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.
Charades-ego: A large-scale dataset of paired third and first person videos
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
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.
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 6roles
background 2polarities
background 2representative citing papers
Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.
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.
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 captioning, step grounding, and cross-modal retrieval.
LLaVA-Octopus introduces instruction-driven adaptive fusion of multiple visual projectors in a multimodal LLM to improve video understanding performance.
Dynamic 3DGS models achieve lower PSNR on egocentric videos than exocentric ones, with the gap arising from static content reconstruction.
citing papers explorer
-
EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning
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.
-
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
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.
-
DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation
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 captioning, step grounding, and cross-modal retrieval.
-
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
LLaVA-Octopus introduces instruction-driven adaptive fusion of multiple visual projectors in a multimodal LLM to improve video understanding performance.
-
Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction
Dynamic 3DGS models achieve lower PSNR on egocentric videos than exocentric ones, with the gap arising from static content reconstruction.