https://deepai.org/publication/agqa-2-0-an-updated-benchmark-for-compositional-spatio-temporal-reasoning
AGQA 2.0: An Updated Benchmark for Compositional Spatio-Temporal Reasoning | DeepAI
Apr 12, 2022 - 04/12/22 - Prior benchmarks have analyzed models' answers to questions about videos in order to measure visual compositional reasoning. Actio...
spatio temporal reasoning2 0
https://deepai.org/publication/agqa-a-benchmark-for-compositional-spatio-temporal-reasoning
AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning | DeepAI
Mar 30, 2021 - 03/30/21 - Visual events are a composition of temporal actions involving actors spatially interacting with objects. When developing computer ...
spatio temporal reasoningbenchmarkcompositionaldeepai
https://www.sri.com/publication/computer-vision-pubs/sasra-semantically-aware-spatio-temporal-reasoning-agent-for-vision-and-language-navigation-in-continuous-environments/
SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in...
May 4, 2023 - This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments.
spatio temporal reasoning
https://openreview.net/forum?id=M7pFDngBgm
STaR: Benchmarking Spatio-Temporal Reasoning for Systematic Generalization | OpenReview
Systematic generalization is the ability of a machine learning model to perform well on a family of test examples that are out-of-distribution with respect to...
spatio temporal reasoningstarbenchmarkingsystematicgeneralization
https://huggingface.co/papers/2503.19355
Paper page - ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language...
Join the discussion on this paper page
https://openreview.net/forum?id=C6EJi0SS7j
ST(OR)$^2$: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room |...
This work proposes a novel surgical activity recognition approach that exploits object-level dynamics. We show superior performance on sample-efficiency...