Few-Shot Referring Relationships in Videos
Yogesh Kumar, Anand Mishra
2023年份
1顶会引用
摘要
github.io/projects/refRelations/ <helicopter, fly above, train> <plane, fly above, truck> Support Set video-1 video-2 video-3 video-4 Test video Output fall off Frequency Predicate Accuracy (a) Problem Setup (c) Accuracy Distribution <bird, fly above, person> <plane, fly above, plane> <plane, fly above, person> (b) Predicate Distribution ride a belief propagation-based message passing on the random field to obtain the spatiotemporal localization or subject and object trajectories. We perform extensive experiments using two public benchmarks, namely ImageNet-VidVRD and VidOR, and compare the proposed approach with competitive baselines to assess its efficacy.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper7
- Interventional Video Relation DetectionYicong Li, Xun Yang, Xindi Shang, Tat-Seng ChuaACM MM 2021 · 被引用 61 次
- Fine-Grained Predicates Learning for Scene Graph GenerationXinyu Lyu, Lianli Gao, Yuyu Guo, Zhou Zhao 等CVPR 2022 · 被引用 48 次
- Dynamic Scene Graph Generation via Anticipatory Pre-trainingYiming Li, Xiaoshan Yang, Changsheng XuCVPR 2022 · 被引用 38 次
- One-Shot Learning for Long-Tail Visual Relation DetectionWeitao Wang, Meng Wang, Sen Wang, Guodong Long 等AAAI 2020 · 被引用 20 次
- VRDFormer: End-to-End Video Visual Relation Detection with TransformersSipeng Zheng, Shizhe Chen, Qin JinCVPR 2022 · 被引用 16 次
相关 Paper
- Video Relation Detection via Multiple Hypothesis AssociationZixuan Su, Xindi Shang, Jingjing Chen, Yu-Gang Jiang 等ACM MM 2020 · 被引用 37 次
- Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global ContextChenchen Liu, Yang Jin, Kehan Xu, Guoqiang Gong 等CVPR 2020
- Video Visual Relation Detection via Iterative InferenceXindi Shang, Yicong Li, Junbin Xiao, Wei Ji 等ACM MM 2021 · 被引用 41 次
- VrdONE: One-stage Video Visual Relation DetectionXinjie Jiang, Chenxi Zheng, Xuemiao Xu, Bangzhen Liu 等ACM MM 2024 · 被引用 1 次
- Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation DetectionKaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao 等ICLR 2023 · 被引用 9 次
