What Happened 3 Seconds Ago? Inferring the Past with Thermal Imaging
Zitian Tang, Wenjie Ye, Wei-Chiu Ma, Hang Zhao
2023Year
4Top-tier citations
Abstract
Choices Now Choices Now What was the person doing? Figure 1. Can you tell what the person was doing 3 seconds ago? Inferring past human motions based on RGB images suffers from huge uncertainty. See the answers in Fig. 2.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext db4ab903-42c7-4e4a-9142-146104aa940eCited by top-tier papers4
- Projecting Trackable Thermal Patterns for Dynamic Computer VisionMark Sheinin, Aswin C. Sankaranarayanan, Srinivasa G. NarasimhanCVPR 2024 · 3 citations
- 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal DiffusionMinchong Chen, Xiaoyun Yuan, Junzhe Wan, Jianing Zhang et al.CVPR 2026 · 2 citations
- CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular FusionShoubin Yu, Jaehong Yoon, Mohit BansalICLR 2025
- Self-Supervised Spatial Correspondence Across ModalitiesAyush Shrivastava, Andrew OwensCVPR 2025
Builds on8
- Learning Trajectory Dependencies for Human Motion PredictionWei Mao, Miaomiao Liu, Mathieu Salzmann, Hongdong LiICCV 2019 · 534 citations
- Human Motion Prediction via Spatio-Temporal InpaintingAlejandro Hernandez Ruiz, Jürgen Gall, Francesc MorenoICCV 2019 · 233 citations
- Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New BaselinePengyu Zhang, Jie Zhao, Dong Wang, Huchuan Lu et al.CVPR 2022 · 225 citations
- Edge-Aware Guidance Fusion Network for RGB-Thermal Scene ParsingWujie Zhou, Shaohua Dong, Caie Xu, Yaguan QianAAAI 2022 · 151 citations
- Predicting 3D Human Dynamics From VideoJason Y. Zhang, Panna Felsen, Angjoo Kanazawa, Jitendra MalikICCV 2019 · 115 citations
Related papers
- Use the Force, Luke! Learning to Predict Physical Forces by Simulating EffectsKiana Ehsani, Shubham Tulsiani, Saurabh Gupta, Ali Farhadi et al.CVPR 2020
- Inferring the Future by Imagining the PastKartik Chandra, Tony Chen, Tzu-Mao Li, Jonathan Ragan-Kelley et al.NeurIPS 2023 · 7 citations
- RoHM: Robust Human Motion Reconstruction via DiffusionSiwei Zhang, Bharat Lal Bhatnagar, Yuanlu Xu, Alexander Winkler et al.CVPR 2024 · 11 citations
- Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal InputJian Wang, Rishabh Dabral, Diogo C. Luvizon, Zhe Cao et al.CVPR 2025
- Human-Aware Object Placement for Visual Environment ReconstructionHongwei Yi, Chun-Hao P. Huang, Dimitrios Tzionas, Muhammed Kocabas et al.CVPR 2022 · 61 citations
