b'Kris Kitani'

research

∙ 05/25/2023

EgoHumans: An Egocentric 3D Multi-Human Benchmark

We present EgoHumans, a new multi-view multi-human video benchmark to ad...

0 Rawal Khirodkar, et al. ∙

research

∙ 05/22/2023

Type-to-Track: Retrieve Any Object via Prompt-based Tracking

One of the recent trends in vision problems is to use natural language c...

0 Pha Nguyen, et al. ∙

research

∙ 05/10/2023

Perpetual Humanoid Control for Real-time Simulated Avatars

We present a physics-based humanoid controller that achieves high-fideli...

1 Zhengyi Luo, et al. ∙

research

∙ 05/10/2023

Joint Metrics Matter: A Better Standard for Trajectory Forecasting

Multi-modal trajectory forecasting methods commonly evaluate using singl...

0 Erica Weng, et al. ∙

research

∙ 03/21/2023

3D-CLFusion: Fast Text-to-3D Rendering with Contrastive Latent Diffusion

We tackle the task of text-to-3D creation with pre-trained latent-based ...

0 Yu-Jhe Li, et al. ∙

research

∙ 02/23/2023

Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification

Motion-based association for Multi-Object Tracking (MOT) has recently re...

0 Gerard Maggiolino, et al. ∙

research

∙ 11/14/2022

Learnable Spatio-Temporal Map Embeddings for Deep Inertial Localization

Indoor localization systems often fuse inertial odometry with map inform...

0 Dennis Melamed, et al. ∙

research

∙ 11/12/2022

3D-Aware Encoding for Style-based Neural Radiance Fields

We tackle the task of NeRF inversion for style-based neural radiance fie...

4 Yu-Jhe Li, et al. ∙

research

∙ 10/17/2022

Track Targets by Dense Spatio-Temporal Position Encoding

In this work, we propose a novel paradigm to encode the position of targ...

0 Jinkun Cao, et al. ∙

research

∙ 10/05/2022

Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection

While recent camera-only 3D detection methods leverage multiple timestep...

0 Jinhyung Park, et al. ∙

research

∙ 03/27/2022

Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking

Multi-Object Tracking (MOT) has rapidly progressed with the development ...

20 Jinkun Cao, et al. ∙

research

∙ 03/24/2022

Occluded Human Mesh Recovery

Top-down methods for monocular human mesh recovery have two stages: (1) ...

4 Rawal Khirodkar, et al. ∙

research

∙ 11/29/2021

DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion

A typical pipeline for multi-object tracking (MOT) is to use a detector ...

11 Peize Sun, et al. ∙

research

∙ 11/25/2021

Cross-Domain Object Detection via Adaptive Self-Training

We tackle the problem of domain adaptation in object detection, where th...

4 Yu-Jhe Li, et al. ∙

research

∙ 10/21/2021

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation

Humans typically perceive the establishment of an action in a video thro...

2 Khoa Vo, et al. ∙

research

∙ 07/23/2021

Multi-Echo LiDAR for 3D Object Detection

LiDAR sensors can be used to obtain a wide range of measurement signals ...

0 Yunze Man, et al. ∙

research

∙ 07/08/2021

Multi-Modality Task Cascade for 3D Object Detection

Point clouds and RGB images are naturally complementary modalities for 3...

14 Jinhyung Park, et al. ∙

research

∙ 04/17/2021

Wide-Baseline Multi-Camera Calibration using Person Re-Identification

We address the problem of estimating the 3D pose of a network of cameras...

0 Yan Xu, et al. ∙

research

∙ 03/07/2021

Efficient Model Performance Estimation via Feature Histories

An important step in the task of neural network design, such as hyper-pa...

0 Shengcao Cao, et al. ∙

research

∙ 03/04/2021

Inverse Reinforcement Learning with Explicit Policy Estimates

Various methods for solving the inverse reinforcement learning (IRL) pro...

9 Navyata Sanghvi, et al. ∙

research

∙ 02/27/2021

DeepBLE: Generalizing RSSI-based Localization Across Different Devices

Accurate smartphone localization (< 1-meter error) for indoor navigation...

0 Harsh Agarwal, et al. ∙

research

∙ 02/08/2021

IDOL: Inertial Deep Orientation-Estimation and Localization

Many smartphone applications use inertial measurement units (IMUs) to se...

0 Scott Sun, et al. ∙

research

∙ 12/10/2020

AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking

3D multi-object tracking is an important component in robotic perception...

0 Xinshuo Weng, et al. ∙

research

∙ 11/21/2020

Rethinking Transformer-based Set Prediction for Object Detection

DETR is a recently proposed Transformer-based method which views object ...

0 Zhiqing Sun, et al. ∙

research

∙ 10/13/2020

Audio-Visual Self-Supervised Terrain Type Discovery for Mobile Platforms

The ability to both recognize and discover terrain characteristics is an...

0 Akiyoshi Kurobe, et al. ∙

research

∙ 08/22/2020

Few-Shot Learning with Intra-Class Knowledge Transfer

We consider the few-shot classification task with an unbalanced dataset,...

23 Vivek Roy, et al. ∙

research

∙ 08/20/2020

Graph Neural Networks for 3D Multi-Object Tracking

3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent ...

7 Xinshuo Weng, et al. ∙

research

∙ 08/18/2020

AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics

3D multi-object tracking (MOT) is essential to applications such as auto...

4 Xinshuo Weng, et al. ∙

research

∙ 07/27/2020

Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning

Diabetic Retinopathy (DR) is a leading cause of blindness in working age...

48 Qiqi Xiao, et al. ∙

research

∙ 06/23/2020

Joint Detection and Multi-Object Tracking with Graph Neural Networks

Object detection and data association are critical components in multi-o...

14 Yongxin Wang, et al. ∙

research

∙ 06/17/2020

When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous

We aim to enable robots to visually localize a target person through the...

6 Xi Sun, et al. ∙

research

∙ 06/12/2020

GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning

3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent ...

15 Xinshuo Weng, et al. ∙

research

∙ 06/06/2020

No-Reference Image Quality Assessment via Feature Fusion and Multi-Task Learning

Blind or no-reference image quality assessment (NR-IQA) is a fundamental...

0 S. Alireza Golestaneh, et al. ∙

research

∙ 03/18/2020

Sequential Forecasting of 100,000 Points

Predicting the future is a crucial first step to effective control, sinc...

4 Xinshuo Weng, et al. ∙

research

∙ 03/18/2020

Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting

Predicting the future is a crucial first step to effective control, sinc...

0 Xinshuo Weng, et al. ∙

research

∙ 12/12/2019

Estimating 3D Camera Pose from 2D Pedestrian Trajectories

We consider the task of re-calibrating the 3D pose of a static surveilla...

20 Yan Xu, et al. ∙

research

∙ 07/23/2019

Incremental Class Discovery for Semantic Segmentation with RGBD Sensing

This work addresses the task of open world semantic segmentation using R...

10 Yoshikatsu Nakajima, et al. ∙

research

∙ 07/11/2019

Diverse Trajectory Forecasting with Determinantal Point Processes

The ability to forecast a set of likely yet diverse possible future beha...

0 Ye Yuan, et al. ∙

research

∙ 07/09/2019

A Baseline for 3D Multi-Object Tracking

3D multi-object tracking (MOT) is an essential component technology for ...

0 Xinshuo Weng, et al. ∙

research

∙ 06/07/2019

Ego-Pose Estimation and Forecasting as Real-Time PD Control

We propose the use of a proportional-derivative (PD) control based polic...

13 Ye Yuan, et al. ∙

research

∙ 05/04/2019

Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading

We focus on the word-level visual lipreading, which requires recognizing...

0 Xinshuo Weng, et al. ∙

research

∙ 05/03/2019

PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings

For autonomous vehicles (AVs) to behave appropriately on roads populated...

0 Nicholas Rhinehart, et al. ∙

research

∙ 03/23/2019

Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud

Monocular 3D scene understanding tasks, such as object size estimation, ...

0 Xinshuo Weng, et al. ∙

research

∙ 03/04/2019

Modeling Social Group Communication with Multi-Agent Imitation Learning

In crowded social scenarios with a myriad of external stimuli, human bra...

10 Navyata Sanghvi, et al. ∙

research

∙ 11/17/2018

GroundNet: Segmentation-Aware Monocular Ground Plane Estimation with Geometric Consistency

We focus on the problem of estimating the orientation of the ground plan...

0 Yunze Man, et al. ∙

research

∙ 09/23/2018

Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection

Non-maximum suppression (NMS) is essential for state-of-the-art object d...

0 Yihui He, et al. ∙

research

∙ 09/22/2018

Shift-based Primitives for Efficient Convolutional Neural Networks

We propose a collection of three shift-based primitives for building eff...

0 Huasong Zhong, et al. ∙

research

∙ 07/30/2018

HARMONIC: A Multimodal Dataset of Assistive Human-Robot Collaboration

We present HARMONIC, a large multi-modal dataset of human interactions i...

0 Benjamin A. Newman, et al. ∙

research

∙ 07/22/2018

Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes

This paper proposes a novel method for understanding daily hand-object m...

0 Minjie Cai, et al. ∙

research

∙ 04/11/2018

Personalized Dynamics Models for Adaptive Assistive Navigation Interfaces

We explore the role of personalization for assistive navigational system...

0 Eshed Ohn-Bar, et al. ∙

Kris Kitani

Featured Co-authors