AI Paper Atlas

Research map / Video / Video segmentation and tracking

Jointly Recognizing Object Fluents and Tasks in Egocentric Videos

Yang Liu, Ping Wei, Song-Chun Zhu

ICCV 2017 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 34 citations (OpenAlex)

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 changedWhereMeasuredEffect
use joint fluent-task hierarchical model instead of two-stream LSTMfluent recognition · Unary fluentsaccuracy: 0.861 -> 0.909Improved
use joint fluent-task hierarchical model instead of two-stream LSTMfluent recognition · Binary fluentsaccuracy: 0.846 -> 0.869Improved
use joint fluent-task hierarchical model instead of two-stream LSTMfluent recognition · Overall fluentsaccuracy: 0.855 -> 0.896Improved
use fluent-based hierarchical representation instead of CNN hit@1task recognition · Task recognitionaccuracy: 0.90 -> 0.96Improved
add temporal LSTM over frame features to CNN hit@1task recognition · Task recognitionaccuracy: 0.90 -> 0.87Hurt
add optical flow stream to spatial LSTMfluent recognition · Binary fluentsaccuracy: 0.820 -> 0.846Improved
replace single frame classification with spatial LSTMfluent recognition · Binary fluentsaccuracy: 0.836 -> 0.820Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy