More Like this

1. Multiview Scene Graph

   Zhang, Juexiao; Zhu, Gao; Li, Sihang; Liu, Xinhao; Song, Haorui; Tang, Xinran; Feng, Chen (December 2024, Advances in Neural Information Processing Systems)
2. Self Supervised Scene Adaptation

   Zhang, Z.; Hoai, M. (June 2023, IEEE/CVF)
3. Scene layout priming relies primarily on low-level features rather than scene layout

   https://doi.org/10.1167/19.1.14  

   Shafer-Skelton, Anna; Brady, Timothy F. (January 2019, Journal of Vision)
4. Overt attentional correlates of memorability of scene images and their relationships to scene semantics

   https://doi.org/10.1167/jov.20.9.2  

   Lyu, Muxuan; Choe, Kyoung Whan; Kardan, Omid; Kotabe, Hiroki P.; Henderson, John M.; Berman, Marc G. (September 2020, Journal of Vision)

   null (Ed.)
5. Scene-level Programming by Demonstration

   Zeng, Zhen; Zhou, Zheming; Sui, Zhiqiang; Jenkins, Odest Chadwicke (April 2017, arXiv.org)

   Scene-level Programming by Demonstration (PbD) is faced with an important challenge - perceptual uncertainty. Addressing this problem, we present a scene-level PbD paradigm that programs robots to perform goal-directed manipulation in unstructured environments with grounded perception. Scene estimation is enabled by our discriminatively-informed generative scene estimation method (DIGEST). Given scene observations, DIGEST utilizes candidates from discriminative object detectors to generate and evaluate hypothesized scenes of object poses. Scene graphs are generated from the estimated object poses, which in turn is used in the PbD system for high-level task planning. We demonstrate that DIGEST performs better than existing method and is robust to false positive detections. Building a PbD system on DIGEST, we show experiments of programming a Fetch robot to set up a tray for delivery with various objects through demonstration of goal scenes. 

   more » « less