# Hand Trajectory Fusion for Egocentric Natural Language Query Grounding

arXiv: https://arxiv.org/abs/2606.02962 · HTML: https://mlsanity.com/paper/2606.02962/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 12 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [MediaPipe Hands: On-device Real-time Hand Tracking](https://mlsanity.com/paper/2006.10214/) (2020)
- [What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention](https://mlsanity.com/paper/1905.09035/) (2019)
- [GroundNLQ @ Ego4D Natural Language Queries Challenge 2023](https://mlsanity.com/paper/2306.15255/) (2023)
- [Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning](https://mlsanity.com/paper/2503.00986/) (2025)
- [Object-Shot Enhanced Grounding Network for Egocentric Video](https://mlsanity.com/paper/2505.04270/) (2025)
- [ObjectNLQ @ Ego4D Episodic Memory Challenge 2024](https://mlsanity.com/paper/2406.15778/) (2024)

## Abstract (arXiv)

Egocentric Natural Language Query (NLQ) grounding asks a model to localize, in a long first-person video, the temporal interval that answers a free-form text query. Existing methods fuse video appearance with the query but ignore hand motion, despite the fact that roughly 41% of Ego4D NLQ queries are answered at a moment of hand--object manipulation or their immediate outcomes.We propose a hand-trajectory encoder for converting a sequence of hand skeletons into highly-semantic hand kinematic features, which are then aligned and combined with pretrained video--text features through a cross-attention fusion strategy with adaptive gating. On the Ego4D NLQ v2 validation split, the clearest gains appear for Hand-Object Interaction queries (+2.54 R1@IoU=0.3) and Quantity/State queries (+4.32 R1@IoU=0.3), indicating that hand trajectory provides grounding cues beyond appearance alone.