AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions

Ce Chen, Yi Ren, Yuanming Li, Viktor Goriachko, Zhenhui Ye, Zujin Guo, Zhibin Hong, Mingming Gong

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 1 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 optical flow input fused with color frames (ablation)TransVLM · STD public datasegment F1: 0.694 -> 0.783Improved
add optical flow input (ablation)TransVLM · STD synthetic dataframe F1: 0.892 -> 0.938Improved
fuse flow at patch embedding instead of separate inputs (ablation)TransVLM · STD benchmarkRTF: 1.29 -> 0.50Improved
fuse flow at patch embedding instead of separate inputs (ablation)TransVLM · STD public datasegment F1: 0.739 -> 0.783Improved
zero-padding init instead of duplicating color weights (ablation)TransVLM · STD public datasegment F1: 0.655 -> 0.783Improved
add fine-tuning on STD training data (ablation)Qwen3-VL-4B · STD public datasegment F1: 0.487 -> 0.783Improved
add public data to synthetic-only training (ablation)TransVLM · STD public datasegment F1: 0.416 -> 0.783Improved
add synthetic data to public-only training (ablation)TransVLM · STD synthetic datasegment F1: 0.720 -> 0.895Improved
add synthetic data to public-only training (ablation)TransVLM · STD public datasegment F1: 0.730 -> 0.783Improved
add public data to synthetic-only training (ablation)TransVLM · STD synthetic dataframe F1: 0.941 -> 0.938No clear effect
use TransVLM instead of Qwen3-VL-4B Instruct zero-shotQwen3-VL-4B · STD public datasegment F1: 0.124 -> 0.783Improved
TransVLM vs AutoShot on boundary error and speedTransVLM · STD public dataABE (s): 1.58 vs 1.78 ABE; RTF 0.50 vs 0.03Hurt

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