cs.LGNov 8, 2026

UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression

Authors: Ziqi Wang, Su Chen, Qiance Tang, Jieyu Lin, Ziyun Li, Barbara De Salvo, Sai Qian Zhang

Organizations: New York University · Meta Reality Labs

Abstract

As long-video understanding gains increasing attention, augmented reality (AR) devices are emerging as a compelling deployment platform. However, egocentric videos exhibit significant temporal redundancy, imposing substantial memory and computational burdens on resource-constrained AR hardware. To address this challenge, we introduce UTOPI, a plug-and-play pre-compression module designed specifically for egocentric long videos on AR platforms. First, we leverage user motion signals to estimate inter-frame overlap and propose a viewpoint-shift-invariant pruning algorithm. Second, we exploit eye-tracking sensors to identify user fixations, enabling the separation of attended foreground content from background and its preferential retention via a fine-tuned neural network-based adjustment mechanism. Across multiple benchmarks and model backbones, UTOPI achieves up to 95% compression while preserving performance. Code and project page are available at https://sai-lab-nyu.github.io/utopi/.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Small Vision-Language Models are Smart Compressors for Long Video Understanding

    Apr 9, 2026Junjie Fei, Jun Chen, Zechun Liu +13Long-Video UnderstandingVideo Token Compression

  2. One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

    Apr 15, 2026Zheyu Zhang, Ziqi Pang, Shixing Chen +3Long-Video UnderstandingVideo Token Compression

  3. AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding

    May 13, 2026Xiao Yang, Yingzhe Ma, Haoxuan Yu +2Efficient VLM InferenceLong-Video Understanding