Search Results for author: Junsong Yuan

Found 69 papers, 19 papers with code

Clustering Driven Deep Autoencoder for Video Anomaly Detection

no code implementations ECCV 2020 Yunpeng Chang, Zhigang Tu, Wei Xie, Junsong Yuan

Because of the ambiguous definition of anomaly and the complexity of real data, anomaly detection in videos is one of the most challenging problems in intelligent video surveillance.

Anomaly Detection

Learning Progressive Joint Propagation for Human Motion Prediction

no code implementations ECCV 2020 Yujun Cai, Lin Huang, Yiwei Wang, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Xu Yang, Yiheng Zhu, Xiaohui Shen, Ding Liu, Jing Liu, Nadia Magnenat Thalmann

Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.

Human motion prediction motion prediction

Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation

no code implementations ECCV 2020 Lin Huang, Jianchao Tan, Ji Liu, Junsong Yuan

To address this issue, we connect this structured output learning problem with the structured modeling framework in sequence transduction field.

3D Hand Pose Estimation

Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track

no code implementations21 Jun 2021 Yuanhao Zhai, Le Wang, David Doermann, Junsong Yuan

The base model training encourages the model to predict reliable predictions based on single modality (i. e., RGB or optical flow), based on the fusion of which a pseudo ground truth is generated and in turn used as supervision to train the base models.

Optical Flow Estimation Weakly-supervised Temporal Action Localization +1

NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field

no code implementations15 May 2021 Celong Liu, Zhong Li, Junsong Yuan, Yi Xu

In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes.

Novel View Synthesis

Model-based 3D Hand Reconstruction via Self-Supervised Learning

1 code implementation CVPR 2021 Yujin Chen, Zhigang Tu, Di Kang, Linchao Bao, Ying Zhang, Xuefei Zhe, Ruizhi Chen, Junsong Yuan

For the first time, we demonstrate the feasibility of training an accurate 3D hand reconstruction network without relying on manual annotations.

Self-Supervised Learning

SPAGAN: Shortest Path Graph Attention Network

1 code implementation10 Jan 2021 Yiding Yang, Xinchao Wang, Mingli Song, Junsong Yuan, DaCheng Tao

SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further {a} more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods.

Graph Attention

Interventional Domain Adaptation

no code implementations7 Nov 2020 Jun Wen, Changjian Shui, Kun Kuang, Junsong Yuan, Zenan Huang, Zhefeng Gong, Nenggan Zheng

To address this issue, we intervene in the learning of feature discriminability using unlabeled target data to guide it to get rid of the domain-specific part and be safely transferable.

Unsupervised Domain Adaptation

Attention-Aware Noisy Label Learning for Image Classification

no code implementations30 Sep 2020 Zhenzhen Wang, Chunyan Xu, Yap-Peng Tan, Junsong Yuan

In this paper, the attention-aware noisy label learning approach ($A^2NL$) is proposed to improve the discriminative capability of the network trained on datasets with potential label noise.

Classification General Classification +2

ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection

1 code implementation14 Aug 2020 Ye Liu, Junsong Yuan, Chang Wen Chen

We consider the problem of Human-Object Interaction (HOI) Detection, which aims to locate and recognize HOI instances in the form of <human, action, object> in images.

Graph Attention Human-Object Interaction Detection +1

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

1 code implementation13 Aug 2020 Jialian Wu, Liangchen Song, Tiancai Wang, Qian Zhang, Junsong Yuan

In the classification tree, as the number of parent class nodes are significantly less, their logits are less noisy and can be utilized to suppress the wrong/noisy logits existed in the fine-grained class nodes.

Classification Few-Shot Object Detection +4

Revisiting Modified Greedy Algorithm for Monotone Submodular Maximization with a Knapsack Constraint

no code implementations12 Aug 2020 Jing Tang, Xueyan Tang, Andrew Lim, Kai Han, Chongshou Li, Junsong Yuan

Second, we enhance the modified greedy algorithm to derive a data-dependent upper bound on the optimum.

Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene

1 code implementation11 Aug 2020 Xinke Li, Chongshou Li, Zekun Tong, Andrew Lim, Junsong Yuan, Yuwei Wu, Jing Tang, Raymond Huang

Based on it, we formulate a hierarchical learning problem for 3D point cloud segmentation and propose a measurement evaluating consistency across various hierarchies.

Instance Segmentation Point Cloud Segmentation +2

Temporal Distinct Representation Learning for Action Recognition

no code implementations ECCV 2020 Junwu Weng, Donghao Luo, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Xudong Jiang, Junsong Yuan

Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos.

Action Recognition Representation Learning

Structure-Aware Human-Action Generation

1 code implementation ECCV 2020 Ping Yu, Yang Zhao, Chunyuan Li, Junsong Yuan, Changyou Chen

Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence.

Action Generation graph construction +1

Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition

no code implementations14 May 2020 Tianhang Zheng, Sheng Liu, Changyou Chen, Junsong Yuan, Baochun Li, Kui Ren

We first formulate generation of adversarial skeleton actions as a constrained optimization problem by representing or approximating the physiological and physical constraints with mathematical formulations.

Action Recognition Skeleton Based Action Recognition

Image Co-skeletonization via Co-segmentation

no code implementations12 Apr 2020 Koteswar Rao Jerripothula, Jianfei Cai, Jiangbo Lu, Junsong Yuan

Object skeletonization in a single natural image is a challenging problem because there is hardly any prior knowledge about the object.

Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions

1 code implementation AAAI 2019 Zhenyi Wang, Ping Yu, Yang Zhao, Ruiyi Zhang, Yufan Zhou, Junsong Yuan, Changyou Chen

In this paper, we focus on skeleton-based action generation and propose to model smooth and diverse transitions on a latent space of action sequences with much lower dimensionality.

Action Generation

A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image

1 code implementation ICCV 2019 Fu Xiong, Boshen Zhang, Yang Xiao, Zhiguo Cao, Taidong Yu, Joey Tianyi Zhou, Junsong Yuan

For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed.

 Ranked #1 on Depth Estimation on NYU-Depth V2 (mAP metric)

3D Pose Estimation Depth Estimation +1

Context-Integrated and Feature-Refined Network for Lightweight Object Parsing

no code implementations26 Jul 2019 Bin Jiang, Wenxuan Tu, Chao Yang, Junsong Yuan

The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM).

Scene Parsing Semantic Segmentation

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

no code implementations24 Jun 2019 Jun Wen, Nenggan Zheng, Junsong Yuan, Zhefeng Gong, Changyou Chen

By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains.

Unsupervised Domain Adaptation

Kervolutional Neural Networks

5 code implementations CVPR 2019 Chen Wang, Jianfei Yang, Lihua Xie, Junsong Yuan

Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks.

3D Hand Shape and Pose Estimation from a Single RGB Image

2 code implementations CVPR 2019 Liuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang, Jianfei Cai, Junsong Yuan

This work addresses a novel and challenging problem of estimating the full 3D hand shape and pose from a single RGB image.

3D Hand Pose Estimation

Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos

no code implementations1 Mar 2019 Bo Hu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan

Previous spatial-temporal action localization methods commonly follow the pipeline of object detection to estimate bounding boxes and labels of actions.

Object Detection Temporal Action Localization

Towards Real-time Eyeblink Detection in The Wild:Dataset,Theory and Practices

no code implementations21 Feb 2019 Guilei Hu, Yang Xiao, Zhiguo Cao, Lubin Meng, Zhiwen Fang, Joey Tianyi Zhou, Junsong Yuan

Effective and real-time eyeblink detection is of wide-range applications, such as deception detection, drive fatigue detection, face anti-spoofing, etc.

Deception Detection Face Anti-Spoofing

PointCloud Saliency Maps

3 code implementations ICCV 2019 Tianhang Zheng, Changyou Chen, Junsong Yuan, Bo Li, Kui Ren

Our motivation for constructing a saliency map is by point dropping, which is a non-differentiable operator.

Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

no code implementations12 Nov 2018 Jun Wen, Risheng Liu, Nenggan Zheng, Qian Zheng, Zhefeng Gong, Junsong Yuan

In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics.

Unsupervised Domain Adaptation

Point-to-Point Regression PointNet for 3D Hand Pose Estimation

no code implementations ECCV 2018 Liuhao Ge, Zhou Ren, Junsong Yuan

Convolutional Neural Networks (CNNs)-based methods for 3D hand pose estimation with depth cameras usually take 2D depth images as input and directly regress holistic 3D hand pose.

3D Hand Pose Estimation

Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition

no code implementations ECCV 2018 Junwu Weng, Mengyuan Liu, Xudong Jiang, Junsong Yuan

This deformable convolution can better utilize contextual joints for action and gesture recognition and is more robust to noisy joints.

Hand Gesture Recognition Hand-Gesture Recognition

Bi-box Regression for Pedestrian Detection and Occlusion Estimation

no code implementations ECCV 2018 Chunluan Zhou, Junsong Yuan

The full body estimation branch is trained to regress full body regions for positive pedestrian proposals, while the visible part estimation branch is trained to regress visible part regions for both positive and negative pedestrian proposals.

Occlusion Estimation Pedestrian Detection

Product Quantization Network for Fast Image Retrieval

no code implementations ECCV 2018 Tan Yu, Junsong Yuan, Chen Fang, Hailin Jin

Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features.

Image Retrieval Quantization

Weakly-supervised 3D Hand Pose Estimation from Monocular RGB Images

no code implementations ECCV 2018 Yujun Cai, Liuhao Ge, Jianfei Cai, Junsong Yuan

Compared with depth-based 3D hand pose estimation, it is more challenging to infer 3D hand pose from monocular RGB images, due to substantial depth ambiguity and the difficulty of obtaining fully-annotated training data.

3D Hand Pose Estimation

Actor-Action Semantic Segmentation with Region Masks

no code implementations23 Jul 2018 Kang Dang, Chunluan Zhou, Zhigang Tu, Michael Hoy, Justin Dauwels, Junsong Yuan

One major challenge for this task is that when an actor performs an action, different body parts of the actor provide different types of cues for the action category and may receive inconsistent action labeling when they are labeled independently.

Action Segmentation Instance Segmentation +1

Conditional Generative Adversarial Network for Structured Domain Adaptation

no code implementations CVPR 2018 Weixiang Hong, Zhenzhen Wang, Ming Yang, Junsong Yuan

In recent years, deep neural nets have triumphed over many computer vision problems, including semantic segmentation, which is a critical task in emerging autonomous driving and medical image diagnostics applications.

Autonomous Driving Domain Adaptation +1

Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display

no code implementations CVPR 2018 Shizheng Wang, Wenjuan Liao, Phil Surman, Zhigang Tu, Yuanjin Zheng, Junsong Yuan

Multi-layer light field displays are a type of computational three-dimensional (3D) display which has recently gained increasing interest for its holographic-like effect and natural compatibility with 2D displays.

Recognizing Human Actions as the Evolution of Pose Estimation Maps

no code implementations CVPR 2018 Mengyuan Liu, Junsong Yuan

Specifically, the evolution of pose estimation maps can be decomposed as an evolution of heatmaps, e. g., probabilistic maps, and an evolution of estimated 2D human poses, which denote the changes of body shape and body pose, respectively.

Action Recognition Multimodal Activity Recognition +2

Non-iterative RGB-D-inertial Odometry

1 code implementation16 Oct 2017 Chen Wang, Minh-Chung Hoang, Lihua Xie, Junsong Yuan

This paper presents a non-iterative solution to RGB-D-inertial odometry system.

Robotics

Common Action Discovery and Localization in Unconstrained Videos

no code implementations ICCV 2017 Jiong Yang, Junsong Yuan

Similar to common object discovery in images or videos, it is of great interests to discover and locate common actions in videos, which can benefit many video analytics applications such as video summarization, search, and understanding.

Object Discovery Video Summarization

Compressive Quantization for Fast Object Instance Search in Videos

no code implementations ICCV 2017 Tan Yu, Zhenzhen Wang, Junsong Yuan

Most of current visual search systems focus on image-to-image (point-to-point) search such as image and object retrieval.

Instance Search Quantization +1

Multi-Label Learning of Part Detectors for Heavily Occluded Pedestrian Detection

no code implementations ICCV 2017 Chunluan Zhou, Junsong Yuan

Detecting pedestrians that are partially occluded remains a challenging problem due to variations and uncertainties of partial occlusion patterns.

Multi-Label Learning Pedestrian Detection

Kernel Cross-Correlator

2 code implementations12 Sep 2017 Chen Wang, Le Zhang, Lihua Xie, Junsong Yuan

Cross-correlator plays a significant role in many visual perception tasks, such as object detection and tracking.

Activity Recognition Object Detection +1

3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images

no code implementations CVPR 2017 Liuhao Ge, Hui Liang, Junsong Yuan, Daniel Thalmann

We propose a simple, yet effective approach for real-time hand pose estimation from single depth images using three-dimensional Convolutional Neural Networks (3D CNNs).

3D Hand Pose Estimation Data Augmentation

Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition

1 code implementation CVPR 2017 Junwu Weng, Chaoqun Weng, Junsong Yuan

Moreover, by identifying key skeleton joints and temporal stages for each action class, our ST-NBNN can capture the essential spatio-temporal patterns that play key roles of recognizing actions, which is not always achievable by using end-to-end models.

Action Recognition Skeleton Based Action Recognition

Fried Binary Embedding for High-Dimensional Visual Features

no code implementations CVPR 2017 Weixiang Hong, Junsong Yuan, Sreyasee Das Bhattacharjee

We argue that long binary codes (b O(d)) are critical to fully utilize the discriminative power of high-dimensional visual features, and can achieve better results in various tasks such as approximate nearest neighbour search.

Object Co-Skeletonization With Co-Segmentation

no code implementations CVPR 2017 Koteswar Rao Jerripothula, Jianfei Cai, Jiangbo Lu, Junsong Yuan

Recent advances in the joint processing of images have certainly shown its advantages over the individual processing.

From Keyframes to Key Objects: Video Summarization by Representative Object Proposal Selection

no code implementations CVPR 2016 Jingjing Meng, Hongxing Wang, Junsong Yuan, Yap-Peng Tan

This representative selection problem is formulated as a sparse dictionary selection problem, i. e., choosing a few representatives object proposals to reconstruct the whole proposal pool.

Video Summarization

Adaptive Exponential Smoothing for Online Filtering of Pixel Prediction Maps

no code implementations ICCV 2015 Kang Dang, Jiong Yang, Junsong Yuan

We propose an efficient online video filtering method, called adaptive exponential filtering (AES) to refine pixel prediction maps.

Saliency Detection Scene Parsing

Fast Action Proposals for Human Action Detection and Search

no code implementations CVPR 2015 Gang Yu, Junsong Yuan

Assuming each action is performed by a human with meaningful motion, both appearance and motion cues are utilized to measure the actionness of the video tubes.

Action Detection Video Segmentation +1

Multi-feature Spectral Clustering with Minimax Optimization

no code implementations CVPR 2014 Hongxing Wang, Chaoqun Weng, Junsong Yuan

To find a consensus clustering result that is agreeable to all feature modalities, our objective is to find a universal feature embedding, which not only fits each individual feature modality well, but also unifies different feature modalities by minimizing their pairwise disagreements.

Topical Video Object Discovery from Key Frames by Modeling Word Co-occurrence Prior

no code implementations CVPR 2013 Gangqiang Zhao, Junsong Yuan, Gang Hua

We show that such data driven co-occurrence information from bottom-up can conveniently be incorporated in LDA with a Gaussian Markov prior, which combines top down probabilistic topic modeling with bottom up priors in a unified model.

Object Discovery Topic Models

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