paper-with-me

홈 › Papers

What Happened 3 Seconds Ago? Inferring the Past with Thermal Imaging

2023-04-26 · CVPR 2023 1 · Zitian Tang, Wenjie Ye, Wei-Chiu Ma, Hang Zhao

Inferring past human motion from RGB images is challenging due to the inherent uncertainty of the prediction problem. Thermal images, on the other hand, encode traces of past human-object interactions left in the environment via thermal radiation measurement. Based on this observation, we collect the first RGB-Thermal dataset for human motion analysis, dubbed Thermal-IM. Then we develop a three-stage neural network model for accurate past human pose estimation. Comprehensive experiments show that thermal cues significantly reduce the ambiguities of this task, and the proposed model achieves remarkable performance. The dataset is available at https://github.com/ZitianTang/Thermal-IM.

📄 PDF Abstract BibTeX arXiv:2304.13651

Code (1)

zitiantang/thermal-im 공식 구현

Tasks

Human-Object Interaction DetectionPose Estimation

Similar Papers 제목 키워드 기반

See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models

2025-10-06 · Kebin Contreras, Luis Toscano-Palomino, Mauro Dalla Mura, Jorge Bacca arxiv

Recovering the past from present observations is an intriguing challenge with potential applications in forensics and scene analysis. Thermal imaging, operating in the infrared range, provides access to otherwise invisib…

Image Reconstruction

Interpretable Apprenticeship Learning with Temporal Logic Specifications

2017-10-28 · Daniel Kasenberg, Matthias Scheutz

Recent work has addressed using formulas in linear temporal logic (LTL) as specifications for agents planning in Markov Decision Processes (MDPs). We consider the inverse problem: inferring an LTL specification from demo…

Multiobjective Optimization

Did that happen? Predicting Social Media Posts that are Indicative of what happened in a scene: A case study of a TV show

2022-06-01 · LREC 2022 6 · Anietie Andy, Reno Kriz, Sharath Chandra Guntuku, Derry Tanti Wijaya 외

While popular Television (TV) shows are airing, some users interested in these shows publish social media posts about the show. Analyzing social media posts related to a TV show can be beneficial for gaining insights abo…

MARPLE: A Benchmark for Long-Horizon Inference

2024-10-02 · Emily Jin, Zhuoyi Huang, Jan-Philipp Fränken, Weiyu Liu 외

Reconstructing past events requires reasoning across long time horizons. To figure out what happened, we need to use our prior knowledge about the world and human behavior and draw inferences from various sources of evid…

Your Learned Constraint is Secretly a Backward Reachable Tube

2025-01-26 · Mohamad Qadri, Gokul Swamy, Jonathan Francis, Michael Kaess 외

Inverse Constraint Learning (ICL) is the problem of inferring constraints from safe (i.e., constraint-satisfying) demonstrations. The hope is that these inferred constraints can then be used downstream to search for safe…