# EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning

arXiv: https://arxiv.org/abs/2609.08938 · HTML: https://mlsanity.com/paper/2609.08938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology](https://mlsanity.com/paper/2410.07087/) (2024)
- [VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation](https://mlsanity.com/paper/2303.08340/) (2023)
- [MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models](https://mlsanity.com/paper/2501.02955/) (2025)
- [Towards Understanding Camera Motions in Any Video](https://mlsanity.com/paper/2504.15376/) (2025)
- [Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework](https://mlsanity.com/paper/2502.13759/) (2025)
- [Agent-Based Anti-Jamming Techniques for UAV Communications in Adversarial Environments: A Comprehensive Survey](https://mlsanity.com/paper/2508.11687/) (2025)
- [Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence](https://mlsanity.com/paper/2607.12477/) (2026)
- [Frequency Point Game Environment for UAVs via Expert Knowledge and Large Language Model](https://mlsanity.com/paper/2508.02757/) (2025)
- [Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation](https://mlsanity.com/paper/2606.09162/) (2026)
- [GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception](https://mlsanity.com/paper/2608.27971/) (2026)

## Abstract (arXiv)

UAV video question answering requires separating camera motion from changes in the scene, but RGB-only multimodal models receive no explicit, stable reference for that separation. We present EgoSIS, a pose-free adapter that converts RGB-derived bidirectional flow into motion-canonical visual evidence in three stages. Factorized Visual Ego-Transitions (FVET) fits a robust image-plane transition and exposes motion, residual-support, and reliability factors. Reliability-Gated Ego-Transition Memory (ReTEM) uses reliability-weighted updates for a bounded history and re-anchors it at cuts or sustained uncertainty. Ego-Aligned Spatial Evidence (EASE) warps supported visual features into each segment's local anchor and injects four spatial evidence tokens per visual slice through zero-initialized residuals, without changing Qwen's visual-token count. On SIS-Bench, EgoSIS-8B obtains 89.9% perception, 82.5% perception-plus-memory, and 76.2% overall accuracy, with the largest gains concentrated in self-awareness perception and memory. The adapter thus provides an interpretable interface between optical flow and spatial reasoning.