Search Results for author: Xiaodong Yang

Found 51 papers, 25 papers with code

UFO²: A Unified Framework towards Omni-supervised Object Detection

1 code implementation ECCV 2020 Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, Alexander G. Schwing, Jan Kautz

Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive image-level tags.

Object object-detection +1

Fundamental limits of community detection from multi-view data: multi-layer, dynamic and partially labeled block models

no code implementations16 Jan 2024 Xiaodong Yang, Buyu Lin, Subhabrata Sen

Multi-view data arises frequently in modern network analysis e. g. relations of multiple types among individuals in social network analysis, longitudinal measurements of interactions among observational units, annotated networks with noisy partial labeling of vertices etc.

Community Detection Stochastic Block Model

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation

1 code implementation ICCV 2023 Zeyu Wang, Dingwen Li, Chenxu Luo, Cihang Xie, Xiaodong Yang

In this work, we propose to boost the representation learning of a multi-camera BEV based student detector by training it to imitate the features of a well-trained LiDAR based teacher detector.

3D Object Detection Autonomous Driving +4

Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving

1 code implementation12 Jun 2023 Wei-Xin Li, Xiaodong Yang

Evaluating the performance of perception modules in autonomous driving is one of the most critical tasks in developing the complex intelligent system.

Autonomous Driving Reinforcement Learning (RL)

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds

1 code implementation CVPR 2023 Jinyu Li, Chenxu Luo, Xiaodong Yang

In order to deal with the sparse and unstructured raw point clouds, LiDAR based 3D object detection research mostly focuses on designing dedicated local point aggregators for fine-grained geometrical modeling.

3D Object Detection Object +1

ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals

no code implementations CVPR 2023 Xishun Wang, Tong Su, Fang Da, Xiaodong Yang

To cope with these difficulties, this paper proposes a novel agent-centric model with anchor-informed proposals for efficient multimodal motion prediction.

Motion Forecasting motion prediction

SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes

1 code implementation14 Nov 2022 Jie Wang, Yuzhou Peng, Xiaodong Yang, Ting Wang, YanMing Zhang

The SportsMOT dataset aims to solve multiple object tracking of athletes in different sports scenes such as basketball or soccer.

Multiple Object Tracking

QML for Argoverse 2 Motion Forecasting Challenge

no code implementations13 Jul 2022 Tong Su, Xishun Wang, Xiaodong Yang

To safely navigate in various complex traffic scenarios, autonomous driving systems are generally equipped with a motion forecasting module to provide vital information for the downstream planning module.

Motion Forecasting Navigate

Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization

no code implementations27 Jun 2022 Xiaodong Yang, Huishuai Zhang, Wei Chen, Tie-Yan Liu

By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data.

TL-GAN: Improving Traffic Light Recognition via Data Synthesis for Autonomous Driving

no code implementations28 Mar 2022 Danfeng Wang, Xin Ma, Xiaodong Yang

Traffic light recognition, as a critical component of the perception module of self-driving vehicles, plays a vital role in the intelligent transportation systems.

Autonomous Driving Image Generation

Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond

2 code implementations28 Feb 2022 Yue Yao, Liang Zheng, Xiaodong Yang, Milind Napthade, Tom Gedeon

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data.

Attribute Data Augmentation +2

Learning Intrinsic Images for Clothing

no code implementations16 Nov 2021 Kuo Jiang, Zian Wang, Xiaodong Yang

A more interpretable edge-aware metric and an annotation scheme is designed for the testing set, which allows diagnostic evaluation for intrinsic models.

Intrinsic Image Decomposition

Neural Network Repair with Reachability Analysis

no code implementations9 Aug 2021 Xiaodong Yang, Tom Yamaguchi, Hoang-Dung Tran, Bardh Hoxha, Taylor T Johnson, Danil Prokhorov

Formally verifying the safety and robustness of well-trained DNNs and learning-enabled systems under attacks, model uncertainties, and sensing errors is essential for safe autonomy.

Collision Avoidance

Reachability Analysis of Convolutional Neural Networks

no code implementations22 Jun 2021 Xiaodong Yang, Tomoya Yamaguchi, Hoang-Dung Tran, Bardh Hoxha, Taylor T Johnson, Danil Prokhorov

Besides the computation of reachable sets, our approach is also capable of backtracking to the input domain given an output reachable set.

Self-Supervised Pillar Motion Learning for Autonomous Driving

1 code implementation CVPR 2021 Chenxu Luo, Xiaodong Yang, Alan Yuille

Autonomous driving can benefit from motion behavior comprehension when interacting with diverse traffic participants in highly dynamic environments.

Autonomous Driving Motion Estimation

Robust Dynamical Decoupling for the Manipulation of a Spin Network via a Single Spin

no code implementations11 Jan 2021 Xiaodong Yang, Yunrui Ge, Bo Zhang, Jun Li

High-fidelity control of quantum systems is crucial for quantum information processing, but is often limited by perturbations from the environment and imperfections in the applied control fields.

Quantum Physics

Network-Constrained Transactive Control for Multi- Microgrids-based Distribution Networks with SOPs

no code implementations6 Nov 2020 Xiaodong Yang, Zehao Song, Jinyu Wen, Chongbo Xu, Qiuwei Wu, Youbing Zhang, Menglin Zhang, Shijie Cheng

Different from most transactive control studies only focusing on economic aspect, this paper develops a novel network-constrained transactive control (NTC) framework that can address both economic and secure issues for a multi-microgrids-based distribution network considering uncertainties.

Optimization and Control

UFO$^2$: A Unified Framework towards Omni-supervised Object Detection

no code implementations21 Oct 2020 Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, Alexander G. Schwing, Jan Kautz

Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive image-level tags.

object-detection Object Detection

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

1 code implementation ECCV 2020 Yang Zou, Xiaodong Yang, Zhiding Yu, B. V. K. Vijaya Kumar, Jan Kautz

To this end, we propose a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id-related feature space exclusively.

Person Re-Identification Unsupervised Domain Adaptation

Hierarchical Contrastive Motion Learning for Video Action Recognition

no code implementations20 Jul 2020 Xitong Yang, Xiaodong Yang, Sifei Liu, Deqing Sun, Larry Davis, Jan Kautz

Thus, the motion features at higher levels are trained to gradually capture semantic dynamics and evolve more discriminative for action recognition.

Action Recognition Contrastive Learning +2

Contrastive Learning for Weakly Supervised Phrase Grounding

1 code implementation ECCV 2020 Tanmay Gupta, Arash Vahdat, Gal Chechik, Xiaodong Yang, Jan Kautz, Derek Hoiem

Given pairs of images and captions, we maximize compatibility of the attention-weighted regions and the words in the corresponding caption, compared to non-corresponding pairs of images and captions.

Contrastive Learning Language Modelling +1

Reachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approach

no code implementations26 Apr 2020 Weiming Xiang, Hoang-Dung Tran, Xiaodong Yang, Taylor T. Johnson

Then, in combination with reachability methods developed for various dynamical system classes modeled by ordinary differential equations, a recursive algorithm is developed for over-approximating the reachable set of the closed-loop system.

NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems

no code implementations12 Apr 2020 Hoang-Dung Tran, Xiaodong Yang, Diego Manzanas Lopez, Patrick Musau, Luan Viet Nguyen, Weiming Xiang, Stanley Bak, Taylor T. Johnson

For learning-enabled CPS, such as closed-loop control systems incorporating neural networks, NNV provides exact and over-approximate reachability analysis schemes for linear plant models and FFNN controllers with piecewise-linear activation functions, such as ReLUs.

Reachability Analysis for Feed-Forward Neural Networks using Face Lattices

1 code implementation2 Mar 2020 Xiaodong Yang, Hoang-Dung Tran, Weiming Xiang, Taylor Johnson

To address this challenge, we propose a parallelizable technique to compute exact reachable sets of a neural network to an input set.

FOCUS: Dealing with Label Quality Disparity in Federated Learning

1 code implementation29 Jan 2020 Yiqiang Chen, Xiaodong Yang, Xin Qin, Han Yu, Biao Chen, Zhiqi Shen

It maintains a small set of benchmark samples on the FL server and quantifies the credibility of the client local data without directly observing them by computing the mutual cross-entropy between performance of the FL model on the local datasets and that of the client local FL model on the benchmark dataset.

Federated Learning Privacy Preserving

Dancing to Music

2 code implementations NeurIPS 2019 Hsin-Ying Lee, Xiaodong Yang, Ming-Yu Liu, Ting-Chun Wang, Yu-Ding Lu, Ming-Hsuan Yang, Jan Kautz

In the analysis phase, we decompose a dance into a series of basic dance units, through which the model learns how to move.

Motion Synthesis Pose Estimation

Rethinking Full Connectivity in Recurrent Neural Networks

no code implementations29 May 2019 Matthijs Van Keirsbilck, Alexander Keller, Xiaodong Yang

We study structurally sparse RNNs, showing that they are well suited for acceleration on parallel hardware, with a greatly reduced cost of the recurrent operations as well as orders of magnitude less recurrent weights.

Action Recognition Language Modelling +3

STEP: Spatio-Temporal Progressive Learning for Video Action Detection

1 code implementation CVPR 2019 Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao, Larry Davis, Jan Kautz

In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos.

Action Detection Action Recognition

Discovering Spatio-Temporal Action Tubes

no code implementations29 Nov 2018 Yuancheng Ye, Xiaodong Yang, YingLi Tian

In this paper, we address the challenging problem of spatial and temporal action detection in videos.

Action Detection

Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction

no code implementations28 Nov 2018 Longlong Jing, Xiaodong Yang, Jingen Liu, YingLi Tian

The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections.

Self-Supervised Action Recognition Temporal Action Localization +1

Verification for Machine Learning, Autonomy, and Neural Networks Survey

1 code implementation3 Oct 2018 Weiming Xiang, Patrick Musau, Ayana A. Wild, Diego Manzanas Lopez, Nathaniel Hamilton, Xiaodong Yang, Joel Rosenfeld, Taylor T. Johnson

This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof.

BIG-bench Machine Learning General Classification

Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation

2 code implementations14 Sep 2018 Deqing Sun, Xiaodong Yang, Ming-Yu Liu, Jan Kautz

We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training.

Optical Flow Estimation

Making Convolutional Networks Recurrent for Visual Sequence Learning

no code implementations CVPR 2018 Xiaodong Yang, Pavlo Molchanov, Jan Kautz

Recurrent neural networks (RNNs) have emerged as a powerful model for a broad range of machine learning problems that involve sequential data.

Action Recognition Face Alignment +6

Budget-Aware Activity Detection with A Recurrent Policy Network

no code implementations30 Nov 2017 Behrooz Mahasseni, Xiaodong Yang, Pavlo Molchanov, Jan Kautz

In this paper, we address the challenging problem of efficient temporal activity detection in untrimmed long videos.

Action Detection Activity Detection

Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network

no code implementations CVPR 2017 Jinwei Gu, Xiaodong Yang, Shalini De Mello, Jan Kautz

We are inspired by the fact that the computation performed in an RNN bears resemblance to Bayesian filters, which have been used for tracking in many previous methods for facial analysis from videos.

 Ranked #1 on Head Pose Estimation on BIWI (MAE (trained with BIWI data) metric, using extra training data)

Face Alignment Feature Engineering +3

Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network

no code implementations CVPR 2016 Pavlo Molchanov, Xiaodong Yang, Shalini Gupta, Kihwan Kim, Stephen Tyree, Jan Kautz

Automatic detection and classification of dynamic hand gestures in real-world systems intended for human computer interaction is challenging as: 1) there is a large diversity in how people perform gestures, making detection and classification difficult; 2) the system must work online in order to avoid noticeable lag between performing a gesture and its classification; in fact, a negative lag (classification before the gesture is finished) is desirable, as feedback to the user can then be truly instantaneous.

Classification General Classification +1

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