Search Results for author: Hamid Rezatofighi

Found 34 papers, 14 papers with code

Tracking Different Ant Species: An Unsupervised Domain Adaptation Framework and a Dataset for Multi-object Tracking

no code implementations25 Jan 2023 Chamath Abeysinghe, Chris Reid, Hamid Rezatofighi, Bernd Meyer

This approach is built upon a joint-detection-and-tracking framework that is extended by a set of domain discriminator modules integrating an adversarial training strategy in addition to the tracking loss.

Multi-Object Tracking Unsupervised Domain Adaptation

Predicting Topological Maps for Visual Navigation in Unexplored Environments

no code implementations23 Nov 2022 Huangying Zhan, Hamid Rezatofighi, Ian Reid

We propose a robotic learning system for autonomous exploration and navigation in unexplored environments.

Visual Navigation

ActiveRMAP: Radiance Field for Active Mapping And Planning

no code implementations23 Nov 2022 Huangying Zhan, Jiyang Zheng, Yi Xu, Ian Reid, Hamid Rezatofighi

We, for the first time, present an RGB-only active vision framework using radiance field representation for active 3D reconstruction and planning in an online manner.

3D Reconstruction

MARLIN: Masked Autoencoder for facial video Representation LearnINg

1 code implementation12 Nov 2022 Zhixi Cai, Shreya Ghosh, Kalin Stefanov, Abhinav Dhall, Jianfei Cai, Hamid Rezatofighi, Reza Haffari, Munawar Hayat

This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS).

DeepFake Detection Face Swapping +5

Unifying Flow, Stereo and Depth Estimation

1 code implementation10 Nov 2022 Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Fisher Yu, DaCheng Tao, Andreas Geiger

We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed images.

Optical Flow Estimation Stereo Depth Estimation +1

JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking

no code implementations20 Oct 2022 Edward Vendrow, Duy Tho Le, Jianfei Cai, Hamid Rezatofighi

In crowded human scenes with close-up human-robot interaction and robot navigation, a deep understanding requires reasoning about human motion and body dynamics over time with human body pose estimation and tracking.

Multi-Person Pose Estimation Multi-Person Pose Estimation and Tracking +1

SoMoFormer: Multi-Person Pose Forecasting with Transformers

1 code implementation30 Aug 2022 Edward Vendrow, Satyajit Kumar, Ehsan Adeli, Hamid Rezatofighi

Although there are several previous works targeting the problem of multi-person dynamic pose forecasting, they often model the entire pose sequence as time series (ignoring the underlying relationship between joints) or only output the future pose sequence of one person at a time.

Human Pose Forecasting motion prediction +1

Learning of Global Objective for Network Flow in Multi-Object Tracking

no code implementations CVPR 2022 Shuai Li, Yu Kong, Hamid Rezatofighi

This paper concerns the problem of multi-object tracking based on the min-cost flow (MCF) formulation, which is conventionally studied as an instance of linear program.

Association Multi-Object Tracking

Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network

1 code implementation31 Dec 2021 Duy-Tho Le, Hengcan Shi, Hamid Rezatofighi, Jianfei Cai

Efficiently and accurately detecting people from 3D point cloud data is of great importance in many robotic and autonomous driving applications.

3D Object Detection Autonomous Driving +3

GMFlow: Learning Optical Flow via Global Matching

2 code implementations CVPR 2022 Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, DaCheng Tao

Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements.

Optical Flow Estimation regression

Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables

no code implementations12 Oct 2021 Alireza Abedin, Hamid Rezatofighi, Damith C. Ranasinghe

Human activity recognition (HAR) is an important research field in ubiquitous computing where the acquisition of large-scale labeled sensor data is tedious, labor-intensive and time consuming.

Human Activity Recognition Representation Learning

ODAM: Object Detection, Association, and Mapping using Posed RGB Video

1 code implementation ICCV 2021 Kejie Li, Daniel DeTone, Steven Chen, Minh Vo, Ian Reid, Hamid Rezatofighi, Chris Sweeney, Julian Straub, Richard Newcombe

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics.

3D Object Detection Association +2

Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization

no code implementations1 Jul 2021 S. Ehsan Mirsadeghi, Ali Royat, Hamid Rezatofighi

In this paper, we propose a novel fully unsupervised semantic segmentation method, the so-called Information Maximization and Adversarial Regularization Segmentation (InMARS).

Image Segmentation Scene Understanding +3

JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection

no code implementations CVPR 2022 Mahsa Ehsanpour, Fatemeh Saleh, Silvio Savarese, Ian Reid, Hamid Rezatofighi

However, learning to recognise human actions and their social interactions in an unconstrained real-world environment comprising numerous people, with potentially highly unbalanced and long-tailed distributed action labels from a stream of sensory data captured from a mobile robot platform remains a significant challenge, not least owing to the lack of a reflective large-scale dataset.

Action Detection Action Understanding +1

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

no code implementations ICCV 2021 Vida Adeli, Mahsa Ehsanpour, Ian Reid, Juan Carlos Niebles, Silvio Savarese, Ehsan Adeli, Hamid Rezatofighi

Joint forecasting of human trajectory and pose dynamics is a fundamental building block of various applications ranging from robotics and autonomous driving to surveillance systems.

Autonomous Driving Human-Object Interaction Detection

Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers

1 code implementation27 Mar 2021 Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom Drummond, Ian Reid, Hamid Rezatofighi

Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.

Association Multi-Object Tracking +1

MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos

no code implementations9 Dec 2020 Kejie Li, Hamid Rezatofighi, Ian Reid

Given a new RGB frame, MOLTR firstly applies a monocular 3D detector to localise objects of interest and extract their shape codes that represent the object shapes in a learned embedding space.

Association Benchmarking +1

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

no code implementations CVPR 2021 Fatemeh Saleh, Sadegh Aliakbarian, Hamid Rezatofighi, Mathieu Salzmann, Stephen Gould

Despite the recent advances in multiple object tracking (MOT), achieved by joint detection and tracking, dealing with long occlusions remains a challenge.

Multiple Object Tracking

How Trustworthy are Performance Evaluations for Basic Vision Tasks?

no code implementations8 Aug 2020 Tran Thien Dat Nguyen, Hamid Rezatofighi, Ba-Ngu Vo, Ba-Tuong Vo, Silvio Savarese, Ian Reid

This paper examines performance evaluation criteria for basic vision tasks involving sets of objects namely, object detection, instance-level segmentation and multi-object tracking.

Multi-Object Tracking object-detection +1

Socially and Contextually Aware Human Motion and Pose Forecasting

no code implementations14 Jul 2020 Vida Adeli, Ehsan Adeli, Ian Reid, Juan Carlos Niebles, Hamid Rezatofighi

In this paper, we propose a novel framework to tackle both tasks of human motion (or trajectory) and body skeleton pose forecasting in a unified end-to-end pipeline.

Human Dynamics Robot Navigation

Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensors

no code implementations14 Jul 2020 Alireza Abedin, Mahsa Ehsanpour, Qinfeng Shi, Hamid Rezatofighi, Damith C. Ranasinghe

Wearables are fundamental to improving our understanding of human activities, especially for an increasing number of healthcare applications from rehabilitation to fine-grained gait analysis.

Human Activity Recognition

Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos

no code implementations ECCV 2020 Mahsa Ehsanpour, Alireza Abedin, Fatemeh Saleh, Javen Shi, Ian Reid, Hamid Rezatofighi

In this paper, we solve the problem of simultaneously grouping people by their social interactions, predicting their individual actions and the social activity of each social group, which we call the social task.

Group Activity Recognition

MOT20: A benchmark for multi object tracking in crowded scenes

1 code implementation19 Mar 2020 Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, Laura Leal-Taixé

The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods.

Multi-Object Tracking Multiple Object Tracking with Transformer +1

JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset

1 code implementation19 Feb 2020 Abhijeet Shenoi, Mihir Patel, JunYoung Gwak, Patrick Goebel, Amir Sadeghian, Hamid Rezatofighi, Roberto Martín-Martín, Silvio Savarese

In this work we present JRMOT, a novel 3D MOT system that integrates information from RGB images and 3D point clouds to achieve real-time, state-of-the-art tracking performance.

Association Autonomous Navigation +3

Learn to Predict Sets Using Feed-Forward Neural Networks

no code implementations30 Jan 2020 Hamid Rezatofighi, Tianyu Zhu, Roman Kaskman, Farbod T. Motlagh, Qinfeng Shi, Anton Milan, Daniel Cremers, Laura Leal-Taixé, Ian Reid

In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality.

Multi-Label Image Classification object-detection +1

Approximating the Permanent by Sampling from Adaptive Partitions

1 code implementation NeurIPS 2019 Jonathan Kuck, Tri Dao, Hamid Rezatofighi, Ashish Sabharwal, Stefano Ermon

Computing the permanent of a non-negative matrix is a core problem with practical applications ranging from target tracking to statistical thermodynamics.

Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression

10 code implementations CVPR 2019 Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese

By incorporating this generalized $IoU$ ($GIoU$) as a loss into the state-of-the art object detection frameworks, we show a consistent improvement on their performance using both the standard, $IoU$ based, and new, $GIoU$ based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.

object-detection Object Detection +1

Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes

no code implementations12 Jan 2019 Yu Liu, Lingqiao Liu, Hamid Rezatofighi, Thanh-Toan Do, Qinfeng Shi, Ian Reid

As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years.

object-detection Object Detection

TrackerBots: Software in the Loop Study of Quad-Copter Robots for Locating Radio-tags in a 3D Space

1 code implementation1 Dec 2018 Hoa Van Nguyen, Hamid Rezatofighi, David Taggart, Bertram Ostendorf, Damith C. Ranasinghe

We investigate the problem of tracking and planning for a UAV in a task to locate multiple radio-tagged wildlife in a three-dimensional (3D) setting in the context of our TrackerBots research project.

Management TAG

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