Search Results for author: Naiyan Wang

Found 60 papers, 43 papers with code

TSTTC: A Large-Scale Dataset for Time-to-Contact Estimation in Driving Scenarios

1 code implementation4 Sep 2023 Yuheng Shi, Zehao Huang, Yan Yan, Naiyan Wang, Xiaojie Guo

Time-to-Contact (TTC) estimation is a critical task for assessing collision risk and is widely used in various driver assistance and autonomous driving systems.

Autonomous Driving Neural Rendering

FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels

2 code implementations7 Aug 2023 Lue Fan, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

Consequently, we develop a suite of components to complement the virtual voxel concept, including a virtual voxel encoder, a virtual voxel mixer, and a virtual voxel assignment strategy.

3D Object Detection Clustering +4

Frame Fusion with Vehicle Motion Prediction for 3D Object Detection

no code implementations19 Jun 2023 Xirui Li, Feng Wang, Naiyan Wang, Chao Ma

To ''forward'' frames, we use vehicle motion models to estimate the future pose of the bounding boxes.

3D Object Detection Future prediction +3

Tracking Objects with 3D Representation from Videos

no code implementations8 Jun 2023 JiaWei He, Lue Fan, Yuqi Wang, Yuntao Chen, Zehao Huang, Naiyan Wang, Zhaoxiang Zhang

In this paper, we rethink the data association in 2D MOT and utilize the 3D object representation to separate each object in the feature space.

Multiple Object Tracking Object +1

Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection

2 code implementations ICCV 2023 Lue Fan, Yuxue Yang, Yiming Mao, Feng Wang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang

Drawing inspiration from this, we propose a high-performance offline detector in a track-centric perspective instead of the conventional object-centric perspective.

3D Object Detection Object +1

Fully Sparse Fusion for 3D Object Detection

1 code implementation24 Apr 2023 Yingyan Li, Lue Fan, Yang Liu, Zehao Huang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang, Tieniu Tan

In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture.

3D Instance Segmentation 3D Object Detection +3

Learnable Graph Matching: A Practical Paradigm for Data Association

1 code implementation27 Mar 2023 JiaWei He, Zehao Huang, Naiyan Wang, Zhaoxiang Zhang

Data association is at the core of many computer vision tasks, e. g., multiple object tracking, image matching, and point cloud registration.

Graph Matching Multiple Object Tracking +1

Deep Planar Parallax for Monocular Depth Estimation

no code implementations9 Jan 2023 Haoqian Liang, Zhichao Li, Ya Yang, Naiyan Wang

Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation.

Autonomous Driving Depth Prediction +2

Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection

1 code implementation CVPR 2023 Shaofei Huang, Zhenwei Shen, Zehao Huang, Zi-han Ding, Jiao Dai, Jizhong Han, Naiyan Wang, Si Liu

An attempt has been made to get rid of BEV and predict 3D lanes from FV representations directly, while it still underperforms other BEV-based methods given its lack of structured representation for 3D lanes.

3D Lane Detection

Object as Query: Lifting any 2D Object Detector to 3D Detection

1 code implementation ICCV 2023 Zitian Wang, Zehao Huang, Jiahui Fu, Naiyan Wang, Si Liu

Existing methods mainly establish 3D representations from multi-view images and adopt a dense detection head for object detection, or employ object queries distributed in 3D space to localize objects.

3D Object Detection Object +1

Super Sparse 3D Object Detection

2 code implementations5 Jan 2023 Lue Fan, Yuxue Yang, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

To enable efficient long-range detection, we first propose a fully sparse object detector termed FSD.

3D Object Detection Autonomous Driving +2

PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework

no code implementations26 Oct 2022 Liuchun Yuan, Zehao Huang, Naiyan Wang

In this paper, we present a general and effective framework for Neural Architecture Search (NAS), named PredNAS.

Neural Architecture Search

YOLOV: Making Still Image Object Detectors Great at Video Object Detection

1 code implementation20 Aug 2022 Yuheng Shi, Naiyan Wang, Xiaojie Guo

On the positive side, the detection in a certain frame of a video, compared with that in a still image, can draw support from other frames.

Object object-detection +1

Fully Sparse 3D Object Detection

4 code implementations20 Jul 2022 Lue Fan, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

To enable efficient long-range LiDAR-based object detection, we build a fully sparse 3D object detector (FSD).

3D Object Detection Autonomous Driving +1

GIFS: Neural Implicit Function for General Shape Representation

1 code implementation CVPR 2022 Jianglong Ye, Yuntao Chen, Naiyan Wang, Xiaolong Wang

This limitation leads to tedious data processing (converting non-watertight raw data to watertight) as well as the incapability of representing general object shapes in the real world.

3D Shape Reconstruction

Embracing Single Stride 3D Object Detector with Sparse Transformer

2 code implementations CVPR 2022 Lue Fan, Ziqi Pang, Tianyuan Zhang, Yu-Xiong Wang, Hang Zhao, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases.

3D Object Detection Autonomous Driving +3

Immortal Tracker: Tracklet Never Dies

1 code implementation26 Nov 2021 Qitai Wang, Yuntao Chen, Ziqi Pang, Naiyan Wang, Zhaoxiang Zhang

We employ a simple Kalman filter for trajectory prediction and preserve the tracklet by prediction when the target is not visible.

3D Multi-Object Tracking Trajectory Prediction

Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild

1 code implementation24 Nov 2021 Jianglong Ye, Yuntao Chen, Naiyan Wang, Xiaolong Wang

Tracking and reconstructing 3D objects from cluttered scenes are the key components for computer vision, robotics and autonomous driving systems.

3D Shape Reconstruction Autonomous Driving +1

SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking

2 code implementations18 Nov 2021 Ziqi Pang, Zhichao Li, Naiyan Wang

3D multi-object tracking (MOT) has witnessed numerous novel benchmarks and approaches in recent years, especially those under the "tracking-by-detection" paradigm.

3D Multi-Object Tracking Management +1

Unsupervised Scale-consistent Depth Learning from Video

2 code implementations25 May 2021 Jia-Wang Bian, Huangying Zhan, Naiyan Wang, Zhichao Li, Le Zhang, Chunhua Shen, Ming-Ming Cheng, Ian Reid

We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time.

Monocular Depth Estimation Monocular Visual Odometry +1

Direct Differentiable Augmentation Search

1 code implementation ICCV 2021 Aoming Liu, Zehao Huang, Zhiwu Huang, Naiyan Wang

Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and datasets.

AutoML Data Augmentation +4

LiDAR R-CNN: An Efficient and Universal 3D Object Detector

1 code implementation CVPR 2021 Zhichao Li, Feng Wang, Naiyan Wang

LiDAR-based 3D detection in point cloud is essential in the perception system of autonomous driving.

Autonomous Driving

RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection

1 code implementation18 Mar 2021 Lue Fan, Xuan Xiong, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

The most notable difference with previous works is that our method is purely based on the range view representation.

3D Object Detection object-detection +2

QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection

1 code implementation CVPR 2022 Chenhongyi Yang, Zehao Huang, Naiyan Wang

On the popular COCO dataset, the proposed method improves the detection mAP by 1. 0 and mAP-small by 2. 0, and the high-resolution inference speed is improved to 3. 0x on average.

object-detection Small Object Detection +1

Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences

4 code implementations10 Mar 2021 Ziqi Pang, Zhichao Li, Naiyan Wang

The code and protocols for our benchmark and algorithm are available at https://github. com/TuSimple/LiDAR_SOT/.

Autonomous Driving Multi-Object Tracking +2

RangeDet: In Defense of Range View for LiDAR-Based 3D Object Detection

1 code implementation ICCV 2021 Lue Fan, Xuan Xiong, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

We first analyze the existing range-view-based methods and find two issues overlooked by previous works: 1) the scale variation between nearby and far away objects; 2) the inconsistency between the 2D range image coordinates used in feature extraction and the 3D Cartesian coordinates used in output.

3D Object Detection object-detection +2

1st Place Solutions of Waymo Open Dataset Challenge 2020 -- 2D Object Detection Track

1 code implementation4 Aug 2020 Zehao Huang, Zehui Chen, Qiaofei Li, Hongkai Zhang, Naiyan Wang

In this technical report, we present our solutions of Waymo Open Dataset (WOD) Challenge 2020 - 2D Object Track.

Object object-detection +1

Auto-Rectify Network for Unsupervised Indoor Depth Estimation

1 code implementation4 Jun 2020 Jia-Wang Bian, Huangying Zhan, Naiyan Wang, Tat-Jun Chin, Chunhua Shen, Ian Reid

However, excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices.

Monocular Depth Estimation Self-Supervised Learning +1

UST: Unifying Spatio-Temporal Context for Trajectory Prediction in Autonomous Driving

no code implementations6 May 2020 Hao He, Hengchen Dai, Naiyan Wang

In contrast to existing methods which heavily rely on recurrent neural network for temporal context and hand-crafted structure for spatial context, our method could automatically partition the spatio-temporal space to adapt the data.

Autonomous Driving Trajectory Prediction

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

3 code implementations ECCV 2020 Hongkai Zhang, Hong Chang, Bingpeng Ma, Naiyan Wang, Xilin Chen

For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors.

object-detection Object Detection +2

DMLO: Deep Matching LiDAR Odometry

no code implementations8 Apr 2020 Zhichao Li, Naiyan Wang

LiDAR odometry is a fundamental task for various areas such as robotics, autonomous driving.

Autonomous Driving Pose Estimation

Cross View Fusion for 3D Human Pose Estimation

1 code implementation ICCV 2019 Haibo Qiu, Chunyu Wang, Jingdong Wang, Naiyan Wang, Wen-Jun Zeng

It consists of two separate steps: (1) estimating the 2D poses in multi-view images and (2) recovering the 3D poses from the multi-view 2D poses.

2D Pose Estimation 3D Human Pose Estimation +1

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

2 code implementations NeurIPS 2019 Jia-Wang Bian, Zhichao Li, Naiyan Wang, Huangying Zhan, Chunhua Shen, Ming-Ming Cheng, Ian Reid

To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.

Depth And Camera Motion Monocular Depth Estimation +1

Revisiting Feature Alignment for One-stage Object Detection

no code implementations5 Aug 2019 Yuntao Chen, Chenxia Han, Naiyan Wang, Zhao-Xiang Zhang

Recently, one-stage object detectors gain much attention due to their simplicity in practice.

Object object-detection +2

Sequence Level Semantics Aggregation for Video Object Detection

2 code implementations ICCV 2019 Haiping Wu, Yuntao Chen, Naiyan Wang, Zhao-Xiang Zhang

In this work, we argue that aggregating features in the full-sequence level will lead to more discriminative and robust features for video object detection.

Clustering Object +4

Single Shot Neural Architecture Search Via Direct Sparse Optimization

no code implementations ICLR 2019 Xinbang Zhang, Zehao Huang, Naiyan Wang

Recently Neural Architecture Search (NAS) has aroused great interest in both academia and industry, however it remains challenging because of its huge and non-continuous search space.

Neural Architecture Search Test

Scale-Aware Trident Networks for Object Detection

4 code implementations ICCV 2019 Yanghao Li, Yuntao Chen, Naiyan Wang, Zhao-Xiang Zhang

In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection.

Object object-detection +1

Spectral Feature Transformation for Person Re-identification

2 code implementations ICCV 2019 Chuanchen Luo, Yuntao Chen, Naiyan Wang, Zhao-Xiang Zhang

With the surge of deep learning techniques, the field of person re-identification has witnessed rapid progress in recent years.

Clustering Person Re-Identification

You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization

1 code implementation5 Nov 2018 Xinbang Zhang, Zehao Huang, Naiyan Wang

Recently Neural Architecture Search (NAS) has aroused great interest in both academia and industry, however it remains challenging because of its huge and non-continuous search space.

Neural Architecture Search Test

Multi-shot Pedestrian Re-identification via Sequential Decision Making

no code implementations CVPR 2018 Jianfu Zhang, Naiyan Wang, Liqing Zhang

In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we propose an interpretable reinforcement learning based approach to this problem.

Decision Making Time Series +1

Like What You Like: Knowledge Distill via Neuron Selectivity Transfer

1 code implementation ICLR 2019 Zehao Huang, Naiyan Wang

In this paper, we propose a novel knowledge transfer method by treating it as a distribution matching problem.

object-detection Object Detection +1

DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer

no code implementations5 Jul 2017 Yuntao Chen, Naiyan Wang, Zhao-Xiang Zhang

have shown that the dark knowledge within a powerful teacher model can significantly help the training of a smaller and faster student network.

Clustering Image Clustering +6

Data-Driven Sparse Structure Selection for Deep Neural Networks

2 code implementations ECCV 2018 Zehao Huang, Naiyan Wang

Deep convolutional neural networks have liberated its extraordinary power on various tasks.

Demystifying Neural Style Transfer

3 code implementations4 Jan 2017 Yanghao Li, Naiyan Wang, Jiaying Liu, Xiaodi Hou

Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry.

Domain Adaptation Style Transfer

On The Stability of Video Detection and Tracking

no code implementations20 Nov 2016 Hong Zhang, Naiyan Wang

Lastly, based on this metric, we evaluate several existing methods for video detection and show how they affect accuracy and stability.

Factorized Bilinear Models for Image Recognition

1 code implementation ICCV 2017 Yanghao Li, Naiyan Wang, Jiaying Liu, Xiaodi Hou

Although Deep Convolutional Neural Networks (CNNs) have liberated their power in various computer vision tasks, the most important components of CNN, convolutional layers and fully connected layers, are still limited to linear transformations.

Revisiting Batch Normalization For Practical Domain Adaptation

1 code implementation15 Mar 2016 Yanghao Li, Naiyan Wang, Jianping Shi, Jiaying Liu, Xiaodi Hou

However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain.

Domain Adaptation Image Classification +2

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

2 code implementations3 Dec 2015 Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, Zheng Zhang

This paper describes both the API design and the system implementation of MXNet, and explains how embedding of both symbolic expression and tensor operation is handled in a unified fashion.

BIG-bench Machine Learning Clustering +2

DevNet: A Deep Event Network for Multimedia Event Detection and Evidence Recounting

no code implementations CVPR 2015 Chuang Gan, Naiyan Wang, Yi Yang, Dit-yan Yeung, Alex G. Hauptmann

Taking key frames of videos as input, we first detect the event of interest at the video level by aggregating the CNN features of the key frames.

Action Recognition Event Detection +2

Bayesian Adaptive Matrix Factorization With Automatic Model Selection

no code implementations CVPR 2015 Peixian Chen, Naiyan Wang, Nevin L. Zhang, Dit-yan Yeung

Low-rank matrix factorization has long been recognized as a fundamental problem in many computer vision applications.

Model Selection

Empirical Evaluation of Rectified Activations in Convolutional Network

2 code implementations5 May 2015 Bing Xu, Naiyan Wang, Tianqi Chen, Mu Li

In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear unit (PReLU) and a new randomized leaky rectified linear units (RReLU).

General Classification Image Classification +1

Understanding and Diagnosing Visual Tracking Systems

no code implementations ICCV 2015 Naiyan Wang, Jianping Shi, Dit-yan Yeung, Jiaya Jia

Surprisingly, our findings are discrepant with some common beliefs in the visual tracking research community.

Visual Tracking

Transferring Rich Feature Hierarchies for Robust Visual Tracking

no code implementations19 Jan 2015 Naiyan Wang, Siyi Li, Abhinav Gupta, Dit-yan Yeung

To fit the characteristics of object tracking, we first pre-train the CNN to recognize what is an object, and then propose to generate a probability map instead of producing a simple class label.

Image Classification Object +4

Collaborative Deep Learning for Recommender Systems

1 code implementation10 Sep 2014 Hao Wang, Naiyan Wang, Dit-yan Yeung

(CF-based) input and propose in this paper a hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix.

Collaborative Filtering Recommendation Systems +1

Learning a Deep Compact Image Representation for Visual Tracking

no code implementations NeurIPS 2013 Naiyan Wang, Dit-yan Yeung

In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background.

Denoising General Classification +3

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