Vision Datasets Understanding Open-Domain Retrieval Under Multi-Modal Settings Gaze Estimation and Prediction in the Wild Image Matching: Local Features and Beyond Sketch-Oriented Deep Learning Omnidirectional Computer Vision in Research and Industry
Schuller; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2382-2391 Abstract This paper presents our contribution to the 3rd Affective Behavior Analysis in-the-Wild (ABAW) challenge. Exploitin...
Rongjie Li, Songyang Zhang, Xuming He; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 19486-19496 Abstract Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most pre...
Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 19174-19183 Abstract Mixup is a powerful data augmentation method that interpolates between...
Tomáš Souček, Jean-Baptiste Alayrac, Antoine Miech, Ivan Laptev, Josef Sivic; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 13956-13966 Abstract Human actions often induce changes of object states such as "cutting an apple", "c...
Fa-Ting Hong, Longhao Zhang, Li Shen, Dan Xu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 3397-3406 Abstract Talking head video generation aims to produce a synthetic human face video that contains the...
Multi-Granularity Alignment Domain Adaptation for Object Detection Wenzhang Zhou, Dawei Du, Libo Zhang, Tiejian Luo, Yanjun Wu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 9581-9590
Yutong Dai, Brian Price, He Zhang, Chunhua Shen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 11707-11716 Abstract Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Com...
Wonhui Park, Dongkwon Jin, Chang-Su Kim; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 2667-2675 Abstract Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this p...
Dongming Wu, Xingping Dong, Ling Shao, Jianbing Shen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 4996-5005 Referring video object segmentation (RVOS) is a challenging language-guided video grounding task, which requires compr...