Few-Shot Referring Relationships in Videos
Yogesh Kumar, Anand Mishra
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 1e8b7909-2f1c-41a0-8fbd-728f74ea5b8dCited by top-tier papers1
Ask how each one uses itBuilds on7
- Interventional Video Relation DetectionYicong Li, Xun Yang, Xindi Shang, Tat-Seng ChuaACM MM 2021 · 61 citations
- Fine-Grained Predicates Learning for Scene Graph GenerationXinyu Lyu, Lianli Gao, Yuyu Guo, Zhou Zhao et al.CVPR 2022 · 48 citations
- Dynamic Scene Graph Generation via Anticipatory Pre-trainingYiming Li, Xiaoshan Yang, Changsheng XuCVPR 2022 · 38 citations
- One-Shot Learning for Long-Tail Visual Relation DetectionWeitao Wang, Meng Wang, Sen Wang, Guodong Long et al.AAAI 2020 · 20 citations
- VRDFormer: End-to-End Video Visual Relation Detection with TransformersSipeng Zheng, Shizhe Chen, Qin JinCVPR 2022 · 16 citations
Related papers
- Video Relation Detection via Multiple Hypothesis AssociationZixuan Su, Xindi Shang, Jingjing Chen, Yu-Gang Jiang et al.ACM MM 2020 · 37 citations
- Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global ContextChenchen Liu, Yang Jin, Kehan Xu, Guoqiang Gong et al.CVPR 2020
- Video Visual Relation Detection via Iterative InferenceXindi Shang, Yicong Li, Junbin Xiao, Wei Ji et al.ACM MM 2021 · 41 citations
- VrdONE: One-stage Video Visual Relation DetectionXinjie Jiang, Chenxi Zheng, Xuemiao Xu, Bangzhen Liu et al.ACM MM 2024 · 1 citation
- Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation DetectionKaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao et al.ICLR 2023 · 9 citations
