The Devil is in the Spurious Correlation: Boosting Moment Retrieval via Temporal Dynamic Learning

• URL: http://arxiv.org/abs/2501.07305v1
• Date: Mon, 13 Jan 2025 13:13:06 GMT
• Title: The Devil is in the Spurious Correlation: Boosting Moment Retrieval via Temporal Dynamic Learning
• Authors: Xinyang Zhou, Fanyue Wei, Lixin Duan, Wen Li,
• Abstract summary: We propose a temporal dynamic learning approach for moment retrieval, where two strategies are designed to mitigate the spurious correlation. Our method establishes a new state-of-the-art performance on two popular benchmarks of moment retrieval, ie, QVHighlights and Charades-STA.
• Score: 23.357772759438806
• License:
• Abstract: Given a textual query along with a corresponding video, the objective of moment retrieval aims to localize the moments relevant to the query within the video. While commendable results have been demonstrated by existing transformer-based approaches, predicting the accurate temporal span of the target moment is currently still a major challenge. In this paper, we reveal that a crucial reason stems from the spurious correlation between the text queries and the moment context. Namely, the model may associate the textual query with the background frames rather than the target moment. To address this issue, we propose a temporal dynamic learning approach for moment retrieval, where two strategies are designed to mitigate the spurious correlation. First, we introduce a novel video synthesis approach to construct a dynamic context for the relevant moment. With separate yet similar videos mixed up, the synthesis approach empowers our model to attend to the target moment of the corresponding query under various dynamic contexts. Second, we enhance the representation by learning temporal dynamics. Besides the visual representation, text queries are aligned with temporal dynamic representations, which enables our model to establish a non-spurious correlation between the query-related moment and context. With the aforementioned proposed method, the spurious correlation issue in moment retrieval can be largely alleviated. Our method establishes a new state-of-the-art performance on two popular benchmarks of moment retrieval, \ie, QVHighlights and Charades-STA. In addition, the detailed ablation analyses demonstrate the effectiveness of the proposed strategies. Our code will be publicly available.

Related papers

• Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition [14.97527336050901]
  We propose a novel Temporal Sequence-Aware Model (TSAM) for few-shot action recognition (FSAR) It incorporates a sequential perceiver adapter into the pre-training framework, to integrate both the spatial information and the sequential temporal dynamics into the feature embeddings. Experimental results on five FSAR datasets demonstrate that our method set a new benchmark, beating the second-best competitors with large margins.
  arXiv  Detail & Related papers  (2024-08-22T15:13:27Z)
• Disentangle and denoise: Tackling context misalignment for video moment retrieval [16.939535169282262]
  Video Moment Retrieval aims to locate in-context video moments according to a natural language query. This paper proposes a cross-modal Context Denoising Network (CDNet) for accurate moment retrieval.
  arXiv  Detail & Related papers  (2024-08-14T15:00:27Z)
• Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement [72.7576395034068]
  Video Corpus Moment Retrieval (VCMR) is a new video retrieval task aimed at retrieving a relevant moment from a large corpus of untrimmed videos using a text query. We argue that effectively capturing the partial relevance between the query and video is essential for the VCMR task. For video retrieval, we introduce a multi-modal collaborative video retriever, generating different query representations for the two modalities. For moment localization, we propose the focus-then-fuse moment localizer, utilizing modality-specific gates to capture essential content.
  arXiv  Detail & Related papers  (2024-02-21T07:16:06Z)
• Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models [58.17315970207874]
  We propose a zero-shot method for adapting generalisable visual-textual priors from arbitrary VLM to facilitate moment-text alignment. Experiments conducted on three VMR benchmark datasets demonstrate the notable performance advantages of our zero-shot algorithm.
  arXiv  Detail & Related papers  (2023-09-01T13:06:50Z)
• Temporal Relevance Analysis for Video Action Models [70.39411261685963]
  We first propose a new approach to quantify the temporal relationships between frames captured by CNN-based action models. We then conduct comprehensive experiments and in-depth analysis to provide a better understanding of how temporal modeling is affected.
  arXiv  Detail & Related papers  (2022-04-25T19:06:48Z)
• Deconfounded Video Moment Retrieval with Causal Intervention [80.90604360072831]
  We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal interactions. We propose a causality-inspired VMR framework that builds structural causal model to capture the true effect of query and video content on the prediction.
  arXiv  Detail & Related papers  (2021-06-03T01:33:26Z)
• DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video [98.54696229182335]
  We study the task of temporal moment localization in a long untrimmed video using natural language query. Our key innovation is to learn a video feature embedding through a language-conditioned message-passing algorithm. A temporal sub-graph captures the activities within the video through time.
  arXiv  Detail & Related papers  (2020-10-13T09:50:29Z)
• Frame-wise Cross-modal Matching for Video Moment Retrieval [32.68921139236391]
  Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant moment in an untrimmed video, and 2) bridging the semantic gap between textual query and video contents. We propose an Attentive Cross-modal Relevance Matching model which predicts the temporal boundaries based on an interaction modeling.
  arXiv  Detail & Related papers  (2020-09-22T10:25:41Z)
• Local-Global Video-Text Interactions for Temporal Grounding [77.5114709695216]
  This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to extract a collection of mid-level features for semantic phrases in a text query. The proposed method effectively predicts the target time interval by exploiting contextual information from local to global.
  arXiv  Detail & Related papers  (2020-04-16T08:10:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.