Search Results for author: Yan Lu

Found 33 papers, 10 papers with code

Temporal Context Mining for Learned Video Compression

no code implementations27 Nov 2021 Xihua Sheng, Jiahao Li, Bin Li, Li Li, Dong Liu, Yan Lu

From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.

MS-SSIM SSIM +1

Video Instance Segmentation by Instance Flow Assembly

no code implementations20 Oct 2021 Xiang Li, Jinglu Wang, Xiao Li, Yan Lu

Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes.

Instance Segmentation Object Localization +2

Deep Contextual Video Compression

no code implementations NeurIPS 2021 Jiahao Li, Bin Li, Yan Lu

In this paper, we propose a deep contextual video compression framework to enable a paradigm shift from predictive coding to conditional coding.

Video Compression

What Makes for Good Representations for Contrastive Learning

no code implementations29 Sep 2021 Haoqing Wang, Xun Guo, Zhi-Hong Deng, Yan Lu

Therefore, we assume the task-relevant information that is not shared between views can not be ignored and theoretically prove that the minimal sufficient representation in contrastive learning is not sufficient for the downstream tasks, which causes performance degradation.

Contrastive Learning Representation Learning

Cross-Stage Transformer for Video Learning

no code implementations29 Sep 2021 Yuanze Lin, Xun Guo, Yan Lu

By inserting the proposed cross-stage mechanism in existing spatial and temporal transformer blocks, we build a separable transformer network for video learning based on ViT structure, in which self-attentions and features are progressively aggregated from one block to the next.

Action Recognition

Self-Supervised Video Representation Learning with Meta-Contrastive Network

no code implementations ICCV 2021 Yuanze Lin, Xun Guo, Yan Lu

Our method contains two training stages based on model-agnostic meta learning (MAML), each of which consists of a contrastive branch and a meta branch.

Action Recognition Contrastive Learning +4

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

1 code implementation ICCV 2021 Yan Lu, Xinzhu Ma, Lei Yang, Tianzhu Zhang, Yating Liu, Qi Chu, Junjie Yan, Wanli Ouyang

In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.

Depth Estimation Monocular 3D Object Detection

SSAN: Separable Self-Attention Network for Video Representation Learning

no code implementations CVPR 2021 Xudong Guo, Xun Guo, Yan Lu

However, spatial correlations and temporal correlations represent different contextual information of scenes and temporal reasoning.

Action Recognition Representation Learning +1

MonoGRNet: A General Framework for Monocular 3D Object Detection

no code implementations18 Apr 2021 Zengyi Qin, Jinglu Wang, Yan Lu

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a monocular image due to the geometric information loss during imagery projection.

2D Object Detection Depth Estimation +2

Phoneme-based Distribution Regularization for Speech Enhancement

no code implementations8 Apr 2021 Yajing Liu, Xiulian Peng, Zhiwei Xiong, Yan Lu

Specifically, we propose a phoneme-based distribution regularization (PbDr) for speech enhancement, which incorporates frame-wise phoneme information into speech enhancement network in a conditional manner.

Speech Enhancement

Custom Object Detection via Multi-Camera Self-Supervised Learning

no code implementations5 Feb 2021 Yan Lu, Yuanchao Shu

This paper proposes MCSSL, a self-supervised learning approach for building custom object detection models in multi-camera networks.

Object Detection Self-Supervised Learning

T-Net: Effective Permutation-Equivariant Network for Two-View Correspondence Learning

1 code implementation ICCV 2021 Zhen Zhong, Guobao Xiao, Linxin Zheng, Yan Lu, Jiayi Ma

We develop a conceptually simple, flexible, and effective framework (named T-Net) for two-view correspondence learning.

Interactive Speech and Noise Modeling for Speech Enhancement

no code implementations17 Dec 2020 Chengyu Zheng, Xiulian Peng, Yuan Zhang, Sriram Srinivasan, Yan Lu

In this paper, we propose a novel idea to model speech and noise simultaneously in a two-branch convolutional neural network, namely SN-Net.

Speaker Separation Speech Enhancement

Weakly Supervised 3D Object Detection from Point Clouds

1 code implementation28 Jul 2020 Zengyi Qin, Jinglu Wang, Yan Lu

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes.

3D Object Detection Knowledge Distillation +1

Weakly-supervised Temporal Action Localization by Uncertainty Modeling

2 code implementations12 Jun 2020 Pilhyeon Lee, Jinglu Wang, Yan Lu, Hyeran Byun

Experimental results show that our uncertainty modeling is effective at alleviating the interference of background frames and brings a large performance gain without bells and whistles.

Action Classification Multiple Instance Learning +4

Scattering under Linear Non Self-Adjoint Operators: Case of in-Plane Elastic Waves

no code implementations6 Mar 2020 Amir Ashkan Mokhtari, Yan Lu, Qiyuan Zhou, Alireza V. Amirkhizi, Ankit Srivastava

In this paper, we consider the problem of the scattering of in-plane waves at an interface between a homogeneous medium and a metamaterial.

Applied Physics

Cross-modality Person re-identification with Shared-Specific Feature Transfer

no code implementations CVPR 2020 Yan Lu, Yue Wu, Bin Liu, Tianzhu Zhang, Baopu Li, Qi Chu, Nenghai Yu

In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance.

Cross-Modality Person Re-identification Person Re-Identification

Reinforcement learning for bandwidth estimation and congestion control in real-time communications

no code implementations4 Dec 2019 Joyce Fang, Martin Ellis, Bin Li, Siyao Liu, Yasaman Hosseinkashi, Michael Revow, Albert Sadovnikov, Ziyuan Liu, Peng Cheng, Sachin Ashok, David Zhao, Ross Cutler, Yan Lu, Johannes Gehrke

Bandwidth estimation and congestion control for real-time communications (i. e., audio and video conferencing) remains a difficult problem, despite many years of research.

Triangulation Learning Network: from Monocular to Stereo 3D Object Detection

1 code implementation CVPR 2019 Zengyi Qin, Jinglu Wang, Yan Lu

In this paper, we study the problem of 3D object detection from stereo images, in which the key challenge is how to effectively utilize stereo information.

3D Object Detection 3D Object Detection From Stereo Images

Relational Knowledge Distillation

3 code implementations CVPR 2019 Wonpyo Park, Dongju Kim, Yan Lu, Minsu Cho

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller.

Knowledge Distillation Metric Learning

Real-Time Anomaly Detection With HMOF Feature

no code implementations12 Dec 2018 Huihui Zhu, Bin Liu, Guojun Yin, Yan Lu, Weihai Li, Nenghai Yu

Most existing methods are computation consuming, which cannot satisfy the real-time requirement.

Anomaly Detection Optical Flow Estimation

Affinity Derivation and Graph Merge for Instance Segmentation

1 code implementation ECCV 2018 Yiding Liu, Siyu Yang, Bin Li, Wengang Zhou, Jizheng Xu, Houqiang Li, Yan Lu

We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance.

Instance Segmentation Semantic Segmentation

MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization

1 code implementation26 Nov 2018 Zengyi Qin, Jinglu Wang, Yan Lu

We propose MonoGRNet for the amodal 3D object detection from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension.

2D Object Detection Depth Estimation +3

MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image

no code implementations23 Nov 2018 Jinglu Wang, Bo Sun, Yan Lu

In this paper, we address the problem of reconstructing an object's surface from a single image using generative networks.

3D Object Reconstruction From A Single Image

Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification

no code implementations6 Aug 2018 Tao Hu, Jizheng Xu, Cong Huang, Honggang Qi, Qingming Huang, Yan Lu

Besides, we propose attention regularization and attention dropout to weakly supervise the generating process of attention maps.

Classification Fine-Grained Image Classification +1

Local Descriptors Optimized for Average Precision

no code implementations CVPR 2018 Kun He, Yan Lu, Stan Sclaroff

In this paper, we improve the learning of local feature descriptors by optimizing the performance of descriptor matching, which is a common stage that follows descriptor extraction in local feature based pipelines, and can be formulated as nearest neighbor retrieval.

Learning-To-Rank

Feature Selective Networks for Object Detection

no code implementations CVPR 2018 Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li

The RoI-based sub-region attention map and aspect ratio attention map are selectively pooled from the banks, and then used to refine the original RoI features for RoI classification.

Object Detection Translation

Robust RGB-D Odometry Using Point and Line Features

no code implementations ICCV 2015 Yan Lu, Dezhen Song

To meet the challenges, we fuse point and line features to form a robust odometry algorithm.

Visual Odometry

Content adaptive screen image scaling

no code implementations21 Oct 2015 Yao Zhai, Qifei Wang, Yan Lu, Shipeng Li

This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing.

General Classification

Human Activity Recognition using Smartphone

no code implementations30 Jan 2014 Amin Rasekh, Chien-An Chen, Yan Lu

In this project, we design a robust activity recognition system based on a smartphone.

Active Learning Activity Recognition +2

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