AI Paper Atlas

Research map / Video / Video segmentation and tracking

TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection

Qianqian Chen, Hyun Bin Kim, Denzel Wijaya, Yang Yi, Bo LIU, Yangkai Ding

ECCV 2026 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 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
add shared-backbone multi-task learning over single-task training (ablation)Single-task baseline · TRINITY (avg)mAP rho=15%: +3.50Improved
add shared and private experts instead of independent experts (ablation)Independent experts (S3) · TRINITY-NaturemAP rho=15%: 44.78 to 58.74Improved
add shared and private experts instead of independent experts (ablation)Independent experts (S3) · TRINITY-EventmAP rho=15%: 37.54 to 40.98Improved
add shared and private experts instead of independent experts (ablation)Independent experts (S3) · TRINITY-EmotionmAP rho=15%: 63.27 to 67.42Improved
use independent experts instead of shared-backbone MTL (ablation)Shared-backbone MTL (S2) · TRINITY (avg)mAP rho=50%: 68.97 -> 69.70Improved
add Nature supervision to Event-only training (ablation)Shared-private model · TRINITY-NaturemAP rho=15%: 31.25 to 57.89Improved
add Nature supervision to Event-only training (ablation)Shared-private model · TRINITY-EventmAP rho=15%: 40.25 -> 39.98No clear effect
add Emotion supervision to Event+Nature training (ablation)Shared-private model · TRINITY-EmotionmAP rho=15%: 45.98 -> 67.42Improved
use MixBatch perspective mixing instead of per-task batches (ablation)Ours · TRINITY-NaturemAP rho=15%: 58.74 to 42.19Hurt
use MixBatch perspective mixing instead of per-task batches (ablation)Ours · TRINITY-EmotionmAP rho=15%: 67.42 -> 63.61Mixed
add round-robin training instead of sequential for single backbone (ablation)Single backbone · TRINITY (avg)mAP rho=15%: 48.89 -> 49.19Improved
add round-robin training instead of sequential (ablation)Shared-private model · TRINITY (avg)mAP rho=15%: 55.56 -> 55.71Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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