2026-08-23

7 arXiv categories· 96 journals· 1743 candidates — 1 worth your time· 92 without an open abstract

Headline

A dense, multi-sensor pedestrian dataset for visual place recognition

Today, together

tag shift
no tag ran above its 30-day average
on the same shoulders
no foundation work was cited by four of the day's papers counted over the 91 of this day's 93 named papers whose reference lists we have — standing on the same older work is not the same as being about the same thing
first appearance
no institution here was new to the last 72 days none of them on a paper we published in the 72 days before this issue

Two counts, not one counted twice: every row here but “on the same shoulders” counts the papers published above, and that one counts every paper this day named — those and the ones under Also published today, whose abstracts we could not read.

preprint

Serdar Yildiz, Abbas Memiş, Songül Varli
arXiv cs.CV

Advanced Image and Video Retrieval Techniques · Robotics and Sensor-Based Localization · Multimodal Machine Learning Applications

YILDIZ-VPR: A Novel Dataset with Dense Coverage Under Diverse Environmental Conditions for Visual Place Recognition

The researchers created YILDIZ-VPR, a visual geo-localization dataset collected via repeated walking traversals of the Yildiz Technical University Davutpasa campus using a GoPro 9 camera. The dataset features dense, pedestrian-level outdoor video frames synchronized with GPS coordinates, gyroscope, speed, and temperature data across different times of day, seasons, and weather conditions.

Why it matters — It provides a dense, multi-sensor pedestrian dataset that captures long-term environmental and seasonal variations, enabling more robust testing of image-based and temporal visual place recognition algorithms in realistic campus environments.

Caveat: The dataset is restricted to a single university campus, which may limit its representativeness for broader urban or highly structured metropolitan environments.

arXiv · pdf

Also published today

These appeared today in journals we track. Their abstracts are not openly available, so we cannot summarise them.