Related papers: HotSpotter - Patterned Species Instance Recognitio…
Despite various methods are proposed to make progress in pedestrian attribute recognition, a crucial problem on existing datasets is often neglected, namely, a large number of identical pedestrian identities in train and test set, which is…
Camera traps have revolutionized the animal research of many species that were previously nearly impossible to observe due to their habitat or behavior. They are cameras generally fixed to a tree that take a short sequence of images when…
Accurate individual identification is essential for monitoring rare amphibians, yet invasive marking is often unsuitable for critically endangered species. We evaluate state-of-the-art computer-vision methods for photographic…
Several computer vision applications such as person search or online fashion rely on human description. The use of instance-level human parsing (HP) is therefore relevant since it localizes semantic attributes and body parts within a…
Global biodiversity is declining at an unprecedented rate, yet little information is known about most species and how their populations are changing. Indeed, some 90% of Earth's species are estimated to be completely unknown. Machine…
Reliable markerless motion tracking of people participating in a complex group activity from multiple moving cameras is challenging due to frequent occlusions, strong viewpoint and appearance variations, and asynchronous video streams. To…
In both terrestrial and marine ecology, physical tagging is a frequently used method to study population dynamics and behavior. However, such tagging techniques are increasingly being replaced by individual re-identification using image…
The increasing frequency of catastrophic natural events, such as wildfires, calls for the development of rapid and automated wildfire detection systems. In this paper, we propose a wildfire identification solution to improve the accuracy of…
The difficulty of image recognition has gradually increased from general category recognition to fine-grained recognition and to the recognition of some subtle attributes such as temperature and geolocation. In this paper, we try to focus…
Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios. In most cases, the existence of a particular attribute is strongly related to a partial region. Recent works…
Coral reefs are fast-changing and complex ecosystems that are crucial to monitor and study. Biological hotspot detection can help coral reef managers prioritize limited resources for monitoring and intervention tasks. Here, we explore the…
Camera traps are used by ecologists globally as an efficient and non-invasive method to monitor animals. While it is time-consuming to manually label the collected images, recent advances in deep learning and computer vision has made it…
This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different datasets. The training procedure uses homographic…
Discrete diffusion models have emerged as a powerful generative modeling framework for discrete data with successful applications spanning from text generation to image synthesis. However, their deployment faces challenges due to the high…
Unsustainable trade in wildlife is one of the major threats affecting the global biodiversity crisis. An important part of the trade now occurs on the internet, especially on digital marketplaces and social media. Automated methods to…
Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize. In this work, we present an end-to-end pipeline for identifying and mitigating spurious patterns…
Feature fusion is a commonly used strategy in image retrieval tasks, which aggregates the matching responses of multiple visual features. Feasible sets of features can be either descriptors (SIFT, HSV) for an entire image or the same…
Efficient on-device models have become attractive for near-sensor insight generation, of particular interest to the ecological conservation community. For this reason, deep learning researchers are proposing more approaches to develop lower…
We propose a method to match anatomical locations between pairs of medical images in longitudinal comparisons. The matching is made possible by computing a descriptor of the query point in a source image based on a hierarchical sparse…
In this paper, we address the problem of cross-view image geo-localization. Specifically, we aim to estimate the GPS location of a query street view image by finding the matching images in a reference database of geo-tagged bird's eye view…