2 papers
cs.CV2024
Temporally Grounding Instructional Diagrams in Unconstrained Videos
Jiahao Zhang, Frederic Z. Zhang, Cristian Rodriguez +3
We study the challenging problem of simultaneously localizing a sequence of queries in the form of instructional diagrams in a video. This requires understanding not only the indiv…
cs.CV2020
Spatially Conditioned Graphs for Detecting Human-Object Interactions
Frederic Z. Zhang, Dylan Campbell, Stephen Gould
We address the problem of detecting human-object interactions in images using graphical neural networks. Unlike conventional methods, where nodes send scaled but otherwise identica…