toggle visibility Search & Display Options
Select All    Deselect All [1–10] << 11 12 13 14 >>
List View
 | 
Citations
 | 
Details
  Records Links
Author Chengyi Zou; Shuai Wan; Tiannan Ji; Marc Gorriz Blanch; Marta Mrak; Luis Herranz edit  url
doi  openurl
  Title Chroma Intra Prediction with Lightweight Attention-Based Neural Networks Type Journal Article
  Year 2023 Publication IEEE Transactions on Circuits and Systems for Video Technology Abbreviated Journal TCSVT  
  Volume 34 Issue 1 Pages 549 - 560  
  Keywords (down)  
  Abstract Neural networks can be successfully used for cross-component prediction in video coding. In particular, attention-based architectures are suitable for chroma intra prediction using luma information because of their capability to model relations between difierent channels. However, the complexity of such methods is still very high and should be further reduced, especially for decoding. In this paper, a cost-effective attention-based neural network is designed for chroma intra prediction. Moreover, with the goal of further improving coding performance, a novel approach is introduced to utilize more boundary information effectively. In addition to improving prediction, a simplification methodology is also proposed to reduce inference complexity by simplifying convolutions. The proposed schemes are integrated into H.266/Versatile Video Coding (VVC) pipeline, and only one additional binary block-level syntax flag is introduced to indicate whether a given block makes use of the proposed method. Experimental results demonstrate that the proposed scheme achieves up to −0.46%/−2.29%/−2.17% BD-rate reduction on Y/Cb/Cr components, respectively, compared with H.266/VVC anchor. Reductions in the encoding and decoding complexity of up to 22% and 61%, respectively, are achieved by the proposed scheme with respect to the previous attention-based chroma intra prediction method while maintaining coding performance.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes MACO; LAMP Approved no  
  Call Number Admin @ si @ ZWJ2023 Serial 3875  
Permanent link to this record
 
 
Author Qingshan Chen; Zhenzhen Quan; Yifan Hu; Yujun Li; Zhi Liu; Mikhail Mozerov edit  url
openurl 
  Title MSIF: multi-spectrum image fusion method for cross-modality person re-identification Type Journal Article
  Year 2023 Publication International Journal of Machine Learning and Cybernetics Abbreviated Journal IJMLC  
  Volume Issue Pages  
  Keywords (down)  
  Abstract Sketch-RGB cross-modality person re-identification (ReID) is a challenging task that aims to match a sketch portrait drawn by a professional artist with a full-body photo taken by surveillance equipment to deal with situations where the monitoring equipment is damaged at the accident scene. However, sketch portraits only provide highly abstract frontal body contour information and lack other important features such as color, pose, behavior, etc. The difference in saliency between the two modalities brings new challenges to cross-modality person ReID. To overcome this problem, this paper proposes a novel dual-stream model for cross-modality person ReID, which is able to mine modality-invariant features to reduce the discrepancy between sketch and camera images end-to-end. More specifically, we propose a multi-spectrum image fusion (MSIF) method, which aims to exploit the image appearance changes brought by multiple spectrums and guide the network to mine modality-invariant commonalities during training. It only processes the spectrum of the input images without adding additional calculations and model complexity, which can be easily integrated into other models. Moreover, we introduce a joint structure via a generalized mean pooling (GMP) layer and a self-attention (SA) mechanism to balance background and texture information and obtain the regional features with a large amount of information in the image. To further shrink the intra-class distance, a weighted regularized triplet (WRT) loss is developed without introducing additional hyperparameters. The model was first evaluated on the PKU Sketch ReID dataset, and extensive experimental results show that the Rank-1/mAP accuracy of our method is 87.00%/91.12%, reaching the current state-of-the-art performance. To further validate the effectiveness of our approach in handling cross-modality person ReID, we conducted experiments on two commonly used IR-RGB datasets (SYSU-MM01 and RegDB). The obtained results show that our method achieves competitive performance. These results confirm the ability of our method to effectively process images from different modalities.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes LAMP Approved no  
  Call Number Admin @ si @ CQH2023 Serial 3885  
Permanent link to this record
 
 
Author Yaxing Wang; Abel Gonzalez-Garcia; Chenshen Wu; Luis Herranz; Fahad Shahbaz Khan; Shangling Jui; Jian Yang; Joost Van de Weijer edit  url
openurl 
  Title MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains Type Journal Article
  Year 2024 Publication International Journal of Computer Vision Abbreviated Journal IJCV  
  Volume 132 Issue Pages 490–514  
  Keywords (down)  
  Abstract Given the often enormous effort required to train GANs, both computationally as well as in dataset collection, the re-use of pretrained GANs largely increases the potential impact of generative models. Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. Mining effectively steers GAN sampling towards suitable regions of the latent space, which facilitates the posterior finetuning and avoids pathologies of other methods, such as mode collapse and lack of flexibility. Furthermore, to prevent overfitting on small target domains, we introduce sparse subnetwork selection, that restricts the set of trainable neurons to those that are relevant for the target dataset. We perform comprehensive experiments on several challenging datasets using various GAN architectures (BigGAN, Progressive GAN, and StyleGAN) and show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods. In addition, MineGAN can successfully transfer knowledge from multiple pretrained GANs. MineGAN.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes LAMP; MACO Approved no  
  Call Number Admin @ si @ WGW2024 Serial 3888  
Permanent link to this record
 
 
Author Shiqi Yang; Yaxing Wang; Joost Van de Weijer; Luis Herranz; Shangling Jui; Jian Yang edit  url
doi  openurl
  Title Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering Type Journal Article
  Year 2023 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI  
  Volume 45 Issue 12 Pages 15883-15895  
  Keywords (down)  
  Abstract Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g., due to data privacy or intellectual property). In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. Our method is based on the observation that target data, which might not align with the source domain classifier, still forms clear clusters. We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity. We observe that higher affinity should be assigned to reciprocal neighbors. To aggregate information with more context, we consider expanded neighborhoods with small affinity values. Furthermore, we consider the density around each target sample, which can alleviate the negative impact of potential outliers. In the experimental results we verify that the inherent structure of the target features is an important source of information for domain adaptation. We demonstrate that this local structure can be efficiently captured by considering the local neighbors, the reciprocal neighbors, and the expanded neighborhood. Finally, we achieve state-of-the-art performance on several 2D image and 3D point cloud recognition datasets.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes LAMP; MACO Approved no  
  Call Number Admin @ si @ YWW2023 Serial 3889  
Permanent link to this record
 
 
Author Vacit Oguz Yazici; Longlong Yu; Arnau Ramisa; Luis Herranz; Joost Van de Weijer edit  url
openurl 
  Title Main product detection with graph networks for fashion Type Journal Article
  Year 2024 Publication Multimedia Tools and Applications Abbreviated Journal MTAP  
  Volume 83 Issue Pages 3215–3231  
  Keywords (down)  
  Abstract Computer vision has established a foothold in the online fashion retail industry. Main product detection is a crucial step of vision-based fashion product feed parsing pipelines, focused on identifying the bounding boxes that contain the product being sold in the gallery of images of the product page. The current state-of-the-art approach does not leverage the relations between regions in the image, and treats images of the same product independently, therefore not fully exploiting visual and product contextual information. In this paper, we propose a model that incorporates Graph Convolutional Networks (GCN) that jointly represent all detected bounding boxes in the gallery as nodes. We show that the proposed method is better than the state-of-the-art, especially, when we consider the scenario where title-input is missing at inference time and for cross-dataset evaluation, our method outperforms previous approaches by a large margin.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes LAMP; MACO; 600.147; 600.167; 600.164; 600.161; 600.141; 601.309 Approved no  
  Call Number Admin @ si @ YYR2024 Serial 4017  
Permanent link to this record
Select All    Deselect All [1–10] << 11 12 13 14 >>
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: