Research map / Video / Video segmentation and tracking
Jointly Recognizing Object Fluents and Tasks in Egocentric Videos
Yang Liu, Ping Wei, Song-Chun Zhu
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 |
|---|---|---|---|
| use joint fluent-task hierarchical model instead of two-stream LSTM | fluent recognition · Unary fluents | accuracy: 0.861 -> 0.909 | Improved |
| use joint fluent-task hierarchical model instead of two-stream LSTM | fluent recognition · Binary fluents | accuracy: 0.846 -> 0.869 | Improved |
| use joint fluent-task hierarchical model instead of two-stream LSTM | fluent recognition · Overall fluents | accuracy: 0.855 -> 0.896 | Improved |
| use fluent-based hierarchical representation instead of CNN hit@1 | task recognition · Task recognition | accuracy: 0.90 -> 0.96 | Improved |
| add temporal LSTM over frame features to CNN hit@1 | task recognition · Task recognition | accuracy: 0.90 -> 0.87 | Hurt |
| add optical flow stream to spatial LSTM | fluent recognition · Binary fluents | accuracy: 0.820 -> 0.846 | Improved |
| replace single frame classification with spatial LSTM | fluent recognition · Binary fluents | accuracy: 0.836 -> 0.820 | Hurt |
Closest papers by meaning
- EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding (ICCV 2023 · similarity 0.87)
- Opening the Vocabulary of Egocentric Actions (NeurIPS 2023 · similarity 0.87)
- Action Scene Graphs for Long-Form Understanding of Egocentric Videos (CVPR 2024 · similarity 0.86)
- A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives (CVPR 2024 · similarity 0.85)
- Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions? (ICLR 2025 · similarity 0.85)
- Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning (ICLR 2025 · similarity 0.85)
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.
