CV4E 2024 at ECCV
Workshop Recording
Accepted Papers and Abstracts
The workshop invited papers for archival (proceedings) and non-archival tracks. Additionally, abstracts were invited to the non-archival track.
Archival full papers
| Paper ID | Paper Title | Authors |
|---|---|---|
| 2 | Generating Binary Species Range Maps (supp) | Filip Gedung Dorm, Christian P Lange, Scott Loarie, Oisin Mac Aodha |
| 4 | WildFusion: Individual Animal Identification with Calibrated Similarity Fusion | Vojtěch Čermák, Lukas Picek, Lukáš Adam, Lukáš Neumann, Jiri Matas |
| 14 | Towards Zero-Shot Camera Trap Image Categorization | Jiří Vyskočil, Lukas Picek |
| 16 | Larval Hostplant Prediction from Luehdorfia japonica Image using Multi-label ABN | Tsubasa Hirakawa, Takaaki Arai, Takayoshi Yamashita, Hironobu Fujiyoshi, Yuichi Oba, Hiromichi Fukui, Masaya Yago |
| 17 | Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimation | Daniele Rege Cambrin, Isaac A Corley, Paolo Garza |
| 19 | Underwater Uncertainty: A Multi-Annotator Image Dataset for Benthic Habitat Classification (supp) | Galadrielle Humblot-Renaux, Anders Skaarup Johansen, Jonathan Eichild Schmidt, Amanda Frederikke Irlind, Niels Madsen, Thomas B. Moeslund, Malte Pedersen |
| 22 | Deep Learning for Automated Shark Detection and Biometrics Without Keypoints | Chinmay Lalgudi, Jaden Clark, Mark E Leone, Jayson Meribe, Sergio Madrigal Mora, Mario Espinoza |
| 24 | Improving in situ real-time classification of long-tail marine plankton images for ecosystem studies (supp) | Noushin Dr Eftekhari, Sophie Pitois, Mojtaba Masoudi, Robert Blackwell, James Scott, Sarah L.C. Giering, Matthew Fry |
| 29 | KAN-Mixer: Kolmogorov-Arnold Networks for Gene Expression Prediction in Plant Species | Jin Gao, Juntu Zhao, Keyu Li, Dequan Wang |
Archival short papers
| Paper ID | Paper Title | Authors |
|---|---|---|
| 6 | Multi-Scale and Multi-Modal Species Distribution Modelling | Nina van Tiel, Robin Zbinden, Emanuele Dalsasso, Benjamin A Kellenberger, Loïc Pellissier, Devis Tuia |
| 8 | Semantic Segmentation of Benthic Classes in Reef Environments using a Large Vision Transformer | Charlotte L Sertic, Jonathan Sauder, Devis Tuia |
| 9 | POLO - Point-based, multi-class animal detection | Giacomo G May, Benjamin A Kellenberger, Emanuele Dalsasso, Devis Tuia |
| 11 | Mining Field Data for Tree Species Recognition at Scale (supp) | Dimitri Gominski, Daniel Ortiz-Gonzalo, Martin S Brandt, Maurice Mugabowindekwe, Rasmus Fensholt |
| 12 | MaskSDM: Adaptive species distribution modeling through data masking (supp) | Robin Zbinden, Nina van Tiel, Gencer Sumbul, Benjamin A Kellenberger, Devis Tuia |
| 15 | Finetuning for Bird Sound Classification - An Empirical Study - | David Stein, Bjoern Andres, |
| 31 | Multimodal Fusion Strategies for Mapping Biophysical Landscape Features | Lucia Gordon, Nico Lang, Catherine Ressijac, Andrew Davies, |
Non-archival papers & abstracts
FishNet competition
The ECCV 2024 Challenge presented a unique opportunity for researchers and practitioners to showcase their expertise in fish species classification in challenging environments using the FishNet dataset. The challenge aimed to address the complexities associated with classifying fish species in diverse and demanding conditions, while also tackling the inherent imbalance in the dataset, characterized by a long-tailed distribution.
Dates:
- Dev Phase: Started May 10, 2024.
- Challenge Phase: Started July 10, 2024.
- Winner Announcement: September 5, 2024.
Dataset
The FishNet dataset comprises a diverse collection of fish images captured in various environmental conditions, including underwater, low-light, and occluded scenarios. The dataset encompasses a wide range of fish species, from common to rare, contributing to its long-tailed distribution. Participants will have access to a large-scale annotated dataset for model training and evaluation.
Challenge details
All the details related to the challenge can be found here.