research
∙
07/30/2023
Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation
Video-based scene graph generation (VidSGG) is an approach that aims to ...
share
research
∙
04/25/2022
Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives
Reasoning about causal and temporal event relations in videos is a new d...
research
∙
12/08/2021
Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs
Today's VidSGG models are all proposal-based methods, i.e., they first g...
research
∙
08/19/2021
Video Relation Detection via Tracklet based Visual Transformer
Video Visual Relation Detection (VidVRD), has received significant atten...
research
∙
03/23/2020
Julia Language in Machine Learning: Algorithms, Applications, and Open Issues
Machine learning is driving development across many fields in science an...
research
∙
08/10/2019