Research map / Large language models / AI and society
HAKE: A Knowledge Engine Foundation for Human Activity Understanding
Yong–Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li, Zuoyu Qiu, Liang Xu, Yue Xu, Hao-Shu Fang, Cewu Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add HAKE primitive reasoning | TIN · HICO-DET Full | mAP (%): 17.03 -> 23.22 | Improved |
| add HAKE primitive reasoning | TIN · HICO-DET Rare | mAP (%): 13.42 -> 23.16 | Improved |
| add HAKE primitive reasoning | VCL · HICO-DET Full | mAP (%): 23.63 -> 28.30 | Improved |
| add HAKE primitive reasoning | QPIC · HICO-DET Full | mAP (%): 29.07 -> 32.10 | Improved |
| add HAKE primitive reasoning | SlowFast · AVA val | mAP (%): 28.2 -> 29.3 | Improved |
| add HAKE primitive reasoning | LFB-Res-50-max · AVA val | mAP (%): 23.9 -> 26.8 | Improved |
| add HAKE for transfer | TIN · V-COCO | mAP (%): 54.2 -> 59.7 | Improved |
| add HAKE for transfer | TIN · Ambiguous-HOI | mAP (%): 8.22 -> 10.56 | Improved |
| add HAKE for transfer | DJ-RN · Ambiguous-HOI | mAP (%): 10.37 -> 12.68 | Improved |
| add HAKE for transfer | AVA-TF · AVA v2.1 image-based | mAP (%): 11.4 -> 15.6 | Improved |
| add logic rule evaluation and updating (ablation) | GT-HAKE · Ambiguous-HOI GT H-O boxes | mAP (%): 64.21 -> 68.20 | Improved |
| use both annotated and generated rules instead of annotated only (ablation) | GT-HAKE · Ambiguous-HOI GT H-O boxes | mAP (%): 66.89 -> 68.20 | Improved |
Closest papers by meaning
- MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition (NeurIPS 2025 · similarity 0.83)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.83)
- Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification (Student Abstract) (AAAI 2025 · similarity 0.82)
- Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning (AAAI 2025 · similarity 0.82)
- From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding (CVPR 2024 · similarity 0.82)
- Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
