Suchergebnisse - 2018 IEEE/CVF Conference on Computer Vision AND Pattern Recognition*

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018) : Salt Lake City, Utah, USA 18-22 June 2018 von IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers

Volltext

Two-stream lightweight sign language transformer von Chen, Yuming, Mei, Xue, Qin, Xuan

“… Despite the recent progress of continuous sign language translation-based video, a variety of deep learning models are difficult to apply to the real-time …”
Volltext

VizWiz Grand Challenge: Answering Visual Questions from Blind People von Gurari, Danna, Li, Qing, Stangl, Abigale J., Guo, Anhong, Lin, Chi, Grauman, Kristen, Luo, Jiebo, Bigham, Jeffrey P.

“… The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial …”
Volltext

Subspace-PnP: A Geometric Constraint Loss for Mutual Assistance of Depth and Optical Flow Estimation von Chi, Cheng, Hao, Tianyu, Wang, Qingjie, Guo, Peng, Yang, Xin

“… , in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4654–4665, 2020; Ranjan et al., in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12240 …”
Volltext

Improving Calibration for Long-Tailed Recognition von Zhong, Zhisheng, Cui, Jiequan, Liu, Shu, Jia, Jiaya

“… Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and …”
Volltext

Disentangling Label Distribution for Long-tailed Visual Recognition von Hong, Youngkyu, Han, Seungju, Choi, Kwanghee, Seo, Seokjun, Kim, Beomsu, Chang, Buru

“… The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution …”
Volltext

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition von Li, Shuang, Gong, Kaixiong, Liu, Chi Harold, Wang, Yulin, Qiao, Feng, Cheng, Xinjing

“… Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the …”
Volltext

CVPR 2019: Call for Papers Deadline November 16: The 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition

Volltext

On the Duality Between Retinex and Image Dehazing von Galdran, Adrian, Bria, Alessandro, Alvarez-Gila, Aitor, Vazquez-Corral, Javier, Bertalmio, Marcelo

“… Retinex has been widely explored in the computer vision literature for image enhancement and other related tasks …”
Volltext

Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation von Jin, Yan, Li, Mengke, Lu, Yang, Cheung, Yiu-ming, Wang, Hanzi

“… Deep neural networks have made huge progress in the last few decades. However, as the real-world data often exhibits a long-tailed distribution, vanilla deep …”
Volltext

Collaborative Spatiotemporal Feature Learning for Video Action Recognition von Li, Chao, Zhong, Qiaoyong, Xie, Di, Pu, Shiliang

“… Spatiotemporal feature learning is of central importance for action recognition in videos …”
Volltext

Hybrid Task Cascade for Instance Segmentation von Chen, Kai, Pang, Jiangmiao, Wang, Jiaqi, Xiong, Yu, Li, Xiaoxiao, Sun, Shuyang, Feng, Wansen, Liu, Ziwei, Shi, Jianping, Ouyang, Wanli, Loy, Chen Change, Lin, Dahua

“… Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation …”
Volltext

Feature Denoising for Improving Adversarial Robustness von Xie, Cihang, Wu, Yuxin, Maaten, Laurens van der, Yuille, Alan L., He, Kaiming

“… Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests …”
Volltext

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation von Cheng, Bowen, Collins, Maxwell D., Zhu, Yukun, Liu, Ting, Huang, Thomas S., Adam, Hartwig, Chen, Liang-Chieh

“… In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up …”
Volltext

Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation von Ke, Liyiming, Li, Xiujun, Bisk, Yonatan, Holtzman, Ari, Gan, Zhe, Liu, Jingjing, Gao, Jianfeng, Choi, Yejin, Srinivasa, Siddhartha

“… We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the 2018 Room-to-Room (R2R …”
Volltext

Improving Semantic Segmentation via Video Propagation and Label Relaxation von Zhu, Yi, Sapra, Karan, Reda, Fitsum A., Shih, Kevin J., Newsam, Shawn, Tao, Andrew, Catanzaro, Bryan

“… Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology …”
Volltext

RSG: A Simple but Effective Module for Learning Imbalanced Datasets von Wang, Jianfeng, Lukasiewicz, Thomas, Hu, Xiaolin, Cai, Jianfei, Xu, Zhenghua

“… Imbalanced datasets widely exist in practice and are a great challenge for training deep neural models with a good generalization on infrequent classes. In …”
Volltext

PoTion: Pose MoTion Representation for Action Recognition von Choutas, Vasileios, Weinzaepfel, Philippe, Revaud, Jerome, Schmid, Cordelia

“… Most state-of-the-art methods for action recognition rely on a two-stream architecture that processes appearance and motion independently …”
Volltext

Learning Meta Face Recognition in Unseen Domains von Guo, Jianzhu, Zhu, Xiangyu, Zhao, Chenxu, Cao, Dong, Lei, Zhen, Li, Stan Z.

“… Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization …”
Volltext

Learning Imbalanced Data with Vision Transformers von Xu, Zhengzhuo, Liu, Ruikang, Yang, Shuo, Chai, Zenghao, Yuan, Chun

“… The real-world data tends to be heavily imbalanced and severely skew the data-driven deep neural networks, which makes Long-Tailed Recognition (LTR …”
Volltext