# Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025

arXiv: https://arxiv.org/abs/2506.02550 · HTML: https://mlsanity.com/paper/2506.02550/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?](https://mlsanity.com/paper/2307.16368/) (2023)
- [EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation](https://mlsanity.com/paper/2406.18070/) (2024)
- [PALM: Predicting Actions through Language Models](https://mlsanity.com/paper/2311.17944/) (2023)
- [Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding](https://mlsanity.com/paper/2503.09143/) (2025)
- [Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023](https://mlsanity.com/paper/2306.16545/) (2023)
- [Object-Shot Enhanced Grounding Network for Egocentric Video](https://mlsanity.com/paper/2505.04270/) (2025)
- [ObjectNLQ @ Ego4D Episodic Memory Challenge 2024](https://mlsanity.com/paper/2406.15778/) (2024)
- [HCQA @ Ego4D EgoSchema Challenge 2024](https://mlsanity.com/paper/2406.15771/) (2024)
- [HCQA-1.5 @ Ego4D EgoSchema Challenge 2025](https://mlsanity.com/paper/2505.20644/) (2025)
- [QueryMamba: A Mamba-Based Encoder-Decoder Architecture with a Statistical Verb-Noun Interaction Module for Video Action Forecasting @ Ego4D Long-Term Action Anticipation Challenge 2024](https://mlsanity.com/paper/2407.04184/) (2024)

## Built on by (most cited first, 9 of 9)

- [Spatial Understanding from Videos: Structured Prompts Meet Simulation Data](https://mlsanity.com/paper/2506.03642/) (2025)
- [Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation](https://mlsanity.com/paper/2508.01742/) (2025)
- [OSGNet @ Ego4D Episodic Memory Challenge 2025](https://mlsanity.com/paper/2506.03710/) (2025)
- [VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026](https://mlsanity.com/paper/2605.20901/) (2026)
- [JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026](https://mlsanity.com/paper/2605.20904/) (2026)
- [MARS: Technical Report for the CASTLE Challenge at EgoVis 2026](https://mlsanity.com/paper/2605.18176/) (2026)
- [TAP-JEPA: Frozen Future-Latent Probing and Two-Stage Score Fusion for EPIC-KITCHENS-100 Action Anticipation](https://mlsanity.com/paper/2606.00662/) (2026)
- [FROST-STA: Frozen Dense Features for the Ego4D Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2606.00694/) (2026)
- [Neuro-Symbolic Hierarchical Intention Anticipation in Human Behavior](https://mlsanity.com/paper/2609.17064/) (2026)

## Abstract (arXiv)

In this report, we present a novel three-stage framework developed for the Ego4D Long-Term Action Anticipation (LTA) task. Inspired by recent advances in foundation models, our method consists of three stages: feature extraction, action recognition, and long-term action anticipation. First, visual features are extracted using a high-performance visual encoder. The features are then fed into a Transformer to predict verbs and nouns, with a verb-noun co-occurrence matrix incorporated to enhance recognition accuracy. Finally, the predicted verb-noun pairs are formatted as textual prompts and input into a fine-tuned large language model (LLM) to anticipate future action sequences. Our framework achieves first place in this challenge at CVPR 2025, establishing a new state-of-the-art in long-term action prediction. Our code will be released at https://github.com/CorrineQiu/Ego4D-LTA-Challenge-2025.