HiERO-StepG augments weakly-supervised HiERO features with level agreement, temporal monotonicity, and noise reduction to reach 56.27% R@1 (IoU=0.3) and second place on the Ego4D Step Grounding challenge without procedure annotations.
OSGNet @ Ego4D episodic memory challenge 2025
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5years
2026 5representative citing papers
JFAA freezes a JEPA future-prediction model, adds a lightweight probe and ensemble, and wins the 2026 EK-100 action anticipation challenge.
A hybrid pipeline of OSGNet candidate generation followed by MLLM reranking secured first place in both the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge.
MARS converts long videos to captions and summaries, maintains modality-specific memories, and deploys an agent to select evidence or answer, placing second on the CASTLE Challenge leaderboard.
VISTA wins first place on the Ego4D Short-Term Object Interaction Anticipation challenge by combining spatial object proposals with temporal context via feature modulation and ROI fusion, followed by ensembling.
citing papers explorer
-
HiERO-StepG @ Ego4D Step Grounding Challenge: hierarchical activity understanding enables zero-shot step grounding
HiERO-StepG augments weakly-supervised HiERO features with level agreement, temporal monotonicity, and noise reduction to reach 56.27% R@1 (IoU=0.3) and second place on the Ego4D Step Grounding challenge without procedure annotations.
-
JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026
JFAA freezes a JEPA future-prediction model, adds a lightweight probe and ensemble, and wins the 2026 EK-100 action anticipation challenge.
-
OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026
A hybrid pipeline of OSGNet candidate generation followed by MLLM reranking secured first place in both the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge.
-
MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
MARS converts long videos to captions and summaries, maintains modality-specific memories, and deploys an agent to select evidence or answer, placing second on the CASTLE Challenge leaderboard.
-
VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026
VISTA wins first place on the Ego4D Short-Term Object Interaction Anticipation challenge by combining spatial object proposals with temporal context via feature modulation and ROI fusion, followed by ensembling.