MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914905894944768 |
|---|---|
| author | Yang, Nakyeong Kim, Minsung Yoon, Seunghyun Shin, Joongbo Jung, Kyomin |
| author_facet | Yang, Nakyeong Kim, Minsung Yoon, Seunghyun Shin, Joongbo Jung, Kyomin |
| contents | With the explosion of multimedia content, video moment retrieval (VMR), which aims to detect a video moment that matches a given text query from a video, has been studied intensively as a critical problem. However, the existing VMR framework evaluates video moment retrieval performance, assuming that a video is given, which may not reveal whether the models exhibit overconfidence in the falsely given video. In this paper, we propose the MVMR (Massive Videos Moment Retrieval for Faithfulness Evaluation) task that aims to retrieve video moments within a massive video set, including multiple distractors, to evaluate the faithfulness of VMR models. For this task, we suggest an automated massive video pool construction framework to categorize negative (distractors) and positive (false-negative) video sets using textual and visual semantic distance verification methods. We extend existing VMR datasets using these methods and newly construct three practical MVMR datasets. To solve the task, we further propose a strong informative sample-weighted learning method, CroCs, which employs two contrastive learning mechanisms: (1) weakly-supervised potential negative learning and (2) cross-directional hard-negative learning. Experimental results on the MVMR datasets reveal that existing VMR models are easily distracted by the misinformation (distractors), whereas our model shows significantly robust performance, demonstrating that CroCs is essential to distinguishing positive moments against distractors. Our code and datasets are publicly available: https://github.com/yny0506/Massive-Videos-Moment-Retrieval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_16701 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors Yang, Nakyeong Kim, Minsung Yoon, Seunghyun Shin, Joongbo Jung, Kyomin Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language With the explosion of multimedia content, video moment retrieval (VMR), which aims to detect a video moment that matches a given text query from a video, has been studied intensively as a critical problem. However, the existing VMR framework evaluates video moment retrieval performance, assuming that a video is given, which may not reveal whether the models exhibit overconfidence in the falsely given video. In this paper, we propose the MVMR (Massive Videos Moment Retrieval for Faithfulness Evaluation) task that aims to retrieve video moments within a massive video set, including multiple distractors, to evaluate the faithfulness of VMR models. For this task, we suggest an automated massive video pool construction framework to categorize negative (distractors) and positive (false-negative) video sets using textual and visual semantic distance verification methods. We extend existing VMR datasets using these methods and newly construct three practical MVMR datasets. To solve the task, we further propose a strong informative sample-weighted learning method, CroCs, which employs two contrastive learning mechanisms: (1) weakly-supervised potential negative learning and (2) cross-directional hard-negative learning. Experimental results on the MVMR datasets reveal that existing VMR models are easily distracted by the misinformation (distractors), whereas our model shows significantly robust performance, demonstrating that CroCs is essential to distinguishing positive moments against distractors. Our code and datasets are publicly available: https://github.com/yny0506/Massive-Videos-Moment-Retrieval. |
| title | MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2309.16701 |