Search Results for author: Hassan Foroosh

Found 51 papers, 11 papers with code

Can Large Language Models do Analytical Reasoning?

no code implementations6 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.

Language Modelling Large Language Model

SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs

no code implementations15 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.

LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Network

no code implementations21 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.

3D Human Pose Estimation

MeetingBank: A Benchmark Dataset for Meeting Summarization

1 code implementation27 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.

Meeting Summarization

DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4

no code implementations24 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.


Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function

no code implementations24 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.

LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception

no code implementations21 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.

Decoder Multi-Task Learning +2

MobileRec: A Large-Scale Dataset for Mobile Apps Recommendation

no code implementations12 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.

Recommendation Systems

LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception

no code implementations19 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.

3D Object Detection 3D Semantic Segmentation +3

Near-Infrared Depth-Independent Image Dehazing using Haar Wavelets

no code implementations26 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.

Image Dehazing

StreamHover: Livestream Transcript Summarization and Annotation

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.

Extractive Summarization

Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation

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.

Clustering Instance Segmentation +2

Self-Attention Network for Skeleton-based Human Action Recognition

no code implementations18 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.

Action Recognition Skeleton Based Action Recognition +1

Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations

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.

Document Summarization Extractive Summarization +3

Maximum Probability Theorem: A Framework for Probabilistic Learning

no code implementations21 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 implementations25 Sep 2019 Yangyang Sun, Yang Zhang, Hassan Foroosh, Shuo Pang

Optimal sensor placement achieves the minimal cost of sensors while obtaining the prespecified objectives.

Vocal Bursts Valence Prediction

Slim-CNN: A Light-Weight CNN for Face Attribute Prediction

no code implementations3 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.


Spatio-Temporal Fusion Networks for Action Recognition

no code implementations17 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.

Action Recognition Video Classification

Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization

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.

Decoder Document Summarization +2

CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild

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.

Adversarial Attack Object

Sparse One-Time Grab Sampling of Inliers

no code implementations21 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.


ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples

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.

Image Compression

Rediscovering Deep Neural Networks Through Finite-State Distributions

no code implementations26 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.

Probabilistic Sparse Subspace Clustering Using Delayed Association

no code implementations28 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.


Simultaneous Detection and Quantification of Retinal Fluid with Deep Learning

no code implementations17 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.

Data Augmentation Decoder +1

Improving RANSAC-Based Segmentation Through CNN Encapsulation

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).

Image Segmentation Iris Recognition +2

View-Invariant Recognition of Action Style Self-Dissimilarity

no code implementations22 May 2017 Yuping Shen, Hassan Foroosh

Self-similarity was recently introduced as a measure of inter-class congruence for classification of actions.

Classification General Classification

An Invariant Model of the Significance of Different Body Parts in Recognizing Different Actions

no code implementations22 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.

Non-Linear Phase-Shifting of Haar Wavelets for Run-Time All-Frequency Lighting

no code implementations20 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.

Phase-Shifting Separable Haar Wavelets and Applications

no code implementations20 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.

Learning Semantics for Image Annotation

no code implementations15 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.

Image Retrieval Retrieval

A Closed-Form Model for Image-Based Distant Lighting

no code implementations14 May 2017 Mais Alnasser, Hassan Foroosh

In this paper, we present a new mathematical foundation for image-based lighting.

Volumetric Super-Resolution of Multispectral Data

no code implementations14 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.

Pansharpening Super-Resolution

Motion-Compensated Temporal Filtering for Critically-Sampled Wavelet-Encoded Images

no code implementations13 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.

Motion Estimation

Single Image Action Recognition by Predicting Space-Time Saliency

no code implementations12 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.

Action Classification Action Recognition +5

View-Invariant Template Matching Using Homography Constraints

no code implementations12 May 2017 Sina Lotfian, Hassan Foroosh

Change in viewpoint is one of the major factors for variation in object appearance across different images.

Object Object Recognition +1

Super-Resolution of Wavelet-Encoded Images

no code implementations3 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.

Image Reconstruction Super-Resolution

Sub-Pixel Registration of Wavelet-Encoded Images

no code implementations1 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.

Compressive Sensing Motion Compensation +1

Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial "Bottleneck" Structure

1 code implementation15 Aug 2016 Min Wang, Baoyuan Liu, Hassan Foroosh

A topological subdivisioning is adopted to reduce the connection between the input channels and output channels.

Sparse Convolutional Neural Networks

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.

Image Classification object-detection +1

SWIFT: Sparse Withdrawal of Inliers in a First Trial

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.


Feature-Independent Action Spotting Without Human Localization, Segmentation or Frame-wise Tracking

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.

Action Spotting Template Matching

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