Search Results - Proceedings of the IEEE/CVF Conference on Computer Vision AND Pattern Recognition*

Subspace-PnP: A Geometric Constraint Loss for Mutual Assistance of Depth and Optical Flow Estimation by 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…”
Get full text

Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio- Visual Event Perception by Gao, Junyu, Chen, Mengyuan, Xu, Changsheng

“…With only video-level event labels, this paper targets at the task of weakly-supervised audio-visual event perception (WS-AVEP), which aims to temporally…”
Get full text

Two-stream lightweight sign language transformer by 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…”
Get full text

MTPose: Human Pose Estimation with High-Resolution Multi-scale Transformers by Wang, Rui, Geng, Fudi, Wang, Xiangyang

“…HRNet (High-Resolution Networks) as reported by Sun et al. (in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2019…”
Get full text

Staged encoder training for cross-camera person re-identification by Xu, Zhi, Yang, Jiawei, Liu, Yuxuan, Zhao, Longyang, Liu, Jiajia

“…As a cross-camera retrieval problem, person re-identification (ReID) suffers from image style variations caused by camera parameters, lighting and other reasons, which will seriously affect the model recognition accuracy…”
Get full text

Multi-cue SORT: integrating weak cues with appearance and motion for multi-object tracking by Liang, Hong, Xu, Mingchen, Zhang, Qian, Shao, Mingwen

“…The objective of multi-object tracking (MOT) is to accurately detect and track all objects within a continuous sequence while maintaining unique identifiers…”
Get full text

VizWiz Grand Challenge: Answering Visual Questions from Blind People by 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…”
Get full text

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

“…In this paper, we introduce a new type of sensing modality, the Dynamic Vision Sensors (Event Cameras…”
Get full text

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition by Meng, Lingchen, Li, Hengduo, Chen, Bor-Chun, Lan, Shiyi, Wu, Zuxuan, Jiang, Yu-Gang, Lim, Ser-Nam

“…Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of tasks recently…”
Get full text

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision by Yang, Chenyu, Chen, Yuntao, Tian, Hao, Tao, Chenxin, Zhu, Xizhou, Zhang, Zhaoxiang, Huang, Gao, Li, Hongyang, Qiao, Yu, Lu, Lewei, Zhou, Jie, Dai, Jifeng

“…We present a novel bird's-eye-view (BEV) detector with perspective supervision, which converges faster and bet-suits modern image backbones…”
Get full text

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition by Wu, Chao-Yuan, Li, Yanghao, Mangalam, Karttikeya, Fan, Haoqi, Xiong, Bo, Malik, Jitendra, Feichtenhofer, Christoph

“…While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet…”
Get full text

Exploring Self-Attention for Image Recognition by Zhao, Hengshuang, Jia, Jiaya, Koltun, Vladlen

“…Recent work has shown that self-attention can serve as a basic building block for image recognition models…”
Get full text

X3D: Expanding Architectures for Efficient Video Recognition by Feichtenhofer, Christoph

“…This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network…”
Get full text

Revisiting Skeleton-based Action Recognition by Duan, Haodong, Zhao, Yue, Chen, Kai, Lin, Dahua, Dai, Bo

“… Many skeleton-based action recognition methods adopt GCNs to extract features on top of human skeletons…”
Get full text

Skeleton-Based Action Recognition With Shift Graph Convolutional Network by Cheng, Ke, Zhang, Yifan, He, Xiangyu, Chen, Weihan, Cheng, Jian, Lu, Hanqing

“…Action recognition with skeleton data is attracting more attention in computer vision…”
Get full text

From Recognition to Cognition: Visual Commonsense Reasoning by Zellers, Rowan, Bisk, Yonatan, Farhadi, Ali, Choi, Yejin

“…Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels…”
Get full text

MagFace: A Universal Representation for Face Recognition and Quality Assessment by Meng, Qiang, Zhao, Shichao, Huang, Zhida, Zhou, Feng

“…The performance of face recognition system degrades when the variability of the acquired faces increases…”
Get full text

AdaFace: Quality Adaptive Margin for Face Recognition by Kim, Minchul, Jain, Anil K., Liu, Xiaoming

“…Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded…”
Get full text

Improving Calibration for Long-Tailed Recognition by 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…”
Get full text

BBN: Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition by Zhou, Boyan, Cui, Quan, Wei, Xiu-Shen, Chen, Zhao-Min

“…Our work focuses on tackling the challenging but natural visual recognition task of long-tailed data distribution (i.e…”
Get full text