Search Results for author:
Found 33 papers, 12 papers with code
Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency
This method is based on two key innovations: a Temporal Eigenvalue Loss (TEL) and a clip-level Quality Cluster Coefficient (QCC).
Attack on Scene Flow using Point Clouds
The robustness of these techniques, however, remains a concern, particularly in the face of adversarial attacks that have been proven to deceive state-of-the-art deep neural networks in many domains.
SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap
This tracking and identification process is crucial for reconstructing the game state, defined by the athletes' positions and identities on a 2D top-view of the pitch, (i. e. a minimap).
Ranked #1 on
Game State Reconstruction
on SoccerNet-GSR
Attention-guided Feature Distillation for Semantic Segmentation
In contrast to existing complex methodologies commonly employed for distilling knowledge from a teacher to a student, this paper showcases the efficacy of a simple yet powerful method for utilizing refined feature maps to transfer attention.
Deep Spectral Improvement for Unsupervised Image Instance Segmentation
This paper addresses the fact that not all channels of the feature map extracted from a self-supervised backbone contain sufficient information for instance segmentation purposes.
Leveraging Swin Transformer for Local-to-Global Weakly Supervised Semantic Segmentation
In recent years, weakly supervised semantic segmentation using image-level labels as supervision has received significant attention in the field of computer vision.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking
To demonstrate the effectiveness of PRTreID, it is integrated with a state-of-the-art tracking method, using a part-based post-processing module to handle long-term tracking.
Rethinking RAFT for Efficient Optical Flow
To address these problems, this paper proposes a novel approach based on the RAFT framework.
Ranked #4 on
Optical Flow Estimation
on Sintel-clean
AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation
With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has emerged as a successful technique for improving the accuracy of lightweight student networks.
Trainable Loss Weights in Super-Resolution
In this article, a new weighting method for pixel-wise loss is proposed.
Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks
Adversarial attacks pose serious challenges for deep neural network (DNN)-based analysis of various input signals.
LPF-Defense: 3D Adversarial Defense based on Frequency Analysis
Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks.
Information-Theoretic Analysis of Minimax Excess Risk
We consider the frequentist problem of minimax excess risk as a zero-sum game between the algorithm designer and the world.
Adversarial Attack by Limited Point Cloud Surface Modifications
The obtained results show that it can perform successful attacks and achieve state-of-the-art results by only a limited number of point modifications while preserving the appearance of the point cloud.
CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search
A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results.
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
For the upper bound, the optimization is further constrained to use $R$ bits from the training set, a setting which relates MER to information-theoretic bounds on the generalization gap in frequentist learning.
Generating Unrestricted Adversarial Examples via Three Parameters
It also reduces the model accuracy by an average of 73% on six datasets MNIST, FMNIST, SVHN, CIFAR10, CIFAR100, and ImageNet.
Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds
This approach provides an insight into learning algorithms by considering the mutual information between the model and the training set.
Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer
The proposed method has been devoted to both lightweight image classification and encoder-decoder architectures to boost the performance of small and compact models without incurring extra computational overhead at the inference process.
Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking
Third, the generalization of the proposed method is validated on various tracking datasets as well as CNN models with similar architectures.
COMET: Context-Aware IoU-Guided Network for Small Object Tracking
To address this problem, we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-stream network and an offline reference proposal generation strategy.
Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking
In recent years, visual tracking methods that are based on discriminative correlation filters (DCF) have been very promising.
Beyond Background-Aware Correlation Filters: Adaptive Context Modeling by Hand-Crafted and Deep RGB Features for Visual Tracking
In recent years, the background-aware correlation filters have achie-ved a lot of research interest in the visual target tracking.
Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking
Then, the proposed method extracts deep semantic information from a fully convolutional FEN and fuses it with the best ResNet-based feature maps to strengthen the target representation in the learning process of continuous convolution filters.
Lightweight Residual Densely Connected Convolutional Neural Network
Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices).
Pointwise Attention-Based Atrous Convolutional Neural Networks
With the rapid progress of deep convolutional neural networks, in almost all robotic applications, the availability of 3D point clouds improves the accuracy of 3D semantic segmentation methods.
Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images
One of the high-level tasks in 3D scene understanding is semantic segmentation of RGB-Depth images.
Ranked #5 on
Semantic Segmentation
on Stanford2D3D - RGBD
Deep Learning for Visual Tracking: A Comprehensive Survey
Second, popular visual tracking benchmarks and their respective properties are compared, and their evaluation metrics are summarized.
Do Compressed Representations Generalize Better?
In this paper, the constraint on the entropy $H(X)$ of the input variable $X$ is studied as a simplicity assumption.
Information Bottleneck and its Applications in Deep Learning
Information Theory (IT) has been used in Machine Learning (ML) from early days of this field.
Multiple human 3d pose estimation from multiview images
In this work, a novel method for multiple human 3D pose estimation using evidences in multiview images is proposed.
Ranked #14 on
3D Multi-Person Pose Estimation
on Campus
A Novel Boundary Matching Algorithm for Video Temporal Error Concealment
It then uses a classic boundary matching criterion or the proposed boundary matching criterion adaptively to identify matching distortion in each boundary of candidate MB.
A Bayesian Framework for Sparse Representation-Based 3D Human Pose Estimation
Our Bayesian framework estimates a posterior distribution for the sparse codes and the dictionaries from labeled training data.
