Video Instance Segmentation

Follow this topic Ask about this topic

Latest papers

11 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentation
Oct 1, 2026Arash Rocky, Q. M. Jonathan WuVideo Object Segmentation Instance Segmentation
Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, N9B 3P4, Canada
Learning to Reason with Persistent Object States for Video Instance Segmentation
Sep 28, 2026Yongxue Xu, Boxue Yang, Ziqian Liu +3Video Object Segmentation Instance Segmentation
Shanghai Jiao Tong University · Sun Yat-sen University · Fudan University
DynEoMT: Learning Object Dynamicity from Online Segmentation Queries
Sep 13, 2026Calvin Galagain, Martyna Poreba, François GouletteVideo Object Segmentation Video Instance Segmentation
Université Paris-Saclay, CEA, List, F-91120 Palaiseau, France · U2IS, ENSTA Paris, Institut Polytechnique de Paris, 91120, Palaiseau, France
QueenVIS: Rethinking Image-Only Training for Video Instance Segmentation via Query Enrichment
Jul 27, 2026Arian Kheirandish, Fardin Ayar, Ehsan Javanmardi +2Video Understanding Instance Segmentation
Amirkabir University of Technology (AUT), Tehran, Iran · The University of Tokyo, Tokyo, Japan
Still image and spatial-temporal tomato data enabling detection, segmentation, tracking, and video-instance segmentation using strong and weak labels
Jul 16, 2026Michael Halstead, Esra Guclu, Mohamed Farag +7Agricultural Image Analysis Plant Phenotyping
University of Bonn, Bonn, Germany · CSIRO, Pullenvale, Australia
UAV-OVVIS: Unmanned Aerial Vehicles Also Need Open-Vocabulary Video Instance Segmentation
Jul 9, 2026Mingyu Dou, Shi Qiu, Ming Hu +2Video Object Segmentation Instance Segmentation
Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Institute of Artificial Intelligence (TeleAI), China Telecom +2
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
Jun 30, 2026Luca Barsellotti, Martin Sundermeyer, Mattia Segu +5Video Object Segmentation Instance Segmentation
⋆Work done during an internship at Google. · Google · TU Munich; Munich Center for Machine Learning +1
SA-VIS: Sparse frame Annotations for training Video Instance Segmentation
Jun 18, 2026Edoardo Mello Rella, Ajad Chhatkuli, Shipra Jain +2Video Understanding Video Object Segmentation
CVL, ETH Zurich · INSAIT, Sofia University "St. Kliment Ohridski" · Align Technology
Mind the Gap: Disentangling Performance Bottlenecks in Video Instance Segmentation
Jun 5, 2026Danial Hamdi, Fardin Ayar, Mahdi JavanmardiVideo Understanding Instance Segmentation
Computer Engineering Department, Amirkabir University of Technology (Tehran Polytechnic), No. 350, Hafez Ave., Valiasr Sq., Tehran, 15875-4413, Tehran, Iran
Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction
Apr 1, 2026Patrick Glandorf, Thomas Norrenbrock, Bodo RosenhahnVideo Instance Segmentation Visual Token Pruning
Institute for Information Processing (tnt), L3S - Leibniz University Hannover, Germany
ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark
Dec 1, 2025Joanne Lin, Ruirui Lin, Yini Li +2Video Instance Segmentation Instance Segmentation
Visual Information Laboratory, University of Bristol

Oct 1, 2026J/K move · Enter open · S save

Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentation

Arash Rocky, Q. M. Jonathan Wu

Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, N9B 3P4, Canada

Video Object Segmentation Instance Segmentation Video Instance Segmentation Multi-Object Tracking

Open paper AskPDF arXiv

Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory requirements confine them to short video clips and their single-prompt inference design makes multi-category open-vocabulary tracking computationally prohibitive. This work introduces two contributions toward fully automated tracking annotation of arbitrary video. The Generalized Presence Token (GPT) reformulates SAM3's inference pipeline to process N text prompts simultaneously via virtual prompt batching, reducing image encoding cost from O(N) to O(1) with no modifications to any learned component. The Annotation and Segmentation Handler (ASH) extends any memory-attention VIS tracker to sequences of arbitrary length through overlapping temporal chunks with IoU-based inter-chunk identity matching, requiring no dataset-specific training. Instantiated on SAM3, the resulting pipeline -- SAM3-ASH -- achieves state-of-the-art HOTA on MOTS20 under fully zero-shot conditions and remains competitive with trained specialists across seven additional benchmarks, while peak GPU memory consumption stays below 25 GB, establishing a practical baseline for scalable, training-free automated video annotation.