论文阅读笔记整理合集

视频关系预测相关

1. Ji J , Krishna R , Li F F , et al. Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
   一个同时提供动作标签和时空场景图标签的大型视频数据集合 Action Genome
   论文阅读：Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
2. Cong Y , Liao W , Ackermann H , et al. Spatial-Temporal Transformer for Dynamic Scene Graph Generation[J]. 2021.
   用时空上下文的Transformer生成动态场景图 STTran
   论文阅读：Spatial-Temporal Transformer for Dynamic Scene Graph Generation
3. Shang X , Ren T , Guo J , et al. Video Visual Relation Detection[C]// the 2017 ACM. ACM, 2017.
   视频视觉关系预测方法VidVRD
   论文阅读：Video Visual Relation Detection
4. Teng Y , Wang L , Li Z , et al. Target Adaptive Context Aggregation for Video Scene Graph Generation[J]. 2021.
   视频场景图中的目标自适应上下文聚合 TRACE
   论文阅读：Target Adaptive Context Aggregation for Video Scene Graph Generation
5. Liu C , Jin Y , Xu K , et al. Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global Context[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
   超越短片段：基于时空上下文的视频关系检测 VID with Spatio-Temporal Global Contex
   论文阅读：Beyond Short-Term Snippet: Video Relation Detection with Spatio-Temporal Global Contex
6. 基于迭代推理的视频视觉关系检测 VidVRD-II
   论文阅读：Video Visual Relation Detection via Iterative Inference