Scene Parsing

[NeurIPS23] ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
The challenge of replicating research results has posed a significant impediment to the field of molecular biology. The advent of …
PDF Cite Code Dataset Poster Video Supp Web 北大AI院官微
[NeurIPS23] ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
[NeurIPS23] ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
Understanding the behavior of non-human primates is crucial for improving animal welfare, modeling social behavior, and gaining …
PDF Cite Code Poster Video Supp Web Dataset Examples Request Dataset 北大AI院官微
[NeurIPS23] ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
[ICLR23] Understanding Embodied Reference with Touch-Line Transformer
We study embodied reference understanding, the task of locating referents using embodied gestural signals and language references. …
PDF Cite Code Poster Video Web 北大新闻网 北大AI院官网 北大新工科官微 北大AI院官微
[ICLR23] Understanding Embodied Reference with Touch-Line Transformer
Visually Grounded Reasoning
[Vision meets Cognition] Topics include affordance, container, functionality, hoi, intent, scene parsing, scene reconstruction, and …
Aug 1, 2022
Visually Grounded Reasoning
[ICCV21] YouRefIt: Embodied Reference Understanding with Language and Gesture
We study the machine’s understanding of embodied reference: One agent uses both language and gesture to refer to an object to …
PDF Cite Code Dataset Poster Video Supp Web
[ICCV21] YouRefIt: Embodied Reference Understanding with Language and Gesture
[CVPR21] Learning Triadic Belief Dynamics in Nonverbal Communication from Videos
Humans possess a unique social cognition capability; nonverbal communication can convey rich social information among agents. In …
PDF Cite Code Dataset Video Supp
[CVPR21] Learning Triadic Belief Dynamics in Nonverbal Communication from Videos
[ECCV20] LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
Understanding and interpreting human actions is a long-standing challenge and a critical indicator of perception in artificial …
PDF Cite Code Dataset Supp Presentation Web
[ECCV20] LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
[ICRA20] Joint Inference of States, Robot Knowledge, and Human (False-)Beliefs
Aiming to understand how human (false-)belief—a core socio-cognitive ability—would affect human interactions with robots, …
PDF Cite Video Presentation
[ICRA20] Joint Inference of States, Robot Knowledge, and Human (False-)Beliefs
[NeurIPS19] PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate …
PDF Cite Poster Supp
[NeurIPS19] PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
[ICCV19] Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic …
PDF Cite Code Poster Video Supp Web
[ICCV19] Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense