相关论文: Coded Residual Transform for Generalizable Deep Me…

Local Feature Matching, an essential component of several computer vision tasks (e.g., structure from motion and visual localization), has been effectively settled by Transformer-based methods. However, these methods only integrate…

Deep neural networks are easily attacked by imperceptible perturbation. Presently, adversarial training (AT) is the most effective method to enhance the robustness of the model against adversarial examples. However, because adversarial…

Visible-infrared cross-modality person re-identification is a challenging ReID task, which aims to retrieve and match the same identity's images between the heterogeneous visible and infrared modalities. Thus, the core of this task is to…

Generalized Chinese Remainder Theorem (CRT) is a well-known approach to solve ambiguity resolution related problems. In this paper, we study the robust CRT reconstruction for multiple numbers from a view of statistics. To the best of our…

As a core step in structure-from-motion and SLAM, robust feature detection and description under challenging scenarios such as significant viewpoint changes remain unresolved despite their ubiquity. While recent works have identified the…

Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt…

Density reconstruction from X-ray projections is an important problem in radiography with key applications in scientific and industrial X-ray computed tomography (CT). Often, such projections are corrupted by unknown sources of noise and…

Difference features obtained by comparing the images of two periods play an indispensable role in the change detection (CD) task. However, a pair of bi-temporal images can exhibit diverse changes, which may cause various difference…

Existing deep multi-object tracking (MOT) approaches first learn a deep representation to describe target objects and then associate detection results by optimizing a linear assignment problem. Despite demonstrated successes, it is…

Metric learning aims to build a distance metric typically by learning an effective embedding function that maps similar objects into nearby points in its embedding space. Despite recent advances in deep metric learning, it remains…

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new…

Transformers serve as the backbone architectures of Foundational Models, where domain-specific tokenizers allow them to adapt to various domains. Graph Transformers (GTs) have recently emerged as leading models in geometric deep learning,…

Understanding how deep neural networks learn representations remains a central challenge in machine learning theory. In this work, we propose a feature-centric framework for analyzing neural network training by relating weight updates to…

This paper concerns the research problem of point cloud registration to find the rigid transformation to optimally align the source point set with the target one. Learning robust point cloud registration models with deep neural networks has…

Image reconstruction from insufficient data is common in computed tomography (CT), e.g., image reconstruction from truncated data, limited-angle data and sparse-view data. Deep learning has achieved impressive results in this field.…

Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the…

Objective functions that optimize deep neural networks play a vital role in creating an enhanced feature representation of the input data. Although cross-entropy-based loss formulations have been extensively used in a variety of supervised…

Visual Multi-Object Tracking (MOT) is a crucial component of robotic perception, yet existing Tracking-By-Detection (TBD) methods often rely on 2D cues, such as bounding boxes and motion modeling, which struggle under occlusions and…

Designing a robust affinity model is the key issue in multiple target tracking (MTT). This paper proposes a novel affinity model by learning feature representation and distance metric jointly in a unified deep architecture. Specifically, we…

Click-through rate (CTR) prediction is widely used in academia and industry. Most CTR tasks fall into a feature embedding \& feature interaction paradigm, where the accuracy of CTR prediction is mainly improved by designing practical…