Search Results for author:
Found 44 papers, 18 papers with code
Head-Free Lightweight Semantic Segmentation with Linear Transformer
On the ADE20K dataset, our model achieves 41. 8 mIoU and 4. 6 GFLOPs, which is 4. 4 mIoU higher than Segformer, with 45% less GFLOPs.
A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition
Although improving motion recognition to some extent, these methods still face sub-optimal situations in the following aspects: (i) Data augmentation, i. e., the scale of the RGB-D datasets is still limited, and few efforts have been made to explore novel data augmentation strategies for videos; (ii) Optimization mechanism, i. e., the tightly space-time-entangled network structure brings more challenges to spatiotemporal information modeling; And (iii) cross-modal knowledge fusion, i. e., the high similarity between multimodal representations caused to insufficient late fusion.
VTC-LFC: Vision Transformer Compression with Low-Frequency Components
Although Vision transformers (ViTs) have recently dominated many vision tasks, deploying ViT models on resource-limited devices remains a challenging problem.
Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition
Besides, these methods directly calculate the pair-wise global self-attention equally for all the joints in both the spatial and temporal dimensions, undervaluing the effect of discriminative local joints and the short-range temporal dynamics.
Effective Vision Transformer Training: A Data-Centric Perspective
To achieve these two purposes, we propose a novel data-centric ViT training framework to dynamically measure the ``difficulty'' of training samples and generate ``effective'' samples for models at different training stages.
FT-HID: A Large Scale RGB-D Dataset for First and Third Person Human Interaction Analysis
It has been studied either using first person vision (FPV) or third person vision (TPV).
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution.
Ranked #4 on
6D Pose Estimation using RGB
on LineMOD
BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective
In our work, considering the different importance of pair-wise samples for both feature learning and domain alignment, we deduce our BP-Triplet loss for effective UDA from the perspective of Bayesian learning.
Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer
During the KD process, the TCL loss transfers the local structure, exploits the higher order information, and mitigates the misalignment of the heterogeneous output of teacher and student networks.
ELSA: Enhanced Local Self-Attention for Vision Transformer
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning.
Ranked #36 on
Instance Segmentation
on COCO minival
Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors.
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations.
Ranked #1 on
Unsupervised Semantic Segmentation
on COCO-Stuff-171
(using extra training data)
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion.
Ranked #8 on
3D Human Pose Estimation
on MPI-INF-3DHP
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.
Ranked #1 on
Unsupervised Person Re-Identification
on Market-1501
(using extra training data)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment, respectively.
Ranked #1 on
Domain Adaptation
on Office-31
Scaled ReLU Matters for Training Vision Transformers
In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the \textit{convolutional stem} (\textit{conv-stem}) matters.
KVT: k-NN Attention for Boosting Vision Transformers
A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies.
TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection
3D mask face presentation attack detection (PAD) plays a vital role in securing face recognition systems from emergent 3D mask attacks.
Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation
Temporal action proposal generation (TAPG) is a fundamental and challenging task in video understanding, especially in temporal action detection.
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE.
Ranked #1 on
3D Human Pose Estimation
on HumanEva-I
TransReID: Transformer-based Object Re-Identification
Extracting robust feature representation is one of the key challenges in object re-identification (ReID).
Ranked #1 on
Person Re-Identification
on Market-1501-C
Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
Comparing with previous NAS methods, the proposed Zen-NAS is magnitude times faster on multiple server-side and mobile-side GPU platforms with state-of-the-art accuracy on ImageNet.
Ranked #1 on
Neural Architecture Search
on ImageNet
Trear: Transformer-based RGB-D Egocentric Action Recognition
In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear.
Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition
To address this issue, instead of using an accuracy predictor, we propose a novel zero-shot index dubbed Zen-Score to rank the architectures.
Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry
In this paper, we propose a method consisting of two camera pose estimators that deal with the information from pairwise images and a short sequence of images respectively.
SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching
The recently developed DARTS (Differentiable Architecture Search) is adopted to search for an effective network architecture that is built upon the two types of cells.
Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
Gesture recognition has attracted considerable attention owing to its great potential in applications.
RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks
It is deployed as a public online service and widely adopted in different business scenarios at Alibaba Group.
Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI), for both isolated and continuous action recognition.
Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition
Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities.
RGB-D-based Human Motion Recognition with Deep Learning: A Survey
Specifically, deep learning methods based on the CNN and RNN architectures have been adopted for motion recognition using RGB-D data.
Skeleton-based Action Recognition Using LSTM and CNN
Recent methods based on 3D skeleton data have achieved outstanding performance due to its conciseness, robustness, and view-independent representation.
Investigation of Different Skeleton Features for CNN-based 3D Action Recognition
The proposed method achieved state-of-the-art performance on NTU RGB+D dataset for 3D human action analysis.
Ranked #84 on
Skeleton Based Action Recognition
on NTU RGB+D
(Accuracy (CV) metric)
Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks
Based on the scene flow vectors, we propose a new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition.
Ranked #3 on
Hand Gesture Recognition
on ChaLearn val
Large-scale Isolated Gesture Recognition Using Convolutional Neural Networks
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI).
Ranked #2 on
Hand Gesture Recognition
on ChaLearn val
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks
Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition.
Ranked #1 on
Skeleton Based Action Recognition
on Gaming 3D (G3D)
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition.
Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks
This paper addresses the problem of continuous gesture recognition from sequences of depth maps using convolutional neutral networks (ConvNets).
Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier
This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth maps, and exploits effectively both the local and global temporal information.
RGB-D-based Action Recognition Datasets: A Survey
Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010.
Online Action Recognition based on Incremental Learning of Weighted Covariance Descriptors
This paper presents a fast yet effective method to recognize actions from stream of noisy skeleton data, and a novel weighted covariance descriptor is adopted to accumulate evidence.
Action recognition from depth maps using deep convolutional neural networks
In addition, the method was evaluated on the large dataset constructed from the above datasets.
Ranked #9 on
Multimodal Activity Recognition
on EV-Action
Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
The results show that our approach can achieve state-of-the-art results on the individual datasets and without dramatical performance degradation on the Combined Dataset.
Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation
These parts are referred to as Frequent Local Parts or FLPs.
