TRACE
TRACE copied to clipboard
Published
7 months ago
•
gyxxyg
gyxxyg
[ICLR 2025] TRACE: Temporal Grounding Video LLM via Casual Event Modeling
TRACE: Temporal Grounding Video LLM via Casual Event Modeling
If our project helps you, please give us a star ⭐ and cite our paper!
News
- 19/10/2024, 🔥 We release trace-retrieval by forcing the predicted timestamps to be align with the input frame timestamps. Results show trace-retrieval achieve better performance on dense video captioning tasks
- 10/10/2024, 🔥 Annotation files of training data are released!
- 10/10/2024, 🔥 Our model checkpoints and code are released!
TODO
- [x] Release the model checkpoints
- [x] Release the inference and evaluation code
- [x] Release the training and fine-tuning code
- [x] Release the training data
- [x] Release the TRACE-Retrieval, which outputs timestamps of input frames instead of predict unseen timestamps.
- [ ] Train TRACE models on more tasks.
Overview
In this work
- We model the videos by a series of events, and propose causal event modeling framework to capture videos' inherent structure.
- We present a novel task-interleaved video LLM model, TRACE, tailored to implement the causal event modeling framework through the sequential encoding/decoding of timestamps, salient scores, and textual captions.
Enviroments
We use NPU environments for training and fine-tuning, and use V100 GPUs for evaluation. The environment we use can be found in npu-requirements and gpu-requirements.
Model Zoo
| Checkpoints | Description | URL |
|---|---|---|
| Initialization | Weights initialized from VideoLLaMA2 | trace-init |
| Stage-1 | Model checkpoints trained after stage-1 | trace-stage1 |
| Stage-2 | Model checkpoints trained after stage-2 | trace |
| FT-Charades | Fine-tuned on Charades-STA dataset | trace-ft-charades |
| FT-Youcook2 | Fine-tuned on Youcook2 dataset | trace-ft-youcook2 |
| FT-QVHighlights | Fine-tuned on QVHighlights dataset | trace-ft-qvhighlights |
| TRACE-retrieval | Forcing the predicted timestamps to be align with input timestamps | trace-retrieval |
Inference and Evaluation
Please make sure the model and video paths are correct before running the code.
- Inference codes are provided in inference.py.
- Evaluation codes are provided in eval.sh
Training
Stage 1 training
bash TRACE/scripts/train/pretrain-128.sh
Stage 2 training
bash TRACE/scripts/train/sft-128.sh
Fine-tune on downsteam task
bash TRACE/scripts/train/sft-youcook2.sh
Please config the data and model paths before running the scrips.
Results
| Youcook2 (Zero-Shot) | CIDER | METEOR | SODA_c | F1 |
|---|---|---|---|---|
| TRACE | 8.1 | 2.8 | 2.2 | 22.4 |
| TRACE-retrieval | 8.3 | 2.9 | 2.3 | 24.1 |
| Charades-STA (Zero-Shot) | 0.3 | 0.5 | 0.7 | mIOU |
|---|---|---|---|---|
| TRACE | 58.6 | 40.3 | 19.4 | 38.7 |
| TRACE-retrieval | 57.9 | 37.4 | 17.3 | 37.4 |
| QVHighlights (Zero-Shot) | mAP | Hit@1 |
|---|---|---|
| TRACE | 26.8 | 42.7 |
| TRACE-retrieval | 27.9 | 44.3 |
| ActivityNet-DVC | CIDER | METEOR | SODA_c | F1 |
|---|---|---|---|---|
| TRACE | 25.9 | 6.0 | 6.4 | 39.3 |
| TRACE-retrieval | 25.7 | 5.9 | 6.5 | 40.1 |
| ActivityNet-MR | 0.3 | 0.5 | 0.7 | mIOU |
|---|---|---|---|---|
| TRACE | 54.0 | 37.7 | 24.0 | 39.0 |
| TRACE-retrieval | 54.4 | 39.8 | 24.9 | 40.2 |
Demo
Acknowledgement
We are grateful for the following awesome projects:
Bibliography
If you find this repository helpful for your project, please consider citing:
@misc{guo2024tracetemporalgroundingvideo,
title={TRACE: Temporal Grounding Video LLM via Causal Event Modeling},
author={Yongxin Guo and Jingyu Liu and Mingda Li and Xiaoying Tang and Qingbin Liu and Xi Chen},
year={2024},
eprint={2410.05643},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2410.05643},
}
gyxxyg