Search Results for author:
Found 49 papers, 18 papers with code
Feature Alignment and Restoration for Domain Generalization and Adaptation
To ensure high discrimination, we propose a Feature Restoration (FR) operation to distill task-relevant features from the residual information and use them to compensate for the aligned features.
Ranked #82 on
Domain Generalization
on PACS
Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification
There is a lack of loss design which enables the joint optimization of multiple instances (of multiple classes) within per-query optimization for person ReID.
Global Distance-distributions Separation for Unsupervised Person Re-identification
To address this problem, we introduce a global distance-distributions separation (GDS) constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view.
Style Normalization and Restitution for Generalizable Person Re-identification
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps.
Ranked #9 on
Unsupervised Domain Adaptation
on Market to Duke
VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimations, we present an end-to-end solution which directly operates in the $3$D space, therefore avoids making incorrect decisions in the 2D space.
Ranked #6 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
Spatiotemporal Fusion in 3D CNNs: A Probabilistic View
Based on the probability space, we further generate new fusion strategies which achieve the state-of-the-art performance on four well-known action recognition datasets.
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency.
Ranked #1 on
Multi-Object Tracking
on 2DMOT15
(using extra training data)
Tracking by Instance Detection: A Meta-Learning Approach
We propose a principled three-step approach to build a high-performance tracker.
Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification
In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation.
Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach
Then we lift the multi-view 2D poses to the 3D space by an Orientation Regularized Pictorial Structure Model (ORPSM) which jointly minimizes the projection error between the 3D and 2D poses, along with the discrepancy between the 3D pose and IMU orientations.
Ranked #1 on
3D Absolute Human Pose Estimation
on Total Capture
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
To the best of our knowledge, we are the first to make use of multi-shots of an object in a teacher-student learning manner for effectively boosting the single image based re-id.
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network
We discover that the two streams should communicate with each other, and this is crucial to phase prediction.
Sound Audio and Speech Processing
Unsupervised High-Resolution Depth Learning From Videos With Dual Networks
Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal.
Monocular Depth Estimation
Vocal Bursts Intensity Prediction
Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments
Our experimental evaluation demonstrates that the result of our method is comparable to fully supervised methods on the NYU Depth V2 benchmark.
Multi-grained Attention Networks for Single Image Super-Resolution
In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts.
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
For an RNN block, an EleAttG is used for adaptively modulating the input by assigning different levels of importance, i. e., attention, to each element/dimension of the input.
Ranked #3 on
Skeleton Based Action Recognition
on SYSU 3D
Cross View Fusion for 3D Human Pose Estimation
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.
Ranked #6 on
3D Human Pose Estimation
on Total Capture
Posterior-Guided Neural Architecture Search
Accordingly, a hybrid network representation is presented which enables us to leverage the Variational Dropout so that the approximation of the posterior distribution becomes fully gradient-based and highly efficient.
Semantics-Aligned Representation Learning for Person Re-identification
Specifically, we build a Semantics Aligning Network (SAN) which consists of a base network as encoder (SA-Enc) for re-ID, and a decoder (SA-Dec) for reconstructing/regressing the densely semantics aligned full texture image.
Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification
An efficient and effective person re-identification (ReID) system relieves the users from painful and boring video watching and accelerates the process of video analysis.
CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
We achieve this by the context interaction among the features of different scales.
SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
The two stages are connected in series as the input proposals of the FM stage are generated by the CM stage.
Relation-Aware Global Attention for Person Re-identification
For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i. e., discriminative feature learning.
Target-Tailored Source-Transformation for Scene Graph Generation
We further explore more powerful representations by integrating language prior with the visual context in the transformation for the scene graph generation.
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data.
Ranked #1 on
Skeleton Based Action Recognition
on SYSU 3D
Quality-Gated Convolutional LSTM for Enhancing Compressed Video
The past decade has witnessed great success in applying deep learning to enhance the quality of compressed video.
View Invariant 3D Human Pose Estimation
The diversity of capturing viewpoints and the flexibility of the human poses, however, remain some significant challenges.
Densely Semantically Aligned Person Re-Identification
We propose a densely semantically aligned person re-identification framework.
Detect or Track: Towards Cost-Effective Video Object Detection/Tracking
Trackers are in general more efficient than detectors but bear the risk of drifting.
Temporal-Spatial Mapping for Action Recognition
We propose a video level 2D feature representation by transforming the convolutional features of all frames to a 2D feature map, referred to as VideoMap.
Ranked #53 on
Action Recognition
on UCF101
Towards a Better Match in Siamese Network Based Visual Object Tracker
Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance.
Ranked #10 on
Visual Object Tracking
on VOT2017/18
Online Dictionary Learning for Approximate Archetypal Analysis
The archetypes generally correspond to the extremal points in the dataset and are learned by requiring them to be convex combinations of the training data.
Adding Attentiveness to the Neurons in Recurrent Neural Networks
We propose adding a simple yet effective Element-wiseAttention Gate (EleAttG) to an RNN block (e. g., all RNN neurons in a network layer) that empowers the RNN neurons to have the attentiveness capability.
Ranked #112 on
Skeleton Based Action Recognition
on NTU RGB+D
Learning to Update for Object Tracking with Recurrent Meta-learner
Generally, model update is formulated as an online learning problem where a target model is learned over the online training set.
Ranked #1 on
Visual Tracking
on OTB-100
MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition
Recent attempts use 3D convolutional neural networks (CNNs) to explore spatio-temporal information for human action recognition.
View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
In order to alleviate the effects of view variations, this paper introduces a novel view adaptation scheme, which automatically determines the virtual observation viewpoints in a learning based data driven manner.
Ranked #1 on
Skeleton Based Action Recognition
on UWA3D
A Twofold Siamese Network for Real-Time Object Tracking
SA-Siam is composed of a semantic branch and an appearance branch.
Ranked #1 on
Visual Object Tracking
on OTB-50
Object Detection in Videos by High Quality Object Linking
In particular, our method improves results by 8. 8% over the static image detector for fast moving objects.
Benchmarking Single Image Dehazing and Beyond
We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE).
Human Pose Estimation using Global and Local Normalization
We present a two-stage normalization scheme, human body normalization and limb normalization, to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation.
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
Rather than re-positioning the skeletons based on a human defined prior criterion, we design a view adaptive recurrent neural network (RNN) with LSTM architecture, which enables the network itself to adapt to the most suitable observation viewpoints from end to end.
Ranked #6 on
Skeleton Based Action Recognition
on SYSU 3D
Deep Convolutional Neural Networks with Merge-and-Run Mappings
A deep residual network, built by stacking a sequence of residual blocks, is easy to train, because identity mappings skip residual branches and thus improve information flow.
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
In this work, we propose an end-to-end spatial and temporal attention model for human action recognition from skeleton data.
Ranked #122 on
Skeleton Based Action Recognition
on NTU RGB+D
Photo Stylistic Brush: Robust Style Transfer via Superpixel-Based Bipartite Graph
With the rapid development of social network and multimedia technology, customized image and video stylization has been widely used for various social-media applications.
Deeply-Fused Nets
Second, in our suggested fused net formed by one deep and one shallow base networks, the flows of the information from the earlier intermediate layer of the deep base network to the output and from the input to the later intermediate layer of the deep base network are both improved.
Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks
In this paper, we study the problem of online action detection from streaming skeleton data.
Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks
Skeleton based action recognition distinguishes human actions using the trajectories of skeleton joints, which provide a very good representation for describing actions.
High-Speed Hyperspectral Video Acquisition With a Dual-Camera Architecture
We propose a novel dual-camera design to acquire 4D high-speed hyperspectral (HSHS) videos with high spatial and spectral resolution.
