Temporal Aspects of CLIP Embeddings

Image embedding models such as OpenAI's CLIP do not in- herently store any temporal information in the embeddings they generate. This paper argues that while such embeddings capture rich semantic relationships, they lack an innate ca- pacity to encode chronological details, requiring fine-tuning or additional layers to infer temporal attributes

Authors

Institutions

Publication Details

Published
2025-05-08
DOI
https://doi.org/10.1145/3701716.3717503
Citations
1
Primary Topic
Algorithms and Data Compression
Type
article
Field-Weighted Citation Impact
2.48
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Temporal Aspects of CLIP Embeddings

Behrooz Mansouri, Nicholas Largey, Mandy Ho, Janna Ahrndt
1 citations
Algorithms and Data Compression
2.48
article

Temporal Aspects of CLIP Embeddings

Behrooz Mansouri, Nicholas Largey, Mandy Ho, Janna Ahrndt
article en
1 citations

Abstract

Image embedding models such as OpenAI's CLIP do not in- herently store any temporal information in the embeddings they generate. This paper argues that while such embeddings capture rich semantic relationships, they lack an innate ca- pacity to encode chronological details, requiring fine-tuning or additional layers to infer temporal attributes

University of Southern Maine (US)
Openalex Percentile: Top 10%
Algorithms and Data Compression
2.48
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Temporal Aspects of CLIP Embeddings — Behrooz Mansouri, Nicholas Largey, et al. · (2025) | TGRS Research Map | TGRS