# A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video

arXiv: https://arxiv.org/abs/2403.03461 · HTML: https://mlsanity.com/paper/2403.03461/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 10 of 10)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [Locality-constrained Spatial Transformer Network for Video Crowd Counting](https://mlsanity.com/paper/1907.07911/) (2019)
- [Spatiotemporal Modeling for Crowd Counting in Videos](https://mlsanity.com/paper/1707.07890/) (2017)
- [RGB-D Indiscernible Object Counting in Underwater Scenes](https://mlsanity.com/paper/2304.11677/) (2023)
- [Optical Flow Dataset and Benchmark for Visual Crowd Analysis](https://mlsanity.com/paper/1811.07170/) (2018)

## Built on by (most cited first, 1 of 1)

- [AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis](https://mlsanity.com/paper/2502.01785/) (2025)

## Abstract (arXiv)

Dense object counting or crowd counting has come a long way thanks to the recent development in the vision community. However, indiscernible object counting, which aims to count the number of targets that are blended with respect to their surroundings, has been a challenge. Image-based object counting datasets have been the mainstream of the current publicly available datasets. Therefore, we propose a large-scale dataset called YoutubeFish-35, which contains a total of 35 sequences of high-definition videos with high frame-per-second and more than 150,000 annotated center points across a selected variety of scenes. For benchmarking purposes, we select three mainstream methods for dense object counting and carefully evaluate them on the newly collected dataset. We propose TransVidCount, a new strong baseline that combines density and regression branches along the temporal domain in a unified framework and can effectively tackle indiscernible object counting with state-of-the-art performance on YoutubeFish-35 dataset.