REVIEW 10 cited by
EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this report, we present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge. Building upon the video-language two-tower model and leveraging our meticulously organized egocentric video data, we introduce a novel foundation model called EgoVideo. This model is specifically designed to cater to the unique characteristics of egocentric videos and provides strong support for our competition submissions. In the Ego4D challenges, we tackle various tasks including Natural Language Queries, Step Grounding, Moment Queries, Short-term Object Interaction Anticipation, and Long-term Action Anticipation. In addition, we also participate in the EPIC-Kitchens challenge, where we engage in the Action Recognition, Multiple Instance Retrieval, and Domain Adaptation for Action Recognition tracks. By adapting EgoVideo to these diverse tasks, we showcase its versatility and effectiveness in different egocentric video analysis scenarios, demonstrating the powerful representation ability of EgoVideo as an egocentric foundation model. Our codebase and pretrained models are publicly available at https://github.com/OpenGVLab/EgoVideo.
Forward citations
Cited by 10 Pith papers
-
Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction
An MLLM trained with auxiliary goal-prediction tasks and multi-token prediction achieves SOTA on COIN and CrossTask visual planning and matches SOTA on Ego4D LTA.
-
THOR: Thermal-guided Hand-Object Reasoning via Adaptive Vision Sampling
A thermal-guided adaptive sampling system cuts RGB video data by roughly 97% while keeping hand-activity recognition F1 around 95%, comparable to processing all frames.
-
Improving Keystep Recognition in Ego-Video via Dexterous Focus
Hand-focused, stabilized cropping of ego-video improves Ego-Exo4D fine-grained keystep recognition accuracy from 39.18% to 45.81% (hands only) and 47.75% (hands plus ego).
-
Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation
Fine-tuning video generators on driving data can improve visual fidelity while degrading how accurately the model predicts the movement of cars and pedestrians.
-
The Repeated-Stimulus Confound in Electroencephalography
The repeated-stimulus confound, where models are trained and tested on repeated presentations of identical stimuli, inflates reported EEG decoding accuracies by an estimated 4.46 to 7.42 percent.
-
EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization
EVA02-AT combines full-dimension spatial and temporal rotary position embeddings with a symmetric multi-similarity loss to improve egocentric video-text retrieval.
-
GazeNLQ @ Ego4D Natural Language Queries Challenge 2025
GazeNLQ adds contrastively pretrained gaze embeddings to a GroundNLQ-style grounding model, reporting 27.82 R1@0.3 on the Ego4D NLQ test split only when ensembled with GroundVQA.
-
OSGNet @ Ego4D Episodic Memory Challenge 2025
OSGNet, an early-fusion grounding model, wins all three Ego4D Episodic Memory Challenge tracks by converting localization tasks into retrieval problems.
-
Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025
A three-stage pipeline using the EgoVideo-V encoder, a verb-noun co-occurrence reranker, SAM2 hand-object features, and a fine-tuned Llama 2 model took first place in the Ego4D 2025 long-term action anticipation challenge.
-
Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision
A comprehensive review of cross-view video understanding that uses both first-person and third-person cameras, organized into a three-direction taxonomy with a dataset catalog and future research gaps.
Discussion (0). Sign in to comment.