SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshop

2025/08/18 by Hamann, Friedhelm, Mededovic, Emil, Gülhan, Fabian +21
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2508.12813

Abstract

We present an overview of the Spatio-temporal Instance Segmentation (SIS) challenge held in conjunction with the CVPR 2025 Event-based Vision Workshop. The task is to predict accurate pixel-level segmentation masks of defined object classes from spatio-temporally aligned event camera and grayscale camera data. We provide an overview of the task, dataset, challenge details and results. Furthermore, we describe the methods used by the top-5 ranking teams in the challenge. More resources and code of the participants' methods are available here: https://github.com/tub-rip/MouseSIS/blob/main/docs/challenge_results.md

Citations

• YOLOv12: Attention-Centric Real-Time Object Detectors
• Instance-Level Moving Object Segmentation from a Single Image with Events
• MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice
• SAM 2: Segment Anything in Images and Videos
• Micrograph segmentations for DDEVD
• Segment Anything
• XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
• Simple Cues Lead to a Strong Multi-Object Tracker
• ActionFormer: Localizing Moments of Actions with Transformers
• Masked-attention Mask Transformer for Universal Image Segmentation
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box
• ByteTrack: Multi-object Tracking by Associating Every Detection Box
• LoRA: Low-Rank Adaptation of Large Language Models
• HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
• High Speed and High Dynamic Range Video with an Event Camera
• Video Instance Segmentation
• Performance Measures and a Data Set for Multi-Target, Multi-Camera\n Tracking
• An Introduction to Convolutional Neural Networks
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Related

• Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track
• SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
• Straight to Shapes++: Real-time Instance Segmentation Made More Accurate
• UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution
• 1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021