# Learning Egocentric In-Hand Object Segmentation through Weak Supervision from Human Narrations

arXiv: https://arxiv.org/abs/2509.26004 · HTML: https://mlsanity.com/paper/2509.26004/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 53 of its 62 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 30 of 53)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [Learning to Detect Human-Object Interactions](https://mlsanity.com/paper/1702.05448/) (2017)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [Detecting and Recognizing Human-Object Interactions](https://mlsanity.com/paper/1704.07333/) (2017)
- [Decoupling Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2112.07910/) (2021)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2211.14813/) (2022)
- [PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection](https://mlsanity.com/paper/1912.12898/) (2019)
- [EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations](https://mlsanity.com/paper/2209.13064/) (2022)
- [HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos](https://mlsanity.com/paper/2411.19167/) (2024)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [Contrastive Learning for Weakly Supervised Phrase Grounding](https://mlsanity.com/paper/2006.09920/) (2020)
- [ManipulaTHOR: A Framework for Visual Object Manipulation](https://mlsanity.com/paper/2104.11213/) (2021)
- [Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer](https://mlsanity.com/paper/2112.01838/) (2021)
- [Grounding Everything: Emerging Localization Properties in Vision-Language Transformers](https://mlsanity.com/paper/2312.00878/) (2023)
- [Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor](https://mlsanity.com/paper/1704.02201/) (2017)

## Abstract (arXiv)

Pixel-level recognition of objects manipulated by the user from egocentric images enables key applications spanning assistive technologies, industrial safety, and activity monitoring. However, progress in this area is currently hindered by the scarcity of annotated datasets, as existing approaches rely on costly manual labels. In this paper, we propose to learn human-object interaction detection leveraging narrations unicodex2013 natural language descriptions of the actions performed by the camera wearer which contain clues about manipulated objects. We introduce Narration-Supervised in-Hand Object Segmentation (NS-iHOS), a novel task where models have to learn to segment in-hand objects by learning from natural-language narrations in a weakly-supervised regime. Narrations are then not employed at inference time. We showcase the potential of the task by proposing Weakly-Supervised In-hand Object Segmentation from Human Narrations (WISH), an end-to-end model distilling knowledge from narrations to learn plausible hand-object associations and enable in-hand object segmentation without using narrations at test time. We benchmark WISH against different baselines based on open-vocabulary object detectors and vision-language models. Experiments on EPIC-Kitchens and Ego4D show that WISH surpasses all baselines, recovering more than 50% of the performance of fully supervised methods, without employing fine-grained pixel-wise annotations. Code and data can be found at https://fpv-iplab.github.io/WISH.