ProcObject-10K is the first benchmark for object-centric procedural reasoning in videos that exposes a large gap where models answer questions plausibly but fail to ground their answers in the correct video segments.
Trackverse: A large- scale object-centric video dataset for image-level representa- tion learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos
ProcObject-10K is the first benchmark for object-centric procedural reasoning in videos that exposes a large gap where models answer questions plausibly but fail to ground their answers in the correct video segments.