# Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion

arXiv: https://arxiv.org/abs/2605.26383 · HTML: https://mlsanity.com/paper/2605.26383/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food](https://mlsanity.com/paper/2103.03375/) (2021)
- [Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification](https://mlsanity.com/paper/2301.09498/) (2023)
- [A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challenges](https://mlsanity.com/paper/2401.10643/) (2024)
- [Identity-aware Feature Decoupling Learning for Clothing-change Person Re-identification](https://mlsanity.com/paper/2501.05851/) (2025)

## Abstract (arXiv)

Object re-identification (ReID) in egocentric kitchen videos is challenging due to rapid viewpoint changes, frequent occlusions, cluttered scenes, and large intra-class appearance variations. Objects may leave and re-enter the field of view, and the large diversity of instances with limited annotations makes supervised ReID difficult to scale, motivating zero-shot approaches. We study zero-shot object ReID on the EPIC-Kitchens benchmark, where the goal is to match active food and kitchen-tool instances across frames using only pre-trained visual features. We first evaluate five state-of-the-art feature extractors, including Vision-Language Models (VLMs) - CLIP, DINOv2, DreamSim, I-JEPA, and SAM3 - and show that zero-shot methods fail, with the best baseline achieving only 45.3% mAP. We then propose an Enhanced SAM3 ReID Pipeline, a zero-shot multi-stage method built around SAM3 segmentation as the core component. Stage 1 uses SAM3 to suppress background clutter. Stage 2 fuses embeddings from SAM3, DINOv2, and CLIP into a single L2-normalized descriptor. Stage 3 augments cosine similarity with mask-shape IoU for geometric consistency, and Stage 4 applies k-reciprocal re-ranking. The full pipeline improves performance by 7.5% mAP to 52.8%.