AI Paper Atlas

Research map / Video / Video-language understanding

Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval

Bangxiang Lan, Ruobing Xie, Ruixiang Zhao, Xingwu Sun, Zhanhui Kang, Gang Yang, Xirong Li

ICCV 2025 · Video › Video-language understanding · approach: Text-video retrieval · 7 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 reconstruction loss supervising pseudo-query with real text features (ablation)PIG · MSRVTT-1kR@1: 45.8 -> 48.6Improved
use video, frame and informative patch tokens as generator input instead of video token only (ablation)PIG · MSRVTT-1kR@1: 46.3 -> 48.6Improved
add informative patch tokens to video and frame tokens (ablation)PIG · MSRVTT-1kR@1: 47.5 -> 48.6Improved
add video-level token to frame and patch tokens (ablation)PIG · MSRVTT-1kR@1: 48.1 -> 48.6Improved
use causal attention transformer generator instead of MLP (ablation)PIG · MSRVTT-1kR@1: 44.1 -> 48.6Improved
use causal attention transformer generator instead of Q-former (ablation)PIG · MSRVTT-1kR@1: 47.6 -> 48.6Improved
use XPool attention fusioner instead of cross attention (ablation)PIG · MSRVTT-1kR@1: 42.2 -> 48.6Improved
use XPool attention fusioner instead of co-attention (ablation)PIG · MSRVTT-1kR@1: 44.5 -> 48.6Improved
use learned pseudo-query generator instead of ShareGPT4Video captions (ablation)PIG · MSRVTT-1kR@1: 43.8 -> 48.6Improved
use learned pseudo-query generator instead of m-PLUG2 captions (ablation)PIG · MSRVTT-1kR@1: 47.4 -> 48.6Improved
add PIG hybrid-tower pseudo-query interaction to CLIP-ViP backboneCLIP-ViP B/32 · MSRVTT-1kR@1: 46.0 -> 48.6Improved
add PIG to CLIP-ViP backboneCLIP-ViP B/32 · MSVDR@1: 45.1 -> 47.9Improved

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