VDU 2024 @ CVPR 2024

The 3rd CVPR Workshop on Vision Datasets Understanding

Overview

Data is the fuel of computer vision, on which state-of-the-art systems are built. A robust object detection system not only needs a strong model architecture and learning algorithms but also relies on a comprehensive large-scale training set. Despite the pivotal significance of datasets, existing research in computer vision is usually algorithm centric. Comparing the number of algorithm-centric works in domain adaptation, the quantitative understanding of the domain gap is much more limited. As a result, there are currently few investigations into the representations of datasets, while in contrast, an abundance of literature concerns ways to represent images or videos, essential elements in datasets.

The 3rd VDU workshop aims to bring together research works and discussions focusing on analyzing vision datasets, as opposed to the commonly seen algorithm-centric counterparts. Specifically, the following topics are of interest in this workshop.

Properties and attributes of vision datasets
Application of dataset-level analysis
Representations of and similarities between vision datasets
Improving vision dataset quality through generation and simulation.
Evaluating model accuracy under various test environments.

In summary, the questions related to the proposed workshop include but are not limited to:

Can vision datasets be analyzed on a large scale?
How to holistically understand the visual semantics contained in a dataset?
How to define vision-related properties and problems on the dataset level?
How can we improve algorithm design by better understanding vision datasets?
Can we predict the performance of an existing model in a new dataset?
What are good dataset representations? Can they be hand-crafted, learned through neural nets or a combination of both?
How do we measure similarities between datasets and their bias and fairness?
Can we improve training data quality through data engineering or simulation?
How to efficiently create labelled datasets under new environments?
How to create realistic datasets that serve our real-world application purpose?
How can we alleviate the need for large-scale labelled datasets in deep learning?
How to best analyze model performance under various environments without requiring accessing the groundtruth labels?
How to evaluate diffusion models and large language models?

Important Dates for the Workshop

Midnight 23:59 March 20th, 2024 (Pacific Time): Workshop paper submission closed
Midnight 23:59 March 27th, 2024 (Pacific Time): Supplementary material submission closed
Thursday, April 11th, 2024: Author notification of paper acceptance
Saturday, April 13th, 2024: Camera ready.
Monday, June 17th, 2024: Half-day workshop.

Note: The above deadlines apply to those who want to have their papers included in the proceedings. If you prefer not to be included into the proceedings but still want to share your work with the community, please contact the organizing committee to find out possible solutions.

DataCV Challenge 2024

In 2024, the DataCV Challenge aims to search for an effective training set from a large-scale data pool such that a competitive target-specific model can be obtained.

Challenge website: https://sites.google.com/view/vdu-cvpr24/competition

Important Dates for DataCV Challenge 2024

Monday, February 5th, 2024: Training and validation data release
Monday, February 12th, 2024: Release of the evaluation server
Saturday, March 9th, 2024: Test data release
Saturday, March 16th, 2024: Result submission closed
Midnight 23:59 March 20th, 2024 (Pacific Time): Workshop paper submission closed
Midnight 23:59 March 27th, 2024 (Pacific Time): Supplementary material submission closed
Thursday, April 11th, 2024: Author notification of paper acceptance
Saturday, April 13th: Camera ready.

Note: If your team would like to compete for an award (1st place, 2nd place etc), it is mandatory to submit a paper to the workshop and release the code publicly. More details are provided on the DataCV Challenge website

Program:

Location: Summit 436

Schedule: June 17th 1:30 pm – 5:30 pm

1:30 pm – 1:40 pm Workshop Kick off and Opening Comments

1:40 pm – 2:10 pm First Keynote Speech by Prof. Cees Snoek (25 mins for talk and 5mins for Q&A)

2:10 pm – 3:02 pm 4 Oral Presentations (10 mins for talk and 3 mins for Q&A)

2:10 pm – 2:23 pm ID-6: DTLLM-VLT: Diverse Text Generation for Visual Language Tracking Based on LLM
2:23 pm – 2:36 pm ID-14: Grounding Stylistic Domain Generalisation with Quantitative Domain Shift Measures and Synthetic Scene Images
2:36 pm – 2:49 pm ID-16: A Survey of Video Datasets for Grounded Event Understanding
2:49 pm – 3:02 pm ID-17: CinePile: A Long Video Question Answering Dataset and Benchmark

3:02 pm – 3:15 pm Coffee Break

3:15 pm – 3:45 pm Second Keynote Speech by Prof. Stephen Gould (25 mins for talk and 5mins for Q&A)

3:45 pm – 4:30 pm 3 Oral Presentations (12 mins for talk and 3 mins for Q&A)

3:45 pm – 3:50 pm Challenge Introduction and Winner Announcement
3:50 pm – 4:03 pm ID-18: DDOS: The Drone Depth and Obstacle Segmentation Dataset
4:03 pm – 4:16 pm ID-19: Classifier Guided Cluster Density Reduction for Dataset Selection
4:16 pm – 4:30 pm ID-22: Optimising Object Detection via Metric-driven Training Data Selection

4:30 pm – 5:00 pm Third Keynote Speech by Prof. Nuno Vasconcelos (25 mins for talk and 5mins for Q&A)

5:00 pm -6:30 pm Poster Session

Invited Speakers:

Cees Snoek

University of Amsterdam

Stephen Gould

Australian National University

Nuno Vasconcelos

University of California San Diego

Paper Submission

To ensure the high quality of the accepted papers, all submissions will be evaluated by research and industry experts from the corresponding fields. Reviewing will be double-blind and we will accept submissions on work that is not published, currently under review, and already published. All accepted workshop papers will be published in the CVPR 2024 Workshop Proceedings by Computer Vision Foundation Open Access. The authors of all accepted papers (oral/spotlight/posters) will be invited to present their work during the actual workshop event at CVPR 2024.

Paper submission has to be in English, in pdf format, and at most 8 pages (excluding references) in double column. The paper format must follow the same guidelines as for all CVPR 2024 submissions. The author kit provides a LaTeX2e template for paper submissions. Please refer to this kit for detailed formatting instructions.

Submission Website: https://cmt3.research.microsoft.com/VDU2024

For information about whether the workshop will be in-person only, please visit the CVPR 2024 website for more attending details.