Search Results for author:
Found 30 papers, 8 papers with code
Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation
We propose AuxSegNet+, a weakly supervised auxiliary learning framework to explore the rich information from these saliency maps and the significant inter-task correlation between saliency detection and semantic segmentation.
Box It to Bind It: Unified Layout Control and Attribute Binding in T2I Diffusion Models
To address these deficiencies, we introduce the Box-it-to-Bind-it (B2B) module - a novel, training-free approach for improving spatial control and semantic accuracy in text-to-image (T2I) diffusion models.
Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art
Transformers have rapidly gained popularity in computer vision, especially in the field of object recognition and detection.
MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation
Building upon the observation that the attended regions of the one-class token in the standard vision transformer can contribute to a class-agnostic localization map, we explore the potential of the transformer model to capture class-specific attention for class-discriminative object localization by learning multiple class tokens.
Object Localization
Weakly supervised Semantic Segmentation
+1
Analysis and Evaluation of Explainable Artificial Intelligence on Suicide Risk Assessment
This study investigates the effectiveness of Explainable Artificial Intelligence (XAI) techniques in predicting suicide risks and identifying the dominant causes for such behaviours.
VAPCNet: Viewpoint-Aware 3D Point Cloud Completion
In this paper, we thus propose an unsupervised viewpoint representation learning scheme for 3D point cloud completion without explicit viewpoint estimation.
Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization
Weakly supervised dense object localization (WSDOL) relies generally on Class Activation Mapping (CAM), which exploits the correlation between the class weights of the image classifier and the pixel-level features.
3D Brain and Heart Volume Generative Models: A Survey
Generative models such as generative adversarial networks and autoencoders have gained a great deal of attention in the medical field due to their excellent data generation capability.
Active-Passive SimStereo -- Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods
In this paper, we propose the Active-Passive SimStereo dataset and a corresponding benchmark to evaluate the performance gap between passive and active stereo images for stereo matching algorithms.
Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision
A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision.
Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images
Novel 3D network architectures are proposed for both the generator and discriminator of the GAN model to significantly reduce the number of parameters while maintaining the quality of image generation.
A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance
Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects.
Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification
It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras.
Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification
In this paper, we present a pseudo-pair based self-similarity learning approach for unsupervised person re-ID without human annotations.
Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense
Moreover, adversarially training a defense model in general cannot produce interpretable predictions towards the inputs with perturbations, whilst a highly interpretable robust model is required by different domain experts to understand the behaviour of a DNN.
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation
3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints.
Ranked #24 on
3D Human Pose Estimation
on Human3.6M
Multi-class Token Transformer for Weakly Supervised Semantic Segmentation
To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens.
Generalized Closed-form Formulae for Feature-based Subpixel Alignment in Patch-based Matching
In this paper, we show that closed form formulae for subpixel disparity computation for the case of one dimensional matching, e. g., in the case of rectified stereo images where the search space is of one dimension, exists when using the standard NCC, SSD and SAD cost functions.
Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation
Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels.
Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems.
A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
Motivated by their growing success in solving various 2D and 3D vision problems, deep learning for stereo-based depth estimation has attracted growing interest from the community, with more than 150 papers published in this area between 2014 and 2019.
Ranked #1 on
Monocular Depth Estimation
on Make3D
(RMSE metric)
Learning Latent Global Network for Skeleton-based Action Prediction
Human actions represented with 3D skeleton sequences are robust to clustered backgrounds and illumination changes.
Ranked #4 on
Skeleton Based Action Recognition
on SYSU 3D
Automatic Hierarchical Classification of Kelps using Deep Residual Features
Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas.
Learning clip representations for skeleton-based 3d action recognition
This paper presents a new representation of skeleton sequences for 3D action recognition.
Ranked #60 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Exploiting Layerwise Convexity of Rectifier Networks with Sign Constrained Weights
By introducing sign constraints on the weights, this paper proposes sign constrained rectifier networks (SCRNs), whose training can be solved efficiently by the well known majorization-minimization (MM) algorithms.
On the Compressive Power of Deep Rectifier Networks for High Resolution Representation of Class Boundaries
To show the superior compressive power of deep rectifier networks over shallow rectifier networks, we prove that the maximum boundary resolution of a single hidden layer rectifier network classifier grows exponentially with the number of units when this number is smaller than the dimension of the patterns.
Skeletonnet: Mining deep part features for 3-d action recognition
Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition.
Ranked #106 on
Skeleton Based Action Recognition
on NTU RGB+D
From Deep to Shallow: Transformations of Deep Rectifier Networks
Similarly, for a residual net and a conventional rectifier net with the same structure except for the skip connections in the residual net, the corresponding single hidden layer representation of the residual net is much more complex than the corresponding single hidden layer representation of the conventional net.
A New Representation of Skeleton Sequences for 3D Action Recognition
This paper presents a new method for 3D action recognition with skeleton sequences (i. e., 3D trajectories of human skeleton joints).
Ranked #65 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Contractive Rectifier Networks for Nonlinear Maximum Margin Classification
The contractive constraints ensure that the achieved separating margin in the input space is larger than or equal to the separating margin in the output layer.
