Related papers: Progressive Hard-case Mining across Pyramid Levels…
It is a common paradigm in object detection frameworks to treat all samples equally and target at maximizing the performance on average. In this work, we revisit this paradigm through a careful study on how different samples contribute to…
Existing studies on Quality Enhancement for Compressed Video (QECV) predominantly rely on known Quantization Parameters (QPs), employing distinct enhancement models per QP setting, termed non-blind methods. However, in real-world scenarios…
Multi-modal systems enhance performance in autonomous driving but face inefficiencies due to indiscriminate processing within each modality. Additionally, the independent feature learning of each modality lacks interaction, which results in…
The rapid advancement of deepfake generation techniques has intensified the need for robust and generalizable detection methods. Existing approaches based on reconstruction learning typically leverage deep convolutional networks to extract…
Remote sensing target detection aims to identify and locate critical targets within remote sensing images, finding extensive applications in agriculture and urban planning. Feature pyramid networks (FPNs) are commonly used to extract…
Stereo matching is the key step in estimating depth from two or more images. Recently, some tree-based non-local stereo matching methods have been proposed, which achieved state-of-the-art performance. The algorithms employed some tree…
Cross-view geo-localization (CVGL) between drone and satellite imagery remains challenging due to severe viewpoint gaps and the presence of hard negatives, which are visually similar but geographically mismatched samples. Existing mining or…
In this work, we aim to develop simple and efficient models for human mesh recovery (HMR) and its predecessor task, human pose estimation (HPE). State-of-the-art HMR methods, such as HMR2.0 and its successors, rely on large,…
Common object detection models consist of classification and regression branches, due to different task drivers, these two branches have different sensibility to the features from the same scale level and the same spatial location. The…
Integrating frame-based RGB cameras with event streams offers a promising solution for robust object detection under challenging dynamic conditions. However, the inherent heterogeneity and data redundancy of these modalities often lead to…
Model-heterogeneous personalized federated learning (MHPFL) enables FL clients to train structurally different personalized models on non-independent and identically distributed (non-IID) local data. Existing MHPFL methods focus on…
A novel approach for the fusion of heterogeneous object detection methods is proposed. In order to effectively integrate the outputs of multiple detectors, the level of ambiguity in each individual detection score is estimated using the…
The dominant multi-camera 3D detection paradigm is based on explicit 3D feature construction, which requires complicated indexing of local image-view features via 3D-to-2D projection. Other methods implicitly introduce geometric positional…
Grasping unknown objects from a single view has remained a challenging topic in robotics due to the uncertainty of partial observation. Recent advances in large-scale models have led to benchmark solutions such as GraspNet-1Billion.…
Class-agnostic object proposal generation is an important first step in many object detection pipelines. However, object proposals of modern systems are rather inaccurate in terms of segmentation and only roughly adhere to object…
The past few years have witnessed great progress in the domain of face recognition thanks to advances in deep learning. However, cross pose face recognition remains a significant challenge. It is difficult for many deep learning algorithms…
As one of the prevalent components, Feature Pyramid Network (FPN) is widely used in current object detection models for improving multi-scale object detection performance. However, its feature fusion mode is still in a misaligned and local…
Due to the effective performance of multi-scale feature fusion, Path Aggregation FPN (PAFPN) is widely employed in YOLO detectors. However, it cannot efficiently and adaptively integrate high-level semantic information with low-level…
Particle Filter(PF) is used extensively for estimation of target Non-linear and Non-gaussian state. However, its performance suffers due to inherent problem of sample degeneracy and impoverishment. In order to address this, we propose a…
Loss functions play an important role in training deep-network-based object detectors. The most widely used evaluation metric for object detection is Average Precision (AP), which captures the performance of localization and classification…