Related papers: HERO-VQL: Hierarchical, Egocentric and Robust Visu…
Existing approaches to video understanding, mainly designed for short videos from a third-person perspective, are limited in their applicability in certain fields, such as robotics. In this paper, we delve into open-ended question-answering…
Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time. High-level…
The recently released Ego4D dataset and benchmark significantly scales and diversifies the first-person visual perception data. In Ego4D, the Visual Queries 2D Localization task aims to retrieve objects appeared in the past from the…
Robust 3D hand reconstruction in egocentric vision is challenging due to depth ambiguity, self-occlusion, and complex hand-object interactions. Prior methods mitigate these issues by scaling training data or adding auxiliary cues, but they…
Recent self-supervised learning (SSL) models trained on human-like egocentric visual inputs substantially underperform on image recognition tasks compared to humans. These models train on raw, uniform visual inputs collected from…
This technical report presents our solution, EgoAdapt (Egocentric Adaptation via Category, Calibration, and Consistency), to the CVPR 2026 HD-EPIC VQA challenge. HD-EPIC evaluates whether a vision-language model can reason over realistic…
Egocentric videos capture how humans manipulate objects and tools, providing diverse motion cues for learning object manipulation. Unlike the costly, expert-driven manual teleoperation commonly used in training Vision-Language-Action models…
Egocentric videos capture sequences of human activities from a first-person perspective and can provide rich multimodal signals. However, most current localization methods use third-person videos and only incorporate visual information. In…
Visual query localization (VQL) aims to predict the spatio-temporal response of the most recent occurrence in a sequence given a query. Currently, most research focuses on visual query localization in 2D videos, while its counterpart in 3D…
Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…
We introduce the lookahead-bounded Q-learning (LBQL) algorithm, a new, provably convergent variant of Q-learning that seeks to improve the performance of standard Q-learning in stochastic environments through the use of ``lookahead'' upper…
Transformer-based deep learning models have demonstrated exceptional performance in medical imaging by leveraging attention mechanisms for feature representation and interpretability. However, these models are prone to learning spurious…
We present EgoCOL, an egocentric camera pose estimation method for open-world 3D object localization. Our method leverages sparse camera pose reconstructions in a two-fold manner, video and scan independently, to estimate the camera pose of…
Understanding and answering questions based on a user's pointing gesture is essential for next-generation egocentric AI assistants. However, current Multimodal Large Language Models (MLLMs) struggle with such tasks due to the lack of…
Episodic memory retrieval enables wearable cameras to recall objects or events previously observed in video. However, existing formulations assume an "offline" setting with full video access at query time, limiting their applicability in…
Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoVLM, a vision-language model specifically designed to…
In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion…
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research efforts have quickly led to the design of novel algorithms able…
In this report, we present our approach for the Natural Language Query track and Goal Step track of the Ego4D Episodic Memory Benchmark at CVPR 2024. Both challenges require the localization of actions within long video sequences using…