Agentic Very Long Video Understanding

The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous, longitudinal stream of egocentric video. Achieving this vision requires advances in long-horizon video understanding, where systems must interpret and recall visual and audio information spanning days or even weeks. Existing methods, including large language models and retrieval-augmented generation, are constrained by limited context windows and lack the ability to perform compositional, multi-hop reasoning over very long video streams. In this work, we address these challenges through EGAgent, an enhanced agentic framework centered on entity scene graphs, which represent people, places, objects, and their relationships over time. Our system equips a planning agent with tools for structured search and reasoning over these graphs, as well as hybrid visual and audio search capabilities, enabling detailed, cross-modal, and temporally coherent reasoning. Experiments on the EgoLifeQA and Video-MME (Long) datasets show that our method achieves state-of-the-art performance on EgoLifeQA (57.5%) and competitive performance on Video-MME (Long) (74.1%) for complex longitudinal video understanding tasks.

Reading Recognition in the Wild

To enable egocentric contextual AI in always-on smart glasses, it is crucial to be able to keep a record of the user's interactions with the world, including during reading. In this paper, we introduce a new task of reading recognition to determine when the user is reading. We first introduce the first-of-its-kind large-scale multimodal Reading in the Wild dataset, containing 100 hours of reading and non-reading videos in diverse and realistic scenarios. We then identify three modalities (egocentric RGB, eye gaze, head pose) that can be used to solve the task, and present a flexible transformer model that performs the task using these modalities, either individually or combined. We show that these modalities are relevant and complementary to the task, and investigate how to efficiently and effectively encode each modality. Additionally, we show the usefulness of this dataset towards classifying types of reading, extending current reading understanding studies conducted in constrained settings to larger scale, diversity and realism. Code, model, and data will be public.

EgoLM: Multi-Modal Language Model of Egocentric Motions

As the prevalence of wearable devices, learning egocentric motions becomes essential to develop contextual AI. In this work, we present EgoLM, a versatile framework that tracks and understands egocentric motions from multi-modal inputs, e.g., egocentric videos and motion sensors. EgoLM exploits rich contexts for the disambiguation of egomotion tracking and understanding, which are ill-posed under single modality conditions. To facilitate the versatile and multi-modal framework, our key insight is to model the joint distribution of egocentric motions and natural languages using large language models (LLM). Multi-modal sensor inputs are encoded and projected to the joint latent space of language models, and used to prompt motion generation or text generation for egomotion tracking or understanding, respectively. Extensive experiments on large-scale multi-modal human motion dataset validate the effectiveness of EgoLM as a generalist model for universal egocentric learning.

Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild

We introduce Nymeria - a large-scale, diverse, richly annotated human motion dataset collected in the wild with multiple multimodal egocentric devices. The dataset comes with a) full-body 3D motion ground truth; b) egocentric multimodal recordings from Project Aria devices with RGB, grayscale, eye-tracking cameras, IMUs, magnetometer, barometer, and microphones; and c) an additional "observer" device providing a third-person viewpoint. We compute world-aligned 6DoF transformations for all sensors, across devices and capture sessions. The dataset also provides 3D scene point clouds and calibrated gaze estimation. We derive a protocol to annotate hierarchical language descriptions of in-context human motion, from fine-grain pose narrations, to atomic actions and activity summarization. To the best of our knowledge, the Nymeria dataset is the world largest in-the-wild collection of human motion with natural and diverse activities; first of its kind to provide synchronized and localized multi-device multimodal egocentric data; and the world largest dataset with motion-language descriptions. It contains 1200 recordings of 300 hours of daily activities from 264 participants across 50 locations, travelling a total of 399Km. The motion-language descriptions provide 310.5K sentences in 8.64M words from a vocabulary size of 6545. To demonstrate the potential of the dataset we define key research tasks for egocentric body tracking, motion synthesis, and action recognition and evaluate several state-of-the-art baseline algorithms. Data and code will be open-sourced.

NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning

In the light of recent analyses on privacy-concerning scene revelation from visual descriptors, we develop descriptors that conceal the input image content. In particular, we propose an adversarial learning framework for training visual descriptors that prevent image reconstruction, while maintaining the matching accuracy. We let a feature encoding network and image reconstruction network compete with each other, such that the feature encoder tries to impede the image reconstruction with its generated descriptors, while the reconstructor tries to recover the input image from the descriptors. The experimental results demonstrate that the visual descriptors obtained with our method significantly deteriorate the image reconstruction quality with minimal impact on correspondence matching and camera localization performance.

Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptors

As autonomous driving and augmented reality evolve, a practical concern is data privacy. In particular, these applications rely on localization based on user images. The widely adopted technology uses local feature descriptors, which are derived from the images and it was long thought that they could not be reverted back. However, recent work has demonstrated that under certain conditions reverse engineering attacks are possible and allow an adversary to reconstruct RGB images. This poses a potential risk to user privacy. We take this a step further and model potential adversaries using a privacy threat model. Subsequently, we show under controlled conditions a reverse engineering attack on sparse feature maps and analyze the vulnerability of popular descriptors including FREAK, SIFT and SOSNet. Finally, we evaluate potential mitigation techniques that select a subset of descriptors to carefully balance privacy reconstruction risk while preserving image matching accuracy; our results show that similar accuracy can be obtained when revealing less information.

Domain Adaptation of Learned Features for Visual Localization

We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have shown superior performance over classical hand-crafted local features. However, in a real-world scenario, there often exists a large domain gap between training and target images, which can significantly degrade the localization accuracy. While existing methods utilize a large amount of data to tackle the problem, we present a novel and practical approach, where only a few examples are needed to reduce the domain gap. In particular, we propose a few-shot domain adaptation framework for learned local features that deals with varying conditions in visual localization. The experimental results demonstrate the superior performance over baselines, while using a scarce number of training examples from the target domain.