8,450 Result(s)
-
Article
Cross-Architecture Knowledge Distillation
The Transformer network architecture has gained attention due to its ability to learn global relations and its superior performance. To boost performance, it is natural to distill complementary knowledge from ...
-
Article
SplatFlow: Learning Multi-frame Optical Flow via Splatting
The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggl...
-
Article
Cross-Modal Fusion and Progressive Decoding Network for RGB-D Salient Object Detection
Most existing RGB-D salient object detection (SOD) methods tend to achieve higher performance by integrating additional modules, such as feature enhancement and edge generation. There is no doubt that these mo...
-
Article
Hugs Bring Double Benefits: Unsupervised Cross-Modal Hashing with Multi-granularity Aligned Transformers
Unsupervised cross-modal hashing (UCMH) has been commonly explored to support large-scale cross-modal retrieval of unlabeled data. Despite promising progress, most existing approaches are developed on convolut...
-
Article
Open AccessDomain Generalization with Small Data
In this work, we propose to tackle the problem of domain generalization in the context of insufficient samples. Instead of extracting latent feature embeddings based on deterministic models, we propose to learn a...
-
Article
Open AccessEvent-Based Non-rigid Reconstruction of Low-Rank Parametrized Deformations from Contours
Visual reconstruction of fast non-rigid object deformations over time is a challenge for conventional frame-based cameras. In recent years, event cameras have gained significant attention due to their bio-insp...
-
Article
Softmax-Free Linear Transformers
Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity in both computation and memory...
-
Article
Deep Learning Technique for Human Parsing: A Survey and Outlook
Human parsing aims to partition humans in image or video into multiple pixel-level semantic parts. In the last decade, it has gained significantly increased interest in the computer vision community and has be...
-
Article
Open AccessRetraction Note: Using hardware counter-based performance model to diagnose scaling issues of HPC applications
-
Article
Exploration and Exploitation of Unlabeled Data for Open-Set Semi-supervised Learning
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples. Un...
-
Article
Correction: Digital human and embodied intelligence for sports science: advancements, opportunities and prospects
-
Article
Retraction Note: Gray relational clustering model for intelligent guided monitoring horizontal wells
-
Article
An automatic framework for quadrilateral surface reconstruction with partitions from 3D point clouds
Currently, three-dimensional (3D) point clouds are widely used in the gaming and film industries. Inspired by the reverse process of polycube-based parametrical map**, we present an automatic framework that ...
-
Article
Multi-scale deep echo state network for time series prediction
Echo state network (ESN) has widely attracted many researchers due to its training process without backpropagation. However, it is hard for single ESN to fit those complex and polytrophic situations. Under thi...
-
Article
Correction to: HierMDS: a hierarchical multi-document summarization model with global–local document dependencies
-
Article
Blockfd: blockchain-based federated distillation against poisoning attacks
Federated learning (FL) is a novel framework that distributes the model training to the participant devices to realize privacy-preserving machine learning. To achieve this, clients upload the parameters of the...
-
Article
DCSG: data complement pseudo-label refinement and self-guided pre-training for unsupervised person re-identification
Existing unsupervised person re-identification (Re-ID) methods use clustering to generate pseudo-labels that are generally noisy, and initializing the model with ImageNet pre-training weights introduces a larg...
-
Article
Open AccessPersonalized hairstyle and hair color editing based on multi-feature fusion
In the metaverse era, virtual design of hairstyle becomes very popular for personalized aesthetics. As hair design tasks can be decomposed into hair attribute editing and generation, the development of generat...
-
Article
Retraction Note: Fast and robust absolute camera pose estimation with known focal length
-
Article
Open AccessFew-shot anime pose transfer
In this paper, we propose a few-shot method for pose transfer of anime characters—given a source image of an anime character and a target pose, we transfer the pose of the target to the source character. Despi...