AI Paper Atlas

Research map / Video / Video-language understanding

TRANSPORTER: Transferring Visual Semantics from VLM Manifolds

Alexandros Stergiou

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding · 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
couple generator and VLM embeddings with learned network instead of decode-and-re-encode (ablation)TRANSPORTER · Caption-target alignment (VideoLLaMA 3)cosine similarity: 0.19 -> 0.26Improved
combine Phi1 and Phi2 via learnable OT instead of using Phi1 only (ablation)TRANSPORTER · Caption-target alignment (VideoLLaMA 3)cosine similarity: 0.16 -> 0.26Improved
use learnable entropic OT instead of Sliced Gromov-Wasserstein (ablation)TRANSPORTER · Caption-target alignment (VideoLLaMA 3)cosine similarity: 0.14 -> 0.26Improved
increase OT projections from 50 to 400 (ablation)TRANSPORTER · Caption-target alignment (VideoLLaMA 3)cosine similarity: 0.24 -> 0.26No clear effect
use bounded Hellinger distance instead of KL divergence for logit divergence (ablation)TRANSPORTER concept bank · Caption-target alignment (VideoLLaMA 3)cosine similarity: 0.19 -> 0.26Improved
use Hellinger distance instead of JS divergence (ablation)TRANSPORTER concept bank · Caption-target alignment (VideoLLaMA 3)cosine similarity: 0.22 -> 0.26Improved
generate videos with TRANSPORTER instead of activation-maximization baselinesVideoLLaMA 3 logits · CLIPv scoreCLIPv score: 16.74 -> 35.44Improved
generate videos with TRANSPORTER instead of feature-visualization baselineGemma 3 logits · FVDFVD: 2.18e3 -> 1.05e2Improved

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