egocentric-video

Tag

Cards List
#egocentric-video

SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning

arXiv cs.AI · 2026-08-11 Cached

SCOUT introduces a recovery-aware agentic framework with an adaptive exploration-exploitation policy for ultra-long egocentric video reasoning, trained via UPS-GRPO, a uncertainty-prioritized RL method with turn-level advantage decomposition. It achieves state-of-the-art results on ultra-long egocentric benchmarks and remains competitive on shorter long-video settings.

0 favorites 0 likes
#egocentric-video

SERUM: State Extraction and Refinement for User Modeling

arXiv cs.LG · 2026-08-03 Cached

Presents SERUM, a multi-pass framework that extracts structured behavioral models of user actions and intents from raw egocentric video using hierarchical VLM annotation, reducing hallucinations and producing interpretable process models without manual annotation.

0 favorites 0 likes
#egocentric-video

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video

Hugging Face Daily Papers · 2026-07-20 Cached

ReViV is a unified framework for holistic egocentric 4D reconstruction that simultaneously reconstructs viewer (body, hand, gaze) and view (depth, camera trajectory) dynamics from a single monocular RGB video using a Masked Generative Egocentric Transformer, achieving state-of-the-art accuracy and efficiency.

0 favorites 0 likes
#egocentric-video

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

Hugging Face Daily Papers · 2026-07-13 Cached

Vinci2 presents a proactive assistance system for continuous egocentric videos, introducing a new benchmark EgoServe and a memory-augmented agent EgoMemo that determines when to intervene based on temporal context.

0 favorites 0 likes
#egocentric-video

@RekaAILabs: CS2-10k is now available on @huggingface 600,000+ egocentric gameplay videos. 10,000+ hours. Every frame paired with th…

X AI KOLs Following · 2026-06-30 Cached

Reka AI Labs releases CS2-10k, a large dataset of over 600,000 egocentric gameplay videos with 10,000+ hours of frame-level keyboard, mouse, and 3D position data, available on Hugging Face for world models, action-conditioned video generation, and egocentric navigation research.

0 favorites 0 likes
#egocentric-video

HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining

Hugging Face Daily Papers · 2026-06-18 Cached

This paper finds that egocentric human video, when processed with a filtering and labeling pipeline, can outperform teleoperated real-robot data for pretraining embodied foundation models, achieving lower validation loss and higher success rates on real-robot tasks.

0 favorites 0 likes
#egocentric-video

ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining

Hugging Face Daily Papers · 2026-06-15 Cached

ACE-EGO-0 is a unified Vision-Language-Action pretraining framework that leverages egocentric human videos and robot trajectories via a reliability-aware training objective, achieving state-of-the-art on embodied AI benchmarks.

0 favorites 0 likes
#egocentric-video

EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video

Hugging Face Daily Papers · 2026-06-15 Cached

EgoPhys introduces a framework to construct deformable physical digital twins from egocentric RGB video using generalizable priors and a compact codebook, enabling zero-shot generalization to unseen objects without per-spring optimization. The system is demonstrated on a real robot, showing that egocentric human play video can serve as internal world representation for deformable-object planning.

0 favorites 0 likes
#egocentric-video

Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

arXiv cs.AI · 2026-06-12 Cached

This paper introduces V-RAGBench, a benchmark for evaluating retrieval-augmented generation over long egocentric videos, and CARVE, a method that adaptively selects retrieval configurations per chunk to improve VideoRAG performance.

0 favorites 0 likes
#egocentric-video

Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning

Hugging Face Daily Papers · 2026-06-10 Cached

A training-free framework for spatial reasoning from egocentric videos that enables revisiting conclusions through synthesized novel-view videos generated from predicted 3D geometry.

0 favorites 0 likes
#egocentric-video

ActiveMimic: Egocentric Video Pretraining with Active Perception

Hugging Face Daily Papers · 2026-06-04 Cached

ActiveMimic is a pretraining framework that recovers camera and wrist trajectories from egocentric human video to model active perception as a viewpoint action, enabling robot pretraining that matches the performance of models trained directly on robot data.

0 favorites 0 likes
#egocentric-video

SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory

Hugging Face Daily Papers · 2026-05-30

SuperMemory-VQA is a new egocentric VQA benchmark featuring 52.9 hours of AI-glasses footage and 4,853 QA pairs designed to evaluate AI assistants on long-horizon memory tasks spanning object recall, intent, timelines, and conversations. Benchmarking reveals existing agentic frameworks and LLMs remain far from reliable on these real-world memory challenges.

0 favorites 0 likes
#egocentric-video

This startup is betting India’s gig economy can train the world’s robots

TechCrunch AI · 2026-05-26 Cached

Human Archive, a Silicon Valley startup, has raised $8.2 million to collect first-person video data from Indian gig workers to train robots for physical tasks. Despite rejections from major home services platforms, the company is partnering with other firms in the sector.

0 favorites 0 likes
#egocentric-video

AI-Assisted Competency Assessment from Egocentric Video in Simulation-Based Nursing Education

arXiv cs.AI · 2026-05-22 Cached

This paper investigates using vision-language models to assess nursing competency from egocentric video during simulation, finding that recognition accuracy inversely relates to competency level, suggesting a pedagogically informative signal.

0 favorites 0 likes
#egocentric-video

Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning

arXiv cs.AI · 2026-05-14 Cached

Ego2World converts egocentric cooking videos (HD-EPIC) into executable symbolic worlds with graph-transition rules, enabling evaluation of belief-state planning under partial observation. Experiments show that belief memory improves task completion, suggesting it should be a first-class target in embodied agent evaluation.

0 favorites 0 likes
#egocentric-video

PhysBrain 1.0 Technical Report

Hugging Face Daily Papers · 2026-05-14 Cached

PhysBrain 1.0 is a technical report presenting a method that uses human egocentric video to generate physical commonsense supervision for vision-language-action models, achieving state-of-the-art results on embodied control benchmarks including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa.

0 favorites 0 likes
← Back to home

Submit Feedback