Skip to search formSkip to main contentSkip to account menu

NUS-WIDE: a real-world web image database from National University of Singapore

The benchmark results indicate that it is possible to learn effective models from sufficiently large image dataset to facilitate general image retrieval and four research issues on web image annotation and retrieval are identified.
View on ACM (opens in a new tab)

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Improved representations of quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations are designed.
View PDF on arXiv (opens in a new tab)

Nonconvex Nonsmooth Low Rank Minimization via Iteratively Reweighted Nuclear Norm

This paper proposes to use a family of nonconvex surrogates of L0-norm on the singular values of a matrix to approximate the rank function, and proves that the IRNN decreases the objective function value monotonically, and any limit point is a stationary point.
View on IEEE (opens in a new tab)

Outer Product-based Neural Collaborative Filtering

Extensive experiments demonstrate the effectiveness of the proposed ONCF framework, in particular, the positive effect of using outer product to model the correlations between embedding dimensions in the low level of multi-layer neural recommender model.
View PDF on arXiv (opens in a new tab)

Generalized Nonconvex Nonsmooth Low-Rank Minimization

In theory, it is proved that IRNN decreases the objective function value monotonically, and any limit point is a stationary point, which enhances the low-rank matrix recovery compared with state-of-the-art convex algorithms.
View on IEEE (opens in a new tab)

Causal Intervention for Weakly-Supervised Semantic Segmentation

A structural causal model to analyze the causalities among images, contexts, and class labels is proposed and a new method: Context Adjustment (CONTA) is developed, to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model.
View PDF on arXiv (opens in a new tab)

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior

A temporal sharpness prior to constrain the deep CNN model to help the latent frame restoration and it is shown that exploring the domain knowledge of video deblurring is able to make the deepCNN model more compact and efficient.
View on IEEE (opens in a new tab)

Richer Convolutional Features for Edge Detection

RCF encapsulates all convolutional features into more discriminative representation, which makes good usage of rich feature hierarchies, and is amenable to training via backpropagation, and achieves state-of-the-art performance on several available datasets.
View on IEEE (opens in a new tab)

Human Parsing with Contextualized Convolutional Neural Network

In this work, we address the human parsing task with a novel Contextualized Convolutional Neural Network (Co-CNN) architecture, which well integrates the cross-layer context, global image-level…
View on IEEE (opens in a new tab)

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

This paper explores a completely novel and different perspective to perform LQE – based on the learned distributions of the four parameters of the bounding box – and develops a considerably lightweight Distribution-Guided Quality Predictor (DGQP) for reliable LqE based on GFLV1, thus producing GFLv2.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)