AI Paper Atlas

Research map / Video / Video-language understanding

Temporal Tessellation: A Unified Approach for Video Analysis

Dotan Kaufman, Gil Levi, Tal Hassner, Lior Wolf

ICCV 2017 · Video › Video-language understanding · approach: Dense video captioning · 37 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
match clips in the joint semantics space instead of appearance space (ablation)Local Tessellation · LSMDC16CIDEr-D: .042 -> .098Improved
add unsupervised Viterbi temporal coherence to local tessellation (ablation)Tessellation · LSMDC16CIDEr-D: .098 -> .102Improved
add LSTM-predicted semantics dynamics (supervised) to local tessellation (ablation)Tessellation · LSMDC16CIDEr-D: .098 -> .109Improved
add LSTM-predicted semantics dynamics to unsupervised tessellation (ablation)Tessellation · LSMDC16BLEU-4: .007 -> .008Improved
add unsupervised temporal coherence to local tessellation (ablation)Tessellation · SumMeF-measure: 33.8 -> 41.4Improved
add supervised LSTM tessellation to local tessellation (ablation)Tessellation · SumMeF-measure: 33.8 -> 37.2Improved
use supervised instead of unsupervised tessellation (ablation)Tessellation · SumMeF-measure: 41.4 -> 37.2Hurt
add unsupervised temporal coherence to local tessellation (ablation)Tessellation · TVSumF-measure: 60.9 -> 64.1Improved
use supervised instead of unsupervised tessellation (ablation)Tessellation · TVSumF-measure: 64.1 -> 63.4Hurt
add context (supervised) to local tessellation (ablation)Tessellation · THUMOS'14 IoT 0.1mAP: 56.4 -> 61.1Improved
add context (supervised) to local tessellation (ablation)Tessellation · THUMOS'14 IoT 0.5mAP: 20.7 -> 23.3Improved
match in semantics space instead of appearance only (ablation)Local Tessellation · Greatest Hits loudnessMSE error: 0.35 -> 0.27Improved

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