AI Paper Atlas

Research map / Video / Video-language understanding

Video Timeline Modeling For News Story Understanding

Meng Liu, Mingda Zhang, Jialu Liu, Hanjun Dai, Ming-Hsuan Yang, Shuiwang Ji, Zheyun Feng, Boqing Gong

NeurIPS 2023 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 0 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
Model nodes as learnable embeddings with three Transformer encoders (Tri-Transformer vs V-Transformer)V-Transformer · YouTube-News-Timeline testmicro precision: 64.4% -> 66.6%Improved
Tri-Transformer vs V-TransformerV-Transformer · YouTube-News-Timeline testmacro Hamming distance: 0.477 -> 0.453Improved
Tri-Transformer vs V-TransformerV-Transformer · YouTube-News-Timeline testmicro Euclidean distance: 0.916 -> 0.837Improved
Add cross-modal distillation from text-aware teacherTri-Transformer · YouTube-News-Timeline testmacro precision: 71.4% -> 72.5%Improved
Add cross-modal distillationTri-Transformer · YouTube-News-Timeline testmicro Hamming distance: 0.490 -> 0.470Improved
Add cross-modal distillationTri-Transformer · YouTube-News-Timeline testmicro Euclidean distance: 0.837 -> 0.804Improved
Add cross-modal distillationTri-Transformer · YouTube-News-Timeline testmacro pairwise agreement accuracy: 85.4% -> 85.2%Hurt
Add cross-modal distillationTri-Transformer · YouTube-News-Timeline testmacro recall: 71.2% -> 71.1%No clear effect
Give the model text node descriptions as input (reference optimum teacher)Tri-Transformer student · YouTube-News-Timeline testmacro Hamming distance: 0.436 -> 0.308Improved
Remove video release-time positional encoding (ablation)Tri-Transformer · YouTube-News-Timeline testmacro Hamming distance: 0.453 -> 0.621Improved
Remove video release-time positional encoding (ablation)Tri-Transformer · YouTube-News-Timeline testmicro pairwise agreement accuracy: 94.3% -> 72.1%Improved
Remove video PE (ablation)Tri-Transformer · YouTube-News-Timeline testmacro Euclidean distance: 0.716 -> 1.523Improved

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