Search Results for author: Yali Wang

Found 31 papers, 15 papers with code

Mining Inter-Video Proposal Relations for Video Object Detection

1 code implementation ECCV 2020 Mingfei Han, Yali Wang, Xiaojun Chang, Yu Qiao

Recent studies have shown that, context aggregating information from proposals in different frames can clearly enhance the performance of video object detection.

Video Object Detection

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

1 code implementation3 May 2022 Mengzhe He, Yali Wang, Jiaxi Wu, Yiru Wang, Hanqing Li, Bo Li, Weihao Gan, Wei Wu, Yu Qiao

It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention.

Object Detection

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

no code implementations17 Apr 2022 Jiaxi Wu, Jiaxin Chen, Mengzhe He, Yiru Wang, Bo Li, Bingqi Ma, Weihao Gan, Wei Wu, Yali Wang, Di Huang

Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.

Disentanglement Domain Adaptation +1

UniFormer: Unifying Convolution and Self-attention for Visual Recognition

3 code implementations24 Jan 2022 Kunchang Li, Yali Wang, Junhao Zhang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning.

Image Classification Object Detection +4

CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

no code implementations20 Jan 2022 Mingye Xu, Yali Wang, Zhipeng Zhou, Hongbin Xu, Yu Qiao

To fill this gap, we propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in the point cloud, and thus promote discriminative power of point cloud representation.

Point cloud reconstruction Self-Supervised Learning

UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning

1 code implementation12 Jan 2022 Kunchang Li, Yali Wang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 9% and 71. 2% top-1 accuracy respectively.

Representation Learning

MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video

1 code implementation24 Nov 2021 David Junhao Zhang, Kunchang Li, Yunpeng Chen, Yali Wang, Shashwat Chandra, Yu Qiao, Luoqi Liu, Mike Zheng Shou

Self-attention has become an integral component of the recent network architectures, e. g., Transformer, that dominate major image and video benchmarks.

Ranked #11 on Action Recognition on Something-Something V2 (using extra training data)

Action Recognition Image Classification +1

Self-slimmed Vision Transformer

no code implementations24 Nov 2021 Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks.

Knowledge Distillation

Self-Slimming Vision Transformer

no code implementations29 Sep 2021 Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu

Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.

Knowledge Distillation

Digging into Uncertainty in Self-supervised Multi-view Stereo

1 code implementation ICCV 2021 Hongbin Xu, Zhipeng Zhou, Yali Wang, Wenxiong Kang, Baigui Sun, Hao Li, Yu Qiao

Specially, the limitations can be categorized into two types: ambiguious supervision in foreground and invalid supervision in background.

Image Reconstruction Self-Supervised Learning

TE-YOLOF: Tiny and efficient YOLOF for blood cell detection

no code implementations27 Aug 2021 Fanxin Xu, Xiangkui Li, Hang Yang, Yali Wang, Wei Xiang

In this work, an object detector based on YOLOF has been proposed to detect blood cell objects such as red blood cells, white blood cells and platelets.

Blood Cell Detection

CT-Net: Channel Tensorization Network for Video Classification

1 code implementation ICLR 2021 Kunchang Li, Xianhang Li, Yali Wang, Jun Wang, Yu Qiao

It can learn to exploit spatial, temporal and channel attention in a high-dimensional manner, to improve the cooperative power of all the feature dimensions in our CT-Module.

Action Classification Action Recognition +1

FineAction: A Fine-Grained Video Dataset for Temporal Action Localization

no code implementations24 May 2021 Yi Liu, LiMin Wang, Xiao Ma, Yali Wang, Yu Qiao

Second, the coarse action classes often lead to the ambiguous annotations of temporal boundaries, which are inappropriate for temporal action localization.

Temporal Action Localization Temporal Localization +1

PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos

no code implementations16 Mar 2021 Tianyu Luan, Yali Wang, Junhao Zhang, Zhe Wang, Zhipeng Zhou, Yu Qiao

By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module.

Human Mesh Recovery

Automatic Preference Based Multi-objective Evolutionary Algorithm on Vehicle Fleet Maintenance Scheduling Optimization

no code implementations23 Jan 2021 Yali Wang, Steffen Limmer, Markus Olhofer, Michael Emmerich, Thomas Baeck

A preference based multi-objective evolutionary algorithm is proposed for generating solutions in an automatically detected knee point region.

Improving Many-Objective Evolutionary Algorithms by Means of Edge-Rotated Cones

no code implementations15 Apr 2020 Yali Wang, André Deutz, Thomas Bäck, Michael Emmerich

Given a point in $m$-dimensional objective space, any $\varepsilon$-ball of a point can be partitioned into the incomparable, the dominated and dominating region.

A Tailored NSGA-III Instantiation for Flexible Job Shop Scheduling

no code implementations14 Apr 2020 Yali Wang, Bas van Stein, Michael T. M. Emmerich, Thomas Bäck

A customized multi-objective evolutionary algorithm (MOEA) is proposed for the multi-objective flexible job shop scheduling problem (FJSP).

Context-Transformer: Tackling Object Confusion for Few-Shot Detection

1 code implementation16 Mar 2020 Ze Yang, Yali Wang, Xianyu Chen, Jianzhuang Liu, Yu Qiao

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors.

Few-Shot Learning Few-Shot Object Detection +1

Learning Attentive Pairwise Interaction for Fine-Grained Classification

1 code implementation24 Feb 2020 Peiqin Zhuang, Yali Wang, Yu Qiao

These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images.

Classification Fine-Grained Image Classification +1

Progressive Object Transfer Detection

no code implementations12 Feb 2020 Hao Chen, Yali Wang, Guoyou Wang, Xiang Bai, Yu Qiao

Inspired by this procedure of learning to detect, we propose a novel Progressive Object Transfer Detection (POTD) framework.

Object Detection

Clustering Bioactive Molecules in 3D Chemical Space with Unsupervised Deep Learning

no code implementations9 Feb 2019 Chu Qin, Ying Tan, Shang Ying Chen, Xian Zeng, Xingxing Qi, Tian Jin, Huan Shi, Yiwei Wan, Yu Chen, Jingfeng Li, Weidong He, Yali Wang, Peng Zhang, Feng Zhu, Hongping Zhao, Yuyang Jiang, Yuzong Chen

We ex-plored the superior learning capability of deep autoencoders for unsupervised clustering of 1. 39 mil-lion bioactive molecules into band-clusters in a 3-dimensional latent chemical space.

Drug Discovery

Temporal Hallucinating for Action Recognition With Few Still Images

no code implementations CVPR 2018 Yali Wang, Lei Zhou, Yu Qiao

To mimic this capacity, we propose a novel Hybrid Video Memory (HVM) machine, which can hallucinate temporal features of still images from video memory, in order to boost action recognition with few still images.

Action Recognition In Still Images Domain Adaptation

LSTD: A Low-Shot Transfer Detector for Object Detection

1 code implementation5 Mar 2018 Hao Chen, Yali Wang, Guoyou Wang, Yu Qiao

Second, we introduce a novel regularized transfer learning framework for low-shot detection, where the transfer knowledge (TK) and background depression (BD) regularizations are proposed to leverage object knowledge respectively from source and target domains, in order to further enhance fine-tuning with a few target images.

Few-Shot Object Detection Transfer Learning

RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos

1 code implementation 2017 IEEE International Conference on Computer Vision (ICCV) 2017 Wenbin Du, Yali Wang, Yu Qiao

Firstly, unlike previous works on pose-related action recognition, our RPAN is an end-to-end recurrent network which can exploit important spatial-temporal evolutions of human pose to assist action recognition in a unified framework.

Action Recognition Action Recognition In Videos +3

Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition

1 code implementation1 Sep 2016 Zhe Wang, Li-Min Wang, Yali Wang, Bo-Wen Zhang, Yu Qiao

In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition.

Scene Recognition

A Marginalized Particle Gaussian Process Regression

no code implementations NeurIPS 2012 Yali Wang, Brahim Chaib-Draa

We present a novel marginalized particle Gaussian process (MPGP) regression, which provides a fast, accurate online Bayesian filtering framework to model the latent function.

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