pith. sign in

arxiv: 1804.09626 · v2 · pith:C6WJO2VVnew · submitted 2018-04-25 · 💻 cs.CV

Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos

classification 💻 cs.CV
keywords charades-egodatasetvideoactivityegocentricfirstthird-personannotations
0
0 comments X
read the original abstract

In Actor and Observer we introduced a dataset linking the first and third-person video understanding domains, the Charades-Ego Dataset. In this paper we describe the egocentric aspect of the dataset and present annotations for Charades-Ego with 68,536 activity instances in 68.8 hours of first and third-person video, making it one of the largest and most diverse egocentric datasets available. Charades-Ego furthermore shares activity classes, scripts, and methodology with the Charades dataset, that consist of additional 82.3 hours of third-person video with 66,500 activity instances. Charades-Ego has temporal annotations and textual descriptions, making it suitable for egocentric video classification, localization, captioning, and new tasks utilizing the cross-modal nature of the data.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning

    cs.CV 2026-05 unverdicted novelty 8.0

    EgoIntrospect provides the first egocentric dataset with self-annotations for internal state tasks and shows multimodal LLMs struggle to infer subjective states from combined signals.

  2. Imprint: Online Memory Compression for Long-Horizon Egocentric QA

    cs.CV 2026-07 unverdicted novelty 7.0

    Imprint compresses egocentric observations into interaction patterns via online memory compression, raising QA accuracy from 31.0% to 35.8% while cutting memory 2.3× and latency 11.8× on a seven-day benchmark.

  3. EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes

    cs.CV 2026-07 unverdicted novelty 7.0

    EgoGapBench shows humans reliably select egocentric actions in multi-agent scenes while MLLMs systematically choose other agents' actions, and standard egocentric training data fails to close the gap.

  4. UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning

    cs.CV 2026-06 unverdicted novelty 7.0

    UNIEGO creates a unified egocentric encoder by using proxy models to mediate multi-teacher distillation from ego-exo, multi-modal, and foundation-model sources, with selective distillation and convex initialization, a...

  5. Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

    cs.CV 2022-04 unverdicted novelty 7.0

    Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.

  6. TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living

    cs.CV 2026-06 unverdicted novelty 6.0

    TimeProVe proposes a propose-then-verify framework using lightweight action-based candidate evidence generation followed by targeted VLM verification for efficient long video temporal reasoning, achieving 7.3% improve...

  7. Harnessing Streaming Video in the Wild

    cs.CV 2026-06 unverdicted novelty 6.0

    Presents Streaming-Train-248K dataset, Streaming Harness system, and Streaming-Eval benchmark to enable VLMs for proactive, memory-equipped streaming video understanding.

  8. DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation

    cs.CV 2026-04 unverdicted novelty 6.0

    A scalable training-free pipeline using video segmentation, filtering, and off-the-shelf multimodal models creates DenseStep2M, a dataset of 100K videos and 2M detailed instructional steps that improves dense captioni...

  9. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

    cs.CV 2023-10 unverdicted novelty 6.0

    LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.

  10. Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction

    cs.CV 2026-04 conditional novelty 5.0

    Dynamic 3DGS models achieve lower PSNR on egocentric videos than exocentric ones, with the gap arising from static content reconstruction.

  11. LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding

    cs.CV 2025-01 unverdicted novelty 5.0

    LLaVA-Octopus introduces instruction-driven adaptive fusion of multiple visual projectors in a multimodal LLM to improve video understanding performance.