AI Paper Atlas

Research map / Video / Video-language understanding

Bayesian Modeling of Temporal Coherence in Videos for Entity Discovery and Summarization

Adway Mitra, Soma Biswas, Chiranjib Bhattacharyya

TPAMI 2016 · Video › Video-language understanding · approach: Dense video captioning · 18 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
add joint temporal-segment modeling (TC-CRF over TC-CRP)TC-CRP · Maha65 entity discoveryPurity: 0.89 -> 0.97Improved
add temporal-coherence prior (TC-CRP over sHDP-HMM)sHDP-HMM · BBTs1e3 entity discoveryPurity: 0.76 -> 0.83Improved
use TC-CRF instead of TC-CRPTC-CRP · Maha66 entity discoveryPurity: 0.96 -> 0.91Hurt
Bayesian nonparametric methods vs constrained spectral clusteringTC-CRF · BBTs1e3 entity discoveryTracklet coverage: 0.09 -> 0.86Improved
add TC-CRF over sHDP-HMMsHDP-HMM · Maha81 entity discoveryTracklet coverage: 0.66 -> 0.80Improved
reduce tracklet size from R=10 to R=5 or R=1 (ablation)TC-CRF, TC-CRP, sHDP-HMM · entity discoveryPurity/coverageNo clear effect
reduce tracklet size to R=1 (ablation)SBMR · entity discoverymatrix rank: 120-130Hurt
online single-pass inference instead of offline Gibbs samplingTC-CRF · Maha81 entity discoveryPurity: 0.89 -> 0.71Hurt
TC-CRP junk component variance factor c from 2 to 4 (ablation)TC-CRP · Maha65 non-face discoveryPrecision: 0.88 -> 0.98Improved
TC-CRP junk component variance factor c from 2 to 5 (ablation)TC-CRP · Maha65 non-face discoveryRecall*: 106 -> 79Hurt
TC-CRP junk detection instead of KMeansKMeans · Maha65 non-face discoveryPrecision: 0.22 -> 0.98Improved
add TC-CRF over TC-CRP for tracklet linkingTC-CRP · Maha82 tracklet linkingFraction fully linked: 0.86 -> 0.89Improved

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