An official website of the United States government
Temporal grounding, a.k.a video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a certain challenge to the compositional generalizability of existing methods. Recent studies establish the correspondence between videos and queries through a decompose-reconstruct manner to achieve compositional generalization. However, they only consider dominant primitives and build negative queries through random sampling and recombination, resulting in semantically implausible negatives that hinder the models from learning rational compositions. In addition, recent DETR-based methods still underperform in compositional temporal grounding, showing irrational saliency responses when given negative queries that have subtle differences from positive queries. To address these limitations, we first propose a large language model-driven method for negative query construction, utilizing GPT-3.5-Turbo to generate semantically plausible hard negative queries. Subsequently, we introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries to boost compositional generalization. Extensive experiments on two challenging benchmarks validate the effectiveness and generalizability of our proposed method. Our code is available at this https URL.
more »
« less
This content will become publicly available on October 8, 2025
SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding
Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a certain challenge to the compositional generalizability of existing methods. Recent studies establish the correspondence between videos and queries through a decompose-reconstruct manner to achieve compositional generalization. However, they only consider dominant primitives and build negative queries through random sampling and recombination, resulting in semantically implausible negatives that hinder the models from learning rational compositions. In addition, recent DETR-based methods still underperform in compositional temporal grounding, showing irrational saliency responses when given negative queries that have subtle differences from positive queries. To address these limitations, we first propose a large language modeldriven method for negative query construction, utilizing GPT-3.5 Turbo to generate semantically plausible hard negative queries. Subsequently, we introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries to boost compositional generalization. Extensive experiments on two challenging benchmarks validate the effectiveness and generalizability of our proposed method. Our code is available at https://github.com/zxccade/SHINE.
more »
« less
- Award ID(s):
- 2028626
- PAR ID:
- 10547774
- Publisher / Repository:
- Springer
- Date Published:
- Format(s):
- Medium: X
- Location:
- The 18th European Conference on Computer Vision ECCV 2024
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We introduce EQUI-VOCAL: a new system that automatically synthesizes queries over videos from limited user interactions. The user only provides a handful of positive and negative examples of what they are looking for. EQUI-VOCAL utilizes these initial examples and additional ones collected through active learning to efficiently synthesize complex user queries. Our approach enables users to find events without database expertise, with limited labeling effort, and without declarative specifications or sketches. Core to EQUI-VOCAL's design is the use of spatio-temporal scene graphs in its data model and query language and a novel query synthesis approach that works on large and noisy video data. Our system outperforms two baseline systems---in terms of F1 score, synthesis time, and robustness to noise---and can flexibly synthesize complex queries that the baselines do not support.more » « less
-
The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web. Existing keyword-based or content-based video retrieval methods usually determine what occurs in a video but not when and where. In this paper, we make an answer to the question of when and where by formulating a new task, namely spatio-temporal video re-localization. Specifically, given a query video and a reference video, spatio-temporal video re-localization aims to localize tubelets in the reference video such that the tubelets semantically correspond to the query. To accurately localize the desired tubelets in the reference video, we propose a novel warp LSTM network, which propagates the spatio-temporal information for a long period and thereby captures the corresponding long-term dependencies. Another issue for spatio-temporal video re-localization is the lack of properly labeled video datasets. Therefore, we reorganize the videos in the AVA dataset to form a new dataset for spatio-temporal video re-localization research. Extensive experimental results show that the proposed model achieves superior performances over the designed baselines on the spatio-temporal video re-localization task.more » « less
-
We address the problem of video moment localization with natural language, i.e. localizing a video segment described by a natural language sentence. While most prior work focuses on grounding the query as a whole, temporal dependencies and reasoning between events within the text are not fully considered. In this paper, we propose a novel Temporal Compositional Modular Network (TCMN) where a tree attention network first automatically decomposes a sentence into three descriptions with respect to the main event, context event and temporal signal. Two modules are then utilized to measure the visual similarity and location similarity between each segment and the decomposed descriptions. Moreover, since the main event and context event may rely on different modalities (RGB or optical flow), we use late fusion to form an ensemble of four models, where each model is independently trained by one combination of the visual input. Experiments show that our model outperforms the state-of-the-art methods on the TEMPO dataset.more » « less
-
null (Ed.)Recent advances in virtual reality cameras have contributed to a phenomenal growth of 360∘∘ videos. Estimating regions likely to attract user attention is critical for efficiently streaming and rendering 360∘∘ videos. In this article, we present a simple, novel, GPU-driven pipeline for saliency computation and virtual cinematography in 360∘∘ videos using spherical harmonics (SH). We efficiently compute the 360∘∘ video saliency through the spectral residual of the SH coefficients between multiple bands at over 60FPS for 4K resolution videos. Further, our interactive computation of spherical saliency can be used for saliency-guided virtual cinematography in 360∘∘ videos.more » « less
