija Taywade, Hassan Foroosh
In this work, we propose a novel framework, P-ToD, to personalize task-oriented dialog systems capable of adapting to a wide range of user profiles in an unsupervised fashion using a zero-shot generalizable reward function.
no code implementations • 24 May 2023 • Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Fei Liu
Human preference judgments are pivotal in guiding large language models (LLMs) to produce outputs that align with human values.
1 code implementation • 27 May 2023 • Yebowen Hu, Tim Ganter, Hanieh Deilamsalehy, Franck Dernoncourt, Hassan Foroosh, Fei Liu
However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential.
no code implementations • 21 Jun 2023 • Dongqiangzi Ye, Yufei Xie, Weijia Chen, Zixiang Zhou, Lingting Ge, Hassan Foroosh
Due to the difficulty of acquiring large-scale 3D human keypoint annotation, previous methods for 3D human pose estimation (HPE) have often relied on 2D image features and sequential 2D annotations.
no code implementations • 15 Feb 2024 • Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Dong Yu, Fei Liu
In this paper, we introduce four novel tasks centered around sports data analytics to evaluate the numerical reasoning and information fusion capabilities of LLMs.
no code implementations • 6 Mar 2024 • Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Dong Yu, Fei Liu
Our analytical reasoning embodies the tasks of letting large language models count how many points each team scores in a quarter in the NBA and NFL games.