Suchergebnisse - Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)

EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors von Wang, Yanxiang, Du, Bowen, Shen, Yiran, Wu, Kai, Zhao, Guangrong, Sun, Jianguo, Wen, Hongkai

“… However, those cameras only produce noisy and asynchronous events of intensity changes rather than frames, where conventional vision-based gait recognition algorithms can't be directly applied …”
Volltext

A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection von Chen, Zhihao, Zhu, Lei, Wan, Liang, Wang, Song, Feng, Wei, Heng, Pheng-Ann

“… Existing shadow detection methods suffer from an intrinsic limitation in relying on limited labeled datasets, and they may produce poor results in some complicated situations …”
Volltext

AdversarialNAS: Adversarial Neural Architecture Search for GANs von Gao, Chen, Chen, Yunpeng, Liu, Si, Tan, Zhenxiong, Yan, Shuicheng

“… Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields …”
Volltext

Bottleneck Transformers for Visual Recognition von Srinivas, Aravind, Lin, Tsung-Yi, Parmar, Niki, Shlens, Jonathon, Abbeel, Pieter, Vaswani, Ashish

“… We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation …”
Volltext

DeepLIIF: An Online Platform for Quantification of Clinical Pathology Slides von Ghahremani, Parmida, Marino, Joseph, Dodds, Ricardo, Nadeem, Saad

“… We present DeepLIIF (https://deepliif.org), a first free online platform for efficient and reproducible IHC scoring …”
Volltext

Google Landmarks Dataset v2 - A Large-Scale Benchmark for Instance-Level Recognition and Retrieval von Weyand, Tobias, Araujo, Andre, Cao, Bingyi, Sim, Jack

“… While image retrieval and instance recognition techniques are progressing rapidly, there is a need for challenging datasets to accurately measure their performance -- while posing novel challenges …”
Volltext

Masked-attention Mask Transformer for Universal Image Segmentation von Cheng, Bowen, Misra, Ishan, Schwing, Alexander G., Kirillov, Alexander, Girdhar, Rohit

“… (50.1 AP on COCO) and semantic segmentation (57.7 mIoU onADE20K) …”
Volltext

MICAI 2009 : advances in artificial intelligence : 8th Mexican International Conference on Artificial Intelligence, Guanajuato, México, November 9-13, 2009 : proceedings von Mexican International Conference on Artificial Intelligence, Hernández Aguirre, Arturo, Borja, Raúl Monroy, Reyes García, Carlos Alberto

“… The Mexican International Conference on Arti?cial Intelligence (MICAI), a yearly international conference organized by the Mexican Society for Arti?cial Intelligence (SMIA …”
Volltext

MobileOne: An Improved One millisecond Mobile Backbone von Vasu, Pavan Kumar Anasosalu, Gabriel, James, Zhu, Jeff, Tuzel, Oncel, Ranjan, Anurag

“… However, these metrics may not correlate well with latency of the network when deployed on a mobile device …”
Volltext

Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection von Haliassos, Alexandros, Vougioukas, Konstantinos, Petridis, Stavros, Pantic, Maja

“… ), thus learning rich internal representations related to natural mouth motion. A temporal network is subsequently finetuned on fixed mouth embeddings of real and …”
Volltext

Deformable Siamese Attention Networks for Visual Object Tracking von Yu, Yuechen, Xiong, Yilei, Huang, Weilin, Scott, Matthew R.

“… However, the target template is not updated online, and the features of target template and search image are computed independently in a Siamese architecture …”
Volltext

Deformable ConvNets V2: More Deformable, Better Results von Zhu, Xizhou, Hu, Han, Lin, Stephen, Dai, Jifeng

“… To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training …”
Volltext

GLIGEN: Open-Set Grounded Text-to-Image Generation von Li, Yuheng, Liu, Haotian, Wu, Qingyang, Mu, Fangzhou, Yang, Jianwei, Gao, Jianfeng, Li, Chunyuan, Lee, Yong Jae

“… enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism …”
Volltext

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks von Dong, Yinpeng, Pang, Tianyu, Su, Hang, Zhu, Jun

“… By optimizing a perturbation over an ensemble of translated images, the generated adversarial example is less sensitive to the white-box model being attacked and has better transferability …”
Volltext

Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources von Abdelnabi, Sahar, Hasan, Rakibul, Fritz, Mario

“… Misinformation is now a major problem due to its poten-tial high risks to our core democratic and societal values and orders. Out-of-context misinformation is …”
Volltext

Fast Online Object Tracking and Segmentation: A Unifying Approach von Wang, Qiang, Zhang, Li, Bertinetto, Luca, Hu, Weiming, Torr, Philip H.S.

“… Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second …”
Volltext

Dense Contrastive Learning for Self-Supervised Visual Pre-Training von Wang, Xinlong, Zhang, Rufeng, Shen, Chunhua, Kong, Tao, Li, Lei

“… To date, most existing self-supervised learning methods are designed and optimized for image classification …”
Volltext

Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation CVPR Proceedings von Williams, Phoenix Neale, Li, Ke

“… Deep neural networks (DNNs) are susceptible to adversarial images, raising concerns about their reliability in safety-critical tasks. Sparse adversarial …”
Volltext

Token Contrast for Weakly-Supervised Semantic Segmentation von Ru, Lixiang, Zheng, Heliang, Zhan, Yibing, Du, Bo

“… Though the recent Vision Transformer (ViT) can remedy this flaw, we observe it also brings the over-smoothing issue, i.e …”
Volltext

Multi-class Token Transformer for Weakly Supervised Semantic Segmentation von Xu, Lian, Ouyang, Wanli, Bennamoun, Mohammed, Boussaid, Farid, Xu, Dan

“… ). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer …”
Volltext