SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.08508 · 2022

A CLIP-Hitchhiker's Guide to Long Video Retrieval

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Our goal in this paper is the adaptation of image-text models for long video retrieval. Recent works have demonstrated state-of-the-art performance in video retrieval by adopting CLIP, effectively hitchhiking on the image-text representation for video tasks. However, there has been limited success in learning temporal aggregation that outperform mean-pooling the image-level representations extracted per frame by CLIP. We find that the simple yet effective baseline of weighted-mean of frame embeddings via query-scoring is a significant improvement above all prior temporal modelling attempts and mean-pooling. In doing so, we provide an improved baseline for others to compare to and demonstrate state-of-the-art performance of this simple baseline on a suite of long video retrieval benchmarks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2205.08508")
get_code_for_paper("2205.08508")
have("2205.08508")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2205.08508.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2205.08508.svg)](https://syntology.ai/paper/2205.08508)

Connect an agent — have() is free.